Search

Few‐shot knowledge graph (KG) reasoning is the main focus in the field of knowledge graph reasoning. In order to expand the application fields of the knowledge graph, a large number of studies are based on a large number of training samples. However, we have learnt that there are actually many missing relationships or entities in the knowledge graph, and in most cases, there are not many training instances when implementing new relationships. To tackle it, in this study, the authors aim to predict a new entity given few reference instances, even only one training instance. A few‐shot learning framework based on a hybrid attention mechanism is proposed. The framework employs traditional embedding models to extract knowledge, and uses an attenuated attention network and a self‐attention mechanism to obtain the hidden attributes of entities. Thus, it can learn a matching metric by considering both the learnt embeddings and one‐hop graph structures. The experimental results present that the model has achieved significant performance improvements on the NELL‐One and Wiki‐One datasets.

Probabilistic inductive logic programming (PILP) is a statistical relational learning technique which extends inductive logic programming by considering probabilistic data. The ability to use probabilities to represent uncertainty comes at the cost of an exponential evaluation time when composing theories to model the given problem. For this reason, PILP systems rely on various pruning strategies in order to reduce the search space. However, to the best of the authors’ knowledge, there has been no systematic analysis of the different pruning strategies, how they impact the search space and how they interact with one another. This work presents a unified representation for PILP pruning strategies which enables end-users to understand how these strategies work both individually and combined and to make an informed decision on which pruning strategies to select so as to best achieve their goals. The performance of pruning strategies is evaluated both time and quality-wise in two state-of-the-art PILP systems with datasets from three different domains. Besides analysing the performance of the pruning strategies, we also illustrate the utility of PILP in one of the application domains, which is a real-world application.

Improving the academic and social outcomes of boys–specifically boys from low-SES backgrounds–remains of international importance. With this in mind, research continues to document the ways in which relational learning is integral for the well-being of students, specifically those students in disadvantaged school contexts. This paper focuses on relational learning as an important resource that marginalised young men draw upon, informing their future orientation towards higher education beyond their compulsory schooling. Within studies of men and masculinities, the affective turn has recently played a significant role in how we understand men as relational. Focusing upon a cohort of boys from some of the poorest urban regions in Australia, the paper addresses how their affective relationships with teachers contribute not only to their conception of themselves as learners but also their general well-being, confidence and aspirations. Through highlighting two trends in the data–Teacher as Persistent Nurturer and Teacher as Supporter–the research presented extends two lines of inquiry. First, understanding student–teacher relationships in disadvantaged educational contexts and, second, the importance of positive student–teacher relationships for working-class boys who have historically disengaged from their education.

This paper explores how senior executives learn (not) to be different in Action Learning Set spaces (ALSS) as part of a business school Executive Education programme. We take a relational social constructionist approach in an empirical study and analyse senior executives’ narratives. This illuminates how executives co-construct action learning set spaces of openness, honesty, confidentiality and challenge and engage in relational processes of learning, vulnerability and identity work. In doing so executives learn to be different in relation to dominant discourses and norms of what it means to be a leader or manager which is personified through claims of vulnerability in the education context. Executives make sense of and work through learning to be comfortable with being uncomfortable, practising learning over time in a ‘safe enough’ space. We offer insights into identity work spaces, as leaders reconceptualise vulnerability as positive and as strength and how claiming vulnerability can defuse the power of fear and negative connotations often associated with vulnerability. With agency, executives express feeling better equipped to decide how and when to be different (vulnerability) or not be different (invulnerability) in their organisations. Practically we extend consciousness to the value of vulnerability for leader and manager identity and learning.

In this article, we describe a personalized approach to meeting individual and community health needs that foregrounds relational learning. This article analyzes how relational approaches to learning expand participants' objectives and result in more enduring learning. We report on mixed methods data from interviews, focus groups, surveys, and goal setting and monitoring. Analyses reveal that relationships de confianza served as a central tool in supporting participants' agency to enact change across scales of practice to promote the health of themselves, their families, and their communities.

We examine the role of learning firm-specific advantages of small and medium size (SME) service firms in their internationalization. We focus on technical services that have received limited scholarly attention. We theorize that innovative born global firms build a set of capabilities in market, internal and relational learning that will provide new knowledge configurations to undertake technical and administrative innovations. Adopting an organizational sub-system view, we posit that market learning drives other learning capabilities in the firm to contribute collectively to innovation, and in turn, international market outcomes. The findings of our study of US born global SMEs support this theorization. Market-learning capability operates in a complex set of relationships with other learning capabilities in its contribution to innovation. Interestingly, relative to technical innovation, administrative innovation makes a prominent contribution to international market outcomes. We discuss implications of our findings for theory and practice and provide future research directions.

