Search

Given the adverse impact of fake news propagation on Social media, fake news mitigation has been one of the main research directions. However, existing approaches neglect fairness towards each community while minimizing the adverse impact of fake news propagation. This results in the exclusion of some minor and underrepresented communities from the benefits of the intervention, which can have important societal repercussions. This research proposes a fairness-aware truth-campaigning method, called FWRRS (Fairness-aware Weighted Reversible Reachable System), which focuses on blocking the influence propagation of a competing entity, in this case, with the use case of fake news mitigation. The proposed method employs weighted reversible reachable trees and maximin fairness to achieve its goals. Experimental analysis shows that FWRRS outperforms fairness-oblivious and fairness-aware methods in terms of both total outreach and fairness. The results show that in the proposed approach, such fairness does not come at a cost in efficiency, and in fact, in most cases, it works as a catalyst for achieving better effectiveness in the future. In real-world networks, we observe up to ∼ 10% improvement in the saved nodes and ∼ 57% improvement in maximin fairness as compared to the second best-performing baseline, which varies for each network. [ABSTRACT FROM AUTHOR]

Sparse neural networks attract increasing interest as they exhibit comparable performance to their dense counterparts while being computationally efficient. Pruning the dense neural networks is among the most widely used methods to obtain a sparse neural network. Driven by the high training cost of such methods that can be unaffordable for a low-resource device, training sparse neural networks sparsely from scratch has recently gained attention. However, existing sparse training algorithms suffer from various issues, including poor performance in high sparsity scenarios, computing dense gradient information during training, or pure random topology search. In this paper, inspired by the evolution of the biological brain and the Hebbian learning theory, we present a new sparse training approach that evolves sparse neural networks according to the behavior of neurons in the network. Concretely, by exploiting the cosine similarity metric to measure the importance of the connections, our proposed method, "Cosine similarity-based and random topology exploration (CTRE)", evolves the topology of sparse neural networks by adding the most important connections to the network without calculating dense gradient in the backward. We carried out different experiments on eight datasets, including tabular, image, and text datasets, and demonstrate that our proposed method outperforms several state-of-the-art sparse training algorithms in extremely sparse neural networks by a large gap. The implementation code is available on Github. [ABSTRACT FROM AUTHOR]

The evolution of online social networks is highly dependent on the recommended links. Most of the existing works focus on predicting intra-community links efficiently. However, it is equally important to predict inter-community links with high accuracy for diversifying a network. In this work, we propose a link prediction method, called HM-EIICT, that considers both the similarity of nodes and their community information to predict both kinds of links, intra-community links as well as inter-community links, with higher accuracy. The proposed framework is built on the concept that the connection likelihood between two given nodes differs for inter-community and intra-community node-pairs. The performance of the proposed methods is evaluated using link prediction accuracy and network modularity reduction. The results are studied on real-world networks and show the effectiveness of the proposed method as compared to the baselines. The experiments suggest that the inter-community links can be predicted with a higher accuracy using community information extracted from the network topology, and the proposed framework outperforms several measures especially proposed for community-based link prediction. The paper is concluded with open research directions. [ABSTRACT FROM AUTHOR]

Data collected over time often exhibit changes in distribution, or concept drift, caused by changes in factors relevant to the classification task, e.g. weather conditions. Incorporating all relevant factors into the model may be able to capture these changes, however, this is usually not practical. Data stream based methods, which instead explicitly detect concept drift, have been shown to retain performance under unknown changing conditions. These methods adapt to concept drift by training a model to classify each distinct data distribution. However, we hypothesize that existing methods do not robustly handle real-world tasks, leading to adaptation errors where context is misidentified. Adaptation errors may cause a system to use a model which does not fit the current data, reducing performance. We propose a novel repair algorithm to identify and correct errors in concept drift adaptation. Evaluation on synthetic data shows that our proposed AiRStream system has higher performance than baseline methods, while is also better at capturing the dynamics of the stream. Evaluation on an air quality inference task shows AiRStream provides increased real-world performance compared to eight baseline methods. A case study shows that AiRStream is able to build a robust model of environmental conditions over this task, allowing the adaptions made to concept drift to be analysed and related to changes in weather. We discovered a strong predictive link between the adaptions made by AiRStream and changes in meteorological conditions. [ABSTRACT FROM AUTHOR]