Data preprocessing is an important component of machine learning pipelines, which requires ample time and resources. An integral part of preprocessing is data transformation into the format required by a given learning algorithm. This paper outlines some of the modern data processing techniques used in relational learning that enable data fusion from different input data types and formats into a single table data representation, focusing on the propositionalization and embedding data transformation approaches. While both approaches aim at transforming data into tabular data format, they use different terminology and task definitions, are perceived to address different goals, and are used in different contexts. This paper contributes a unifying framework that allows for improved understanding of these two data transformation techniques by presenting their unified definitions, and by explaining the similarities and differences between the two approaches as variants of a unified complex data transformation task. In addition to the unifying framework, the novelty of this paper is a unifying methodology combining propositionalization and embeddings, which benefits from the advantages of both in solving complex data transformation and learning tasks. We present two efficient implementations of the unifying methodology: an instance-based PropDRM approach, and a feature-based PropStar approach to data transformation and learning, together with their empirical evaluation on several relational problems. The results show that the new algorithms can outperform existing relational learners and can solve much larger problems., Accepted in MLJ

Artificial Intelligence agents are required to learn from their surroundings and to reason about the knowledge that has been learned in order to make decisions. While state-of-the-art learning from data typically uses sub-symbolic distributed representations, reasoning is normally useful at a higher level of abstraction with the use of a first-order logic language for knowledge representation. As a result, attempts at combining symbolic AI and neural computation into neural-symbolic systems have been on the increase. In this paper, we present Logic Tensor Networks (LTN), a neurosymbolic formalism and computational model that supports learning and reasoning through the introduction of a many-valued, end-to-end differentiable first-order logic called Real Logic as a representation language for deep learning. We show that LTN provides a uniform language for the specification and the computation of several AI tasks such as data clustering, multi-label classification, relational learning, query answering, semi-supervised learning, regression and embedding learning. We implement and illustrate each of the above tasks with a number of simple explanatory examples using TensorFlow 2. Keywords: Neurosymbolic AI, Deep Learning and Reasoning, Many-valued Logic., 68 pages, 28 figures, 6 tables

This paper positions Open Educational Practices (OEP) as adding significant value to pandemic-era online learning. Much of online learning during Covid was characterised as being low quality, and an emphasis on providing care began to override the impact that reformed pedagogy could have in caring for students. Concepts of Indigenous Knowledge Authority, consent, collaboration, situated knowledge in communities of practice can help to frame how caring pedagogy and cognitive compassion can be cultivated. This paper shares the redevelopment and evaluation of a unit of learning called Cultural Capabilities amidst pandemic pedagogy rhetoric in which care for knowledge and online learning is discussed. The focus of this study was to refine the concept of care and compassion pedagogy whilst developing a sustainable model for caring for knowledge as higher education professionals. The learning design process and emergent outcomes of the evaluation for learning design are shared. Student feedback showed significant appreciation for the learning design, affective experiences of the deeper learning facilitated by OEP and relational learning. Australian Covid lockdowns allowed for new approaches to open engagement to practical care and compassionate practices for learning and knowledges. This paper argues that successful OEP can be cultivated with cognitive compassion as a focus instead of a panic-induced care narrative for more sustainable caring academic and professional capabilities as we continue to learn online.

University-industry collaboration (UIC) is increasingly seen as an important driver of economic growth, but knowledge on its implementation mechanisms is still limited especially in developing countries. This constrains the capacity of those countries to design adequate policies and strategies to foster such interactions. This paper provides information about the extent to which academic staff from Tertiary Education Institutions (TEIs) in Rwanda interact with industry. It identifies the factors underlying their propensity to engage in interactions and the barriers or challenges faced. Data were collected from 334 academic staff permanently employed by 17 Higher Education Institutions in Rwanda. Results indicate a low level of interaction except in some informal channels arguably less inclined to foster relational learning and knowledge creation. Regression analyses indicated that the type of institution and the academic grades are significantly associated with the propensity of academic staff to interact with industry. In addition, four main barriers to interaction are identified and they are all linked to poor support from the government and the universities. Therefore, the study recommends the elaboration of explicit policies and strategies at country and institutional levels to set the stage for such indispensable interactions.

The objective of this paper is to review the state-of-the-art of statistical relational learning (SRL) models developed to deal with machine learning and data mining in relational domains in presence of missing, partially observed, and/or noisy data. It starts by giving a general overview of conventional graphical models, first-order logic and inductive logic programming approaches as needed for background. The historical development of each SRL key model is critically reviewed. The study also focuses on the practical application of SRL techniques to a broad variety of areas and their limitations.

Pedestrian attribute recognition in surveillance is a challenging task due to poor image quality, significant appearance variations and diverse spatial distribution of different attributes. This paper treats pedestrian attribute recognition as a sequential attribute prediction problem and proposes a novel visual-semantic graph reasoning framework to address this problem. Our framework contains a spatial graph and a directed semantic graph. By performing reasoning using the Graph Convolutional Network (GCN), one graph captures spatial relations between regions and the other learns potential semantic relations between attributes. An end-to-end architecture is presented to perform mutual embedding between these two graphs to guide the relational learning for each other. We verify the proposed framework on three large scale pedestrian attribute datasets including PETA, RAP, and PA100k. Experiments show superiority of the proposed method over state-of-the-art methods and effectiveness of our joint GCN structures for sequential attribute prediction.

This paper outlines RSR, a relational social recommendation approach applied to a social graph comprised of relational entity profiles. RSR uses information extraction and learning methods to obtain relational facts about persons of interest from the Web, and generates an associative entity-relation social network from their extracted personal profiles. As a case study, we consider the task of peer recommendation at scientific conferences. Given a social graph of scholars, RSR employs graph similarity measures to rank conference participants by their relatedness to a user. Unlike other recommender systems that perform social rankings, RSR provides the user with detailed supporting explanations in the form of relational connecting paths. In a set of user studies, we collected feedbacks from participants onsite of scientific conferences, pertaining to RSR quality of recommendations and explanations. The feedbacks indicate that users appreciate and benefit from RSR explainability features. The feedbacks further indicate on recommendation serendipity using RSR, having it recommend persons of interest who are not apriori known to the user, oftentimes exposing surprising inter-personal associations. Finally, we outline and assess potential gains in recommendation relevance and serendipity using path-based relational learning within RSR.

Handling relational data streams has become a crucial task, given the availability of pervasive sensors and Internet-produced content, such as social networks and knowledge graphs. In a relational environment, this is a particularly challenging task, since one cannot assure that the streams of examples are independent along the iterations. Thus, most relational learning systems are still designed to learn only from closed batches of data. Furthermore, in case there is a previously acquired model, these systems either would discard it or assuming it as correct. In this work, we propose an online relational learning algorithm that can handle continuous, open-ended streams of relational examples as they arrive. We employ techniques of theory revision to take advantage of the previously acquired model as a starting point, by finding where it should be modified to cope with the new examples, and automatically update it. We rely on the Hoeffding’s bound statistical theory to decide if the model must, in fact, be updated in accordance with the new examples. The proposed algorithm is built upon ProPPR statistical relational language, aiming at contemplating the uncertainty inherent to real data. Experimental results in social networks and entity co-reference datasets show the potential of the proposed approach compared to other relational learners.

Online structure learning approaches, such as those stemming from statistical relational learning, enable the discovery of complex relations in noisy data streams. However, these methods assume the existence of fully-labelled training data, which is unrealistic for most real-world applications. We present a novel approach for completing the supervision of a semi-supervised structure learning task. We incorporate graph-cut minimisation, a technique that derives labels for unlabelled data, based on their distance to their labelled counterparts. In order to adapt graph-cut minimisation to first order logic, we employ a suitable structural distance for measuring the distance between sets of logical atoms. The labelling process is achieved online (single-pass) by means of a caching mechanism and the Hoeffding bound, a statistical tool to approximate globally-optimal decisions from locally-optimal ones. We evaluate our approach on the task of composite event recognition by using a benchmark dataset for human activity recognition, as well as a real dataset for maritime monitoring. The evaluation suggests that our approach can effectively complete the missing labels and eventually, improve the accuracy of the underlying structure learning system.

Recommender systems have played a critical role in many web applications to meet user's personalized interests and alleviate the information overload. In this survey, we review the development of recommendation frameworks with the focus on heterogeneous relational learning, which consists of different types of dependencies among users and items. The objective of this task is to map heterogeneous relational data into latent representation space, such that the structural and relational properties from both user and item domain can be well preserved. To address this problem, recent research developments can fall into three major lines: social recommendation, knowledge graph-enhanced recommender system, and multi-behavior recommendation. We discuss the learning approaches in each category, such as matrix factorization, attention mechanism and graph neural networks, for effectively distilling heterogeneous contextual information. Finally, we present an exploratory outlook to highlight several promising directions and opportunities in heterogeneous relational learning frameworks for recommendation., Comment: Published as a paper in IJCAI 2021

Data on software vulnerabilities, products and exploits is typically collected from multiple non-structured sources. Valuable information, e.g., on which products are affected by which exploits, is conveyed by matching data from those sources, i.e., through their relations. In this paper, we leverage this simple albeit unexplored observation to introduce a statistical relational learning (SRL) approach for the analysis of vulnerabilities, products and exploits. In particular, we focus on the problem of determining the existence of an exploit for a given product, given information about the relations between products and vulnerabilities, and vulnerabilities and exploits, focusing on Industrial Control Systems (ICS), the National Vulnerability Database and ExploitDB. Using RDN-Boost, we were able to reach an AUC ROC of 0.83 and an AUC PR of 0.69 for the problem at hand. To reach that performance, we indicate that it is instrumental to include textual features, e.g., extracted from the description of vulnerabilities, as well as structured information, e.g., about product categories. In addition, using interpretable relational regression trees we report simple rules that shed insight on factors impacting the weaponization of ICS products.