In real-world complex networks, understanding the dynamics of their evolution has been of great interest to the scientific community. Predicting non-existent but probable links is an essential task of social network analysis as the addition or removal of the links over time leads to the network evolution. In a network, links can be categorized as intra-community links if both end nodes of the link belong to the same community, otherwise inter-community links. The existing link-prediction methods have mainly focused on achieving high accuracy for intra-community link prediction. In this work, we propose a network embedding method, called NodeSim, which captures both similarities between the nodes and the community structure while learning the low-dimensional representation of the network. The embedding is learned using the proposed NodeSim random walk, which efficiently explores the diverse neighborhood while keeping the more similar nodes closer in the context of the node. We verify the efficacy of the proposed embedding method over state-of-the-art methods using diverse link prediction. We propose a machine learning model for link prediction that considers both the nodes' embedding and their community information to predict the link between two given nodes. Extensive experimental results on several real-world networks demonstrate the effectiveness of the proposed method for both inter and intra-community link prediction. [ABSTRACT FROM AUTHOR]

Effectively detecting anomalous nodes in attributed networks is crucial for the success of many real-world applications such as fraud and intrusion detection. Existing approaches have difficulties with three major issues: sparsity and nonlinearity capturing, residual modeling, and network smoothing. We propose Residual Graph Convolutional Network (ResGCN), an attention-based deep residual modeling approach that can tackle these issues: modeling the attributed networks with GCN allows to capture the sparsity and nonlinearity, utilizing a deep neural network allows direct residual ing from the input, and a residual-based attention mechanism reduces the adverse effect from anomalous nodes and prevents over-smoothing. Extensive experiments on several real-world attributed networks demonstrate the effectiveness of ResGCN in detecting anomalies. [ABSTRACT FROM AUTHOR]

Discrete Markov chains are frequently used to analyse transition behaviour in sequential data. Here, the transition probabilities can be estimated using varying order Markov chains, where order k specifies the length of the sequence history that is used to model these probabilities. Generally, such a model is fitted to the entire dataset, but in practice it is likely that some heterogeneity in the data exists and that some sequences would be better modelled with alternative parameter values, or with a Markov chain of a different order. We use the framework of Exceptional Model Mining (EMM) to discover these exceptionally behaving sequences. In particular, we propose an EMM model class that allows for discovering subgroups with transition behaviour of varying order. To that end, we propose three new quality measures based on information-theoretic scoring functions. Our findings from controlled experiments show that all three quality measures find exceptional transition behaviour of varying order and are reasonably sensitive. The quality measure based on Akaike's Information Criterion is most robust for the number of observations. We furthermore add to existing work by seeking for subgroups of sequences, as opposite to subgroups of transitions. Since we use sequence-level descriptive attributes, we form subgroups of entire sequences, which is practically relevant in situations where you want to identify the originators of exceptional sequences, such as patients. We show this relevance by analysing sequences of blood glucose values of adult persons with diabetes type 2. In the experiments, we find subgroups of patients based on age and glycated haemoglobin (HbA1c), a measure known to correlate with average blood glucose values. Clinicians and domain experts confirmed the transition behaviour as estimated by the fitted Markov chain models. [ABSTRACT FROM AUTHOR]

Major complications arise from the recent increase in the amount of high-dimensional data, including high computational costs and memory requirements. Feature selection, which identifies the most relevant and informative attributes of a dataset, has been introduced as a solution to this problem. Most of the existing feature selection methods are computationally inefficient; inefficient algorithms lead to high energy consumption, which is not desirable for devices with limited computational and energy resources. In this paper, a novel and flexible method for unsupervised feature selection is proposed. This method, named QuickSelection (The code is available at: https://github.com/zahraatashgahi/QuickSelection), introduces the strength of the neuron in sparse neural networks as a criterion to measure the feature importance. This criterion, blended with sparsely connected denoising autoencoders trained with the sparse evolutionary training procedure, derives the importance of all input features simultaneously. We implement QuickSelection in a purely sparse manner as opposed to the typical approach of using a binary mask over connections to simulate sparsity. It results in a considerable speed increase and memory reduction. When tested on several benchmark datasets, including five low-dimensional and three high-dimensional datasets, the proposed method is able to achieve the best trade-off of classification and clustering accuracy, running time, and maximum memory usage, among widely used approaches for feature selection. Besides, our proposed method requires the least amount of energy among the state-of-the-art autoencoder-based feature selection methods. [ABSTRACT FROM AUTHOR]