To determinate the role of organizational learning across project-based organizations, this study applies a micro-level perspective of organizational learning theory to the social constructivist approach to address relational learning information collaboration that takes into account a strategic perspective involving the development of collective knowledge. The sample was distributed to 180 individuals from different targeted private universities from a total population of 1400 private universities that operate through collaborative ventures to test the research hypotheses. We were able to use 168 surveys in our statistical study after deleting 12 surveys with incorrect responses. Furthermore, value building continues to play a role in bridging the gap between corporate development and long-term strategic growth. Furthermore, exploratory purpose shows a major mediation function in inter-organizational learning, as well as the potential to sustain long-term partnerships with partners, as a beneficial result of partner diversity as a moderate factor. Information convergence was shown to be strongly linked for strategic achievement, as was corporate culture, competences and capabilities, and team cooperation

COVID-19 pandemic has affected nearly every aspect of life. Observing online the spread of the virus can offer a complementary view to the cases that are daily officially recorded and reported. In this article, we present an approach that exploits information available on social media to predict whether a patient has been infected with COVID-19. Our approach is based on a Bayesian model that is trained using data collected online. Then the trained model can be used for evaluating the possibility that new patients are infected with COVID-19. The experimental evaluation presented shows the high quality of our approach. In addition, our model can be incrementally retrained, so that it becomes more robust in an efficient way.

A large body of machine learning and AI is focused on learning models composed of (probabilistic) logical rules, i.e., relational models, over relational databases and knowledge bases. To learn effective relational models over the huge space of possible ones efficiently, users of the current learning systems must restrict the structure of the candidate models using language bias. ML experts have to spend a long time inspecting the data and performing many rounds of trial and error to develop an effective language bias. We propose AutoBias, a system that leverages information in the underlying data to generate the language bias. As its induced language bias may not restrict the set of candidate models as tightly as the manually-written ones, learning may not scale to large datasets. Thus, we design novel and efficient methods to sample and learn effective relational models over large data. Our extensive empirical study shows that AutoBias delivers the same accuracy as using manually-written language bias by imposing only a slight overhead on the learning time.

Humans and other animals are capable of inferring never-experienced relations (e.g., A>C) from other relational observations (e.g., A>B and B>C). The processes behind such transitive inference are subject to intense research. Here, we demonstrate a new aspect of relational learning, building on previous evidence that transitive inference can be accomplished through simple reinforcement learning mechanisms. We show in simulations that inference of novel relations benefits from an asymmetric learning policy, where observers update only their belief about the winner (or loser) in a pair. Across 4 experiments (n=145), we find substantial empirical support for such asymmetries in inferential learning. The learning policy favoured by our simulations and experiments gives rise to a compression of values which is routinely observed in psychophysics and behavioural economics. In other words, a seemingly biased learning strategy that yields well-known cognitive distortions can be beneficial for transitive inferential judgments.

Traditional Machine Learning (ML) models have had limited success in predicting Coronoavirus-19 (COVID-19) outcomes using Electronic Health Record (EHR) data partially due to not effectively capturing the inter-connectivity patterns between various data modalities. In this work, we propose a novel framework that utilizes relational learning based on a heterogeneous graph model (HGM) for predicting mortality at different time windows in COVID-19 patients within the intensive care unit (ICU). We utilize the EHRs of one of the largest and most diverse patient populations across five hospitals in major health system in New York City. In our model, we use an LSTM for processing time varying patient data and apply our proposed relational learning strategy in the final output layer along with other static features. Here, we replace the traditional softmax layer with a Skip-Gram relational learning strategy to compare the similarity between a patient and outcome embedding representation. We demonstrate that the construction of a HGM can robustly learn the patterns classifying patient representations of outcomes through leveraging patterns within the embeddings of similar patients. Our experimental results show that our relational learning-based HGM model achieves higher area under the receiver operating characteristic curve (auROC) than both comparator models in all prediction time windows, with dramatic improvements to recall.

Aiming at expanding few-shot relations' coverage in knowledge graphs (KGs), few-shot knowledge graph completion (FKGC) has recently gained more research interests. Some existing models employ a few-shot relation's multi-hop neighbor information to enhance its semantic representation. However, noise neighbor information might be amplified when the neighborhood is excessively sparse and no neighbor is available to represent the few-shot relation. Moreover, modeling and inferring complex relations of one-to-many (1-N), many-to-one (N-1), and many-to-many (N-N) by previous knowledge graph completion approaches requires high model complexity and a large amount of training instances. Thus, inferring complex relations in the few-shot scenario is difficult for FKGC models due to limited training instances. In this paper, we propose a few-shot relational learning with global-local framework to address the above issues. At the global stage, a novel gated and attentive neighbor aggregator is built for accurately integrating the semantics of a few-shot relation's neighborhood, which helps filtering the noise neighbors even if a KG contains extremely sparse neighborhoods. For the local stage, a meta-learning based TransH (MTransH) method is designed to model complex relations and train our model in a few-shot learning fashion. Extensive experiments show that our model outperforms the state-of-the-art FKGC approaches on the frequently-used benchmark datasets NELL-One and Wiki-One. Compared with the strong baseline model MetaR, our model achieves 5-shot FKGC performance improvements of 8.0% on NELL-One and 2.8% on Wiki-One by the metric Hits@10., Comment: The full version of a paper accepted to SIGIR 2021

In real scenarios, a multilingual model trained to solve NLP tasks on a set of languages can be required to support new languages over time. Unfortunately, the straightforward retraining on a dataset containing annotated examples for all the languages is both expensive and time-consuming, especially when the number of target languages grows. Moreover, the original annotated material may no longer be available due to storage or business constraints. Re-training only with the new language data will inevitably result in Catastrophic Forgetting of previously acquired knowledge. We propose a Continual Learning strategy that updates a model to support new languages over time, while maintaining consistent results on previously learned languages. We define a Teacher-Student framework where the existing model “teaches” to a student model its knowledge about the languages it supports, while the student is also trained on a new language. We report an experimental evaluation in several tasks including Sentence Classification, Relational Learning and Sequence Labeling.

Relational learning addresses the task of learning models or patterns from relational data. Complementary to relational learning approaches that learn directly from relational data, developed in the Inductive Logic Programming research community, this chapter addresses the propositionalization approach of first transforming a relational database into a single-table representation, followed by a model or pattern construction step using a standard machine learning algorithm.

Zero-Shot Action Recognition (ZSAR) aims to transfer knowledge from a source domain to a target domain so that the unlabelled action can be inferred and recognized. However, previous methods often fail to highlight information about the salient factors of the video sequence. In the process of cross-modal search, information redundancy will weaken the association of key information among different modes. In this paper, we propose Dual Visual Attention Matching Network (DVAMN) to distill sparse saliency information from action video. We utilize dual visual attention mechanism and spatiotemporal Gated Recurrent Units (GRU) to establish irredundant and sparse visual space, which can boost the performance of the cross-modal recognition. Relational learning strategy is employed for final classification. Moreover, the whole network is trained in an end-to-end manner. Experiments on both the HMDB51 and the UCF101 datasets show that the proposed architecture achieves state-of-the-art results among methods using only spatial and temporal video features in zero-shot action recognition.

Multi-label classification of chest X-ray images is frequently performed using discriminative approaches, i.e. learning to map an image directly to its binary labels. Such approaches make it challenging to incorporate auxiliary information such as annotation uncertainty or a dependency among the labels. Building towards this, we propose a novel knowledge graph reformulation of multi-label classification, which not only readily increases predictive performance of an encoder but also serves as a general framework for introducing new domain knowledge. Specifically, we construct a multi-modal knowledge graph out of the chest X-ray images and its labels and pose multi-label classification as a link prediction problem. Incorporating auxiliary information can then simply be achieved by adding additional nodes and relations among them. When tested on a publicly-available radiograph dataset (CheXpert), our relational-reformulation using a naive knowledge graph outperforms the state-of-art by achieving an area-under-ROC curve of 83.5%, an improvement of "sim 1" over a purely discriminative approach.

This chapter provides an introduction to standard machine learning approaches that learn from tabular data representations, followed by an outline of approaches using various other data types addressed in this monograph: texts, relational databases, and networks (graphs, knowledge graphs, and ontologies). We first briefly sketch the historical outline of the research area, establish the basic terminology, and categorize learning tasks in Sect. 2.1. Section 2.2 provides a short introduction to text mining. Section 2.3 introduces relational learning techniques, followed by a brief introduction to network analysis, including semantic data mining, in Sect. 2.4. The means for evaluating the performance of machine learning algorithms, when used for prediction and rule quality estimation, are outlined in Sect. 2.5. We outline selected data mining techniques and platforms in Sect. 2.6. Finally, Sect. 2.7 presents the implemented software that allows for running selected methods on illustrative examples.

Lately there has been an increasing interest in learning object affordances. This is particularly to address human activity understanding and intention recognition for household robots. However, most existing approaches do not concentrate on imbibing new perceptual models of inferring affordances from visual input. Such models are key for object usage by household robots. Towards this goal, this paper introduces a knowledge based approach to inferring semantic object affordances. This is achieved by integrating ontology and qualitative reasoning within a statistical relational learning scheme. Encouraging results are obtained for the CAD-120 dataset consisting of indoor household activity videos involving human-object interactions.

Purpose This paper aims to increase related knowledge across personal, social and ecological dimensions of sustainability and how it can be applied to support transformative learning. Design/methodology/approach The paper provides a reflexive case study of the design, content and impact of a course on eco-justice that integrates relational learning with an equity and justice lens. The reflexive case study provides a critical, exploratory self-assessment, including interviews, group discussions and surveys with key stakeholders and course participants. Findings The results show how relational approaches can support transformative learning for sustainability and provide concrete practices, pathways and recommendations for curricula development that other universities/training institutions could follow or learn from. Originality/value Sustainability research, practice and education generally focuses on structural or systemic factors of transformation (e.g. technology, governance and policy) without due consideration as to how institutions and systems are shaping and shaped by the transformation of personal agency and subjectivity. This presents a vast untapped and under-studied potential for addressing deep leverage points for change by using a relational approach to link personal, societal and ecological transformations for sustainability.

Fast propagation, ease-of-access, and low cost have made social media an increasingly popular means for news consumption. However, this has also led to an increase in the preponderance of fake news. Widespread propagation of fake news can be detrimental to society, and this has created enormous interest in fake news detection on social media. Many approaches to fake news detection use the news content, social context, or both. In this work, we look at fake news detection as a problem of estimating the credibility of both the news publishers and users that propagate news articles. We introduce a new approach called the credibility score-based model that can jointly infer fake news and credibility scores for publishers and users. We use a state-of-the-art statistical relational learning framework called probabilistic soft logic to perform this joint inference effectively. We show that our approach is accurate at both fake news detection and inferring credibility scores. Further, our model can easily integrate any auxiliary information that can aid in fake news detection. Using the FakeNewsNet dataset, we show that our approach significantly outperforms previous approaches at fake news detection by up to 10% in recall and 4% in accuracy. Furthermore, the credibility scores learned for both publishers and users are representative of their true behavior.