Recurrent neural networks (RNNs) have achieved state-of-the-art performances on various applications. However, RNNs are prone to be memory-bandwidth limited in practical applications and need both long periods of training and inference time. The aforementioned problems are at odds with training and deploying RNNs on resource-limited devices where the memory and floating-point operations (FLOPs) budget are strictly constrained. To address this problem, conventional model compression techniques usually focus on reducing inference costs, operating on a costly pre-trained model. Recently, dynamic sparse training has been proposed to accelerate the training process by directly training sparse neural networks from scratch. However, previous sparse training techniques are mainly designed for convolutional neural networks and multi-layer perceptron. In this paper, we introduce a method to train intrinsically sparse RNN models with a fixed number of parameters and floating-point operations (FLOPs) during training. We demonstrate state-of-the-art sparse performance with long short-term memory and recurrent highway networks on widely used tasks, language modeling, and text classification. We simply use the results to advocate that, contrary to the general belief that training a sparse neural network from scratch leads to worse performance than dense networks, sparse training with adaptive connectivity can usually achieve better performance than dense models for RNNs. [ABSTRACT FROM AUTHOR]

Learning causal effects from observational data greatly benefits a variety of domains such as health care, education, and sociology. For instance, one could estimate the impact of a new drug on specific individuals to assist clinical planning and improve the survival rate. In this paper, we focus on studying the problem of estimating the Conditional Average Treatment Effect (CATE) from observational data. The challenges for this problem are two-fold: on the one hand, we have to derive a causal estimator to estimate the causal quantity from observational data, in the presence of confounding bias; on the other hand, we have to deal with the identification of the CATE when the distributions of covariates over the treatment group units and the control units are imbalanced. To overcome these challenges, we propose a neural network framework called Adversarial Balancing-based representation learning for Causal Effect Inference (ABCEI), based on recent advances in representation learning. To ensure the identification of the CATE, ABCEI uses adversarial learning to balance the distributions of covariates in the treatment and the control group in the latent representation space, without any assumptions on the form of the treatment selection/assignment function. In addition, during the representation learning and balancing process, highly predictive information from the original covariate space might be lost. ABCEI can tackle this information loss problem by preserving useful information for predicting causal effects under the regularization of a mutual information estimator. The experimental results show that ABCEI is robust against treatment selection bias, and matches/outperforms the state-of-the-art approaches. Our experiments show promising results on several datasets, encompassing several health care (and other) domains. [ABSTRACT FROM AUTHOR]

A data stream is a sequence of observations produced by a generating process which may evolve over time. In such a time-varying stream the relationship between input features and labels, or concepts, can change. Adapting to changes in concept is most often done by destroying and incrementally rebuilding the current classifier. Many systems additionally store and reuse previously built models to more efficiently adapt when stream conditions drift to a previously seen state. Reusing a model offers increased classification performance over rebuilding, and provides an indicator, or transparency, into the hidden state of the generating process. When only a subset of past models can be stored for reuse, for example due to memory constraints, the choice of which models to store for optimal future reuse is an important problem. Current methods of evaluating which models to store use valuation policies such as age, time since last use, accuracy and diversity. These policies are often not optimal, losing predictive performance by undervaluing complex models. We propose a new valuation policy based on advantage, the misclassifications avoided by reusing a model rather than training a new model, which more accurately reflects the true value of model storage. We evaluate our method on synthetic and real world data, including a real world air pollution dataset. Our results show accuracy increases of up to 6% using our valuation policy, while preserving transparency. [ABSTRACT FROM AUTHOR]

Artificial neural networks (ANNs) have emerged as hot topics in the research community. Despite the success of ANNs, it is challenging to train and deploy modern ANNs on commodity hardware due to the ever-increasing model size and the unprecedented growth in the data volumes. Particularly for microarray data, the very high dimensionality and the small number of samples make it difficult for machine learning techniques to handle. Furthermore, specialized hardware such as graphics processing unit (GPU) is expensive. Sparse neural networks are the leading approaches to address these challenges. However, off-the-shelf sparsity-inducing techniques either operate from a pretrained model or enforce the sparse structure via binary masks. The training efficiency of sparse neural networks cannot be obtained practically. In this paper, we introduce a technique allowing us to train truly sparse neural networks with fixed parameter count throughout training. Our experimental results demonstrate that our method can be applied directly to handle high-dimensional data, while achieving higher accuracy than the traditional two-phase approaches. Moreover, we have been able to create truly sparse multilayer perceptron models with over one million neurons and to train them on a typical laptop without GPU (https://github.com/dcmocanu/sparse-evolutionary-artificial-neural-networks/tree/master/SET-MLP-Sparse-Python-Data-Structures), this being way beyond what is possible with any state-of-the-art technique. [ABSTRACT FROM AUTHOR]