Background and objectives There is a need to ensure that the future healthcare workforce has the necessary knowledge and skills to deliver high quality compassionate care to the increasing number of people with dementia. Our programme has been set up to address this challenge. In the programme, undergraduate healthcare students (nursing, medical and paramedic) visit a family (person with dementia and their carer) in pairs over a 2-year period. This qualitative study sought to understand the student experience of the programme. Methods Participants were undergraduate healthcare students who were undertaking our programme at two universities. We sampled for variation in the student participants in order to generate a framework for understanding the student experience of the programme. Students were invited to take part in the qualitative study, and written consent was obtained. Interviews and focus group transcripts were analysed using thematic analysis. Results Thirty-nine (nursing, medical and paramedic) student participants took part in individual in-depth qualitative interviews and 38 took part in five focus groups. Four key themes were identified from the analysis; relational learning, insight and understanding, challenging attitudes and enhanced dementia practice. Discussion Student experience of our programme was shown to be positive. The relationship between the students and family was most impactful in supporting student learning, and the subsequent improvement in knowledge, attitudes and practice. Our model of undergraduate dementia education has applicability for other long-term conditions.

Collective classification, as an important technique to study networked data, aims to exploit the label autocorrelation for a group of inter-connected entities with complex dependencies. As the emergence of various heterogeneous information networks (HINs), collective classification at present is confronting several severe challenges stemming from the heterogeneity of HINs, such as complex relational hierarchy, potential incompatible semantics and node-context relational semantics. To address the challenges, in this paper, we propose a novel heterogeneous graph convolutional network-based deep learning model, called HGCN, to collectively categorize the entities in HINs. Our work involves three primary contributions: i) HGCN not only learns the latent relations from the relation-sophisticated HINs via multi-layer heterogeneous convolutions, but also captures the semantic incompatibility among relations with properly-learned edge-level filter parameters; ii) to preserve the fine-grained relational semantics of different-type nodes, we propose a heterogeneous graph convolution to directly tackle the original HINs without any in advance transforming the network from heterogeneity to homogeneity; iii) we perform extensive experiments using four real-world datasets to validate our proposed HGCN, the multi-facet results show that our proposed HGCN can significantly improve the performance of collective classification compared with the state-of-the-art baseline methods.

Traffic accident anticipation aims to predict accidents from dashcam videos as early as possible, which is critical to safety-guaranteed self-driving systems. With cluttered traffic scenes and limited visual cues, it is of great challenge to predict how long there will be an accident from early observed frames. Most existing approaches are developed to learn features of accident-relevant agents for accident anticipation, while ignoring the features of their spatial and temporal relations. Besides, current deterministic deep neural networks could be overconfident in false predictions, leading to high risk of traffic accidents caused by self-driving systems. In this paper, we propose an uncertainty-based accident anticipation model with spatio-temporal relational learning. It sequentially predicts the probability of traffic accident occurrence with dashcam videos. Specifically, we propose to take advantage of graph convolution and recurrent networks for relational feature learning, and leverage Bayesian neural networks to address the intrinsic variability of latent relational representations. The derived uncertainty-based ranking loss is found to significantly boost model performance by improving the quality of relational features. In addition, we collect a new Car Crash Dataset (CCD) for traffic accident anticipation which contains environmental attributes and accident reasons annotations. Experimental results on both public and the newly-compiled datasets show state-of-the-art performance of our model. Our code and CCD dataset are available at https://github.com/Cogito2012/UString., Accepted by ACM MM 2020

Robotic agents should be able to learn from sub-symbolic sensor data and, at the same time, be able to reason about objects and communicate with humans on a symbolic level. This raises the question of how to overcome the gap between symbolic and sub-symbolic artificial intelligence. We propose a semantic world modeling approach based on bottom-up object anchoring using an object-centered representation of the world. Perceptual anchoring processes continuous perceptual sensor data and maintains a correspondence to a symbolic representation. We extend the definitions of anchoring to handle multi-modal probability distributions and we couple the resulting symbol anchoring system to a probabilistic logic reasoner for performing inference. Furthermore, we use statistical relational learning to enable the anchoring framework to learn symbolic knowledge in the form of a set of probabilistic logic rules of the world from noisy and sub-symbolic sensor input. The resulting framework, which combines perceptual anchoring and statistical relational learning, is able to maintain a semantic world model of all the objects that have been perceived over time, while still exploiting the expressiveness of logical rules to reason about the state of objects which are not directly observed through sensory input data. To validate our approach we demonstrate, on the one hand, the ability of our system to perform probabilistic reasoning over multi-modal probability distributions, and on the other hand, the learning of probabilistic logical rules from anchored objects produced by perceptual observations. The learned logical rules are, subsequently, used to assess our proposed probabilistic anchoring procedure. We demonstrate our system in a setting involving object interactions where object occlusions arise and where probabilistic inference is needed to correctly anchor objects. ispartof: Frontiers in Robotics and AI vol:7 ispartof: location:Switzerland status: published

Event and activity modelling and recognition is at the centre of situational awareness (SA). Being able to detect and extract useful semantic information from diverse data sources in the form of events and activities, an SA system may assist human operators with cognitive analysis, situation monitoring and to inform decision making. Recognition of realworld activities with complex spatial and temporal interactions in the presence of uncertainty has been a major line of research. In this respect, Statistical Relational Learning methods such as Markov Logic Networks (MLNs) have been shown to provide a powerful and promising framework, and efficiently leveraging their representational power for event and activity recognition are active research and development activities. In this paper we propose a complementary method to existing approaches, FQSTAG-MLN, that combines Fuzzy MLNs with Fuzzy Qualitative Spatio-Temporal Activity Graphs (FQSTAGs) toward achieving efficient and explainable activity modelling and recognition. With FQSTAG-MLNs, the complexity of real-world activities is addressed by combining the representational richness of high-level activity specification with compact local spatio-temporal narratives for low-level events; while the uncertainty of activity and world models is calibrated using probabilistic methods and the vagueness of observations is calibrated using fuzzy set theory. We describe its current implementation within RUSH, which aims to be a flexible reasoning and learning platform for situational awareness. We present a use case illustration and early results.

Statistical machine learning algorithms usually assume that there is considerably-size data to train the models. However, they would fail in addressing domains where data is difficult or expensive to obtain. Transfer learning has emerged to address this problem of learning from scarce data by relying on a model learned in a source domain where data is easy to obtain to be a starting point for the target domain. On the other hand, real-world data contains objects and their relations, usually gathered from noisy environment. Finding patterns through such uncertain relational data has been the focus of the Statistical Relational Learning (SRL) area. Thus, to address domains with scarce, relational, and uncertain data, in this paper, we propose TreeBoostler, an algorithm that transfers the SRL state-of-the-art Boosted Relational Dependency Networks learned in a source domain to the target domain. TreeBoostler first finds a mapping between pairs of predicates to accommodate the additive trees into the target vocabulary. After, it employs two theory revision operators devised to handle incorrect relational regression trees aiming at improving the performance of the mapped trees. In the experiments presented in this paper, TreeBoostler has successfully transferred knowledge among several distinct domains. Moreover, it performs comparably or better than learning from scratch methods in terms of accuracy and outperforms a transfer learning approach in terms of accuracy and runtime.

Purpose The purpose of this study is to examine the tension between learning and protection in university-industry relationships (UIRs) and, in particular, to identify practices that facilitate ways of coping with this tension. Design/methodology/approach The empirical work for the study is based on a qualitative comparative case analysis of six successful, long-term relationships between industrial technology firms and university research groups in Finland. Findings The findings of the study reveal that the development of mutual trust, based on personal-level relationships, adaptation and reaching a consensus about the utilization of research results represent the key processes that enable partners to balance learning and protection and lower the informational barriers within the collaboration. Research limitations/implications The case data have been collected from IT industry, in which the need for knowledge is changing rapidly and the need for learning is typically high. However, generalization of the results may need additional case studies including from other industrial areas. Practical implications The results highlight a rich set of practices that can support both industrial actors and academics in improving their engagement in collaboration and to facilitate successful knowledge creation and utilization in UIRs. Originality/value This study extends the existing literature on UIR learning by presenting organizational practices, which help UIR actors to balance learning and protection in their collaboration. Along with mutual trust and adaptation achieved in long-term personal relationships, these practices allow partners to overcome organizational barriers that result from different orientations, attitudes and incentives.

This paper presents a classifier architecture that is able to deal with classification of interlinked entities when the only information available is the existing relationships between these entities, i.e. no semantic content is known for either the entities or their relationships. After proposing a classifier to deal with this problem, we provide extensive experimental evaluation showing that our proposed method is sound and that it is able to achieve high accuracy, in most cases much higher than other already existing algorithms configured to tackle this very same problem. The contributions of this paper are twofold: first, it presents a classifier for interlinked entities that outperforms most of the existing algorithms when the only information available is the relationships between these entities; second, it reveals the power of using label independent (LI) features extracted from network structural properties in the bootstrapping phases of relational classification.

Social media data is useful for personalized search engines, recommender systems, and targeted online marketing. Sometimes values of attributes are missing due to security reasons or problematic data collection process. In this case, the information about connections between vertices become more important since it explicitly allows for using the structure of a social graph for inferring missing attributes. One of the general and effective approaches of inferring missing attributes on graph structures are statistical relational learning. For machine learning tasks, the graph embeddings represent topological properties better, but they are not aimed at the attributes prediction. In this study, we introduce a method combining graph embeddings and the statistical relational learning. We consider different their combinations, as there are possible different hidden connections between social ties and considered attributes. We compare the performance using real data from the social network with different missing attributes and assortative patterns: gender, age, and economic status. As a result, the inclusion of graph embeddings in statistical relational learning improves accuracy and significantly decreases the number of iterations.