Collective social media provides a vast amount of geo-tagged social posts, which contain various records on spatio-temporal behavior. Modeling spatio-temporal behavior on collective social media is an important task for applications like tourism recommendation, location prediction and urban planning. Properly accomplishing this task requires a model that allows for diverse behavioral patterns on each of the three aspects: spatial location, time, and text. In this paper, we address the following question: how to find representative subgroups of social posts, for which the spatio-temporal behavioral patterns are substantially different from the behavioral patterns in the whole dataset? Selection and evaluation are the two challenging problems for finding the exceptional subgroups. To address these problems, we propose BNPM: a Bayesian non-parametric model, to model spatio-temporal behavior and infer the exceptionality of social posts in subgroups. By training BNPM on a large amount of randomly sampled subgroups, we can get the global distribution of behavioral patterns. For each given subgroup of social posts, its posterior distribution can be inferred by BNPM. By comparing the posterior distribution with the global distribution, we can quantify the exceptionality of each given subgroup. The exceptionality scores are used to guide the search process within the exceptional model mining framework to automatically discover the exceptional subgroups. Various experiments are conducted to evaluate the effectiveness and efficiency of our method. On four real-world datasets our method discovers subgroups coinciding with events, subgroups distinguishing professionals from tourists, and subgroups whose consistent exceptionality can only be truly appreciated by combining exceptional spatio-temporal and exceptional textual behavior. [ABSTRACT FROM AUTHOR]

Network embedding (NE) is playing a principal role in network mining, due to its ability to map nodes into efficient low-dimensional embedding vectors. However, two major limitations exist in state-of-the-art NE methods: role preservation and uncertainty modeling. Almost all previous methods represent a node into a point in space and focus on local structural information, i.e., neighborhood information. However, neighborhood information does not capture global structural information and point vector representation fails in modeling the uncertainty of node representations. In this paper, we propose a new NE framework, struc2gauss, which learns node representations in the space of Gaussian distributions and performs network embedding based on global structural information. struc2gauss first employs a given node similarity metric to measure the global structural information, then generates structural context for nodes and finally learns node representations via Gaussian embedding. Different structural similarity measures of networks and energy functions of Gaussian embedding are investigated. Experiments conducted on real-world networks demonstrate that struc2gauss effectively captures global structural information while state-of-the-art network embedding methods fail to, outperforms other methods on the structure-based clustering and classification task and provides more information on uncertainties of node representations. [ABSTRACT FROM AUTHOR]

Epilepsy and psychogenic non-epileptic seizures (PNES) often show over-lap in symptoms, especially at an early disease stage. During a PNES, the electrical activity of the brain remains normal but in case of an epileptic seizure the brain will show epileptiform discharges on the electroencephalogram (EEG). In many cases an accurate diagnosis can only be achieved after a long-term video monitoring combined with EEG recording which is quite expensive and time-consuming. In this paper using short-term EEG data, the classification of epilepsy and PNES subjects is analyzed based on signal, functional network and EEG microstate features. Our results showed that the beta-band is the most useful EEG frequency sub-band as it performs best for classifying subjects. Also the results depicted that when the coverage feature of the EEG microstate analysis is calculated in beta-band, the classification shows fairly high accuracy and precision. Hence, the beta-band and the coverage are the most important features for classification of epilepsy and PNES patients. [ABSTRACT FROM AUTHOR]

Given a database of records, it might be possible to identify small subsets of data which distribution is exceptionally different from the distribution in the complete set of data records. Finding such interesting relationships, which we call exceptional relationships, in an automated way would allow discovering unusual or exceptional hidden behaviour. In this paper, we formulate the problem of mining exceptional relationships as a special case of exceptional model mining and propose a grammar-guided genetic programming algorithm (MERG3P) that enables the discovery of any exceptional relationships. In particular, MERG3P can work directly not only with categorical, but also with numerical data. In the experimental evaluation, we conduct a case study on mining exceptional relations between well-known and widely used quality measures of association rules, which exceptional behaviour would be of interest to pattern mining experts. For this purpose, we constructed a data set comprising a wide range of values for each considered association rule quality measure, such that possible exceptional relations between measures could be discovered. Thus, besides the actual validation of MERG3P, we found that the Support and Leverage measures in fact are negatively correlated under certain conditions, while in general experts in the field expect these measures to be positively correlated. [ABSTRACT FROM AUTHOR]

Finding synchronization between the outputs of a dynamic system, which are represented mostly as time series, helps to characterize the system activities during an occurrence. An important issue in analyzing