Diagnosis and treatment of multiple pulmonary nodules are clinically important but challenging. Prior studies on nodule characterization use solitary-nodule approaches on multiple nodular patients, which ignores the relations between nodules. In this study, we propose a multiple instance learning (MIL) approach and empirically prove the benefit to learn the relations between multiple nodules. By treating the multiple nodules from a same patient as a whole, critical relational information between solitary-nodule voxels is extracted. To our knowledge, it is the first study to learn the relations between multiple pulmonary nodules. Inspired by recent advances in natural language processing (NLP) domain, we introduce a self-attention transformer equipped with 3D CNN, named {NoduleSAT}, to replace typical pooling-based aggregation in multiple instance learning. Extensive experiments on lung nodule false positive reduction on LUNA16 database, and malignancy classification on LIDC-IDRI database, validate the effectiveness of the proposed method., 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI 2020)

Our work concerned the socio-cultural practices of tutors from diverse higher education institutes. The tutors were practising lecturers who had contributed to peer assessment studies published in refereed academic journals. Analysis of interview data considered the relational interdependency of tutors’ and students’ activity in the socially and culturally structured world of peer assessment. Undertaking peer assessment led to changes in: (1) relational learning between tutors and students, and (2) tutors’ and students’ perceived identities. The findings are discussed in terms of: (a) learning in communities of practice through boundary interactions with other communities, and (b) the participatory and acquisition metaphors of learning. The wider role of peer assessment in terms of interactions, communications and the balance of learning metaphors in higher education is considered.

Relational learning algorithms learn the definition of a new relation in terms of existing relations in the database. The same database may be represented under different schemas for various reasons, such as efficiency, data quality, and usability. Unfortunately, the output of current relational learning algorithms tends to vary quite substantially over the choice of schema, both in terms of learning accuracy and efficiency. We introduce the property of schema independence of relational learning algorithms, and study both the theoretical and empirical dependence of existing algorithms on the common class of (de) composition schema transformations. We show theoretically and empirically that current relational learning algorithms are generally not schema independent. We propose Castor, a relational learning algorithm that achieves schema independence.

Networked data, generated by social media, presents opportunities and challenges to the study of collective behaviors in a social networking environment. In this paper, we focus on multi-label classification on networked data, for which behaviors are represented as labels and an individual can have multiple labels. Existing relational learning methods exploit the connectivity of individuals and they have shown better performance than traditional multi-label classification methods. However, an individual's behavior may be influenced by other factors, particularly personal preference. Hence, we propose a novel approach that integrates causal analysis into multi-label classification to learn collective behaviors. We employ propensity score matching and causal effect estimation to distinguish the contributions of peer influence and personal preference to collective behaviors and incorporate the findings into the design of the classifier. We further study behavior heterogeneity across subgroups in social networks, as people with different demographic features may behave differently due to different impacts of peer influence and personal preference. We estimate conditional average causal effects to analyze the impacts of peer influence and personal preference in different subgroups in social networks. Experiments on real-world datasets demonstrate that our proposed methods improve classification performance over existing methods. Refereed/Peer-reviewed

Extant research argues that innovation collaboration (IC) has strong potential to create relational rents, but few scholars have investigated what capabilities can drive and enhance IC. This paper considers relational learning (RL) as a dynamic capability that strengthens IC and its contribution to firm performance through a better understanding of a firm's past collaboration and its future potential. By focusing on the timing of collaboration, the paper explains how IC is embedded in a firm's innovation activities by investigating the extent to which external partners are involved at various stages of the innovation process. The results of the study, which are based on a quantitative survey of 155 Russian firms, confirm the positive role of RL in innovation collaboration. They also highlight that the extent of the collaboration payoff varies according to its timing. The inclusion of the IC timing perspective indicates that firms should account for both the direct and indirect effects of RL on IC, and IC on firm performance when preparing for and managing their IC efforts with external partners.

This article presents a platform for interactive graph mining and relational machine learning called GraphVis. The platform combines interactive visual representations with state-of-the-art graph mining and relational machine learning techniques to aid in revealing important insights quickly as well as learning an appropriate and highly predictive model for a particular task (e.g., classification, link prediction, discovering the roles of nodes, and finding influential nodes). Visual representations and interaction techniques and tools are developed for simple, fast, and intuitive real-time interactive exploration, mining, and modeling of graph data. In particular, we propose techniques for interactive relational learning (e.g., node/link classification), interactive link prediction and weighting, role discovery and community detection, higher-order network analysis (via graphlets, network motifs), among others. GraphVis also allows for the refinement and tuning of graph mining and relational learning methods for specific application domains and constraints via an end-to-end interactive visual analytic pipeline that learns, infers, and provides rapid interactive visualization with immediate feedback at each change/prediction in real-time. Other key aspects include interactive filtering, querying, ranking, manipulating, exporting, as well as tools for dynamic network analysis and visualization, interactive graph generators (including new block model approaches), and a variety of multi-level network analysis techniques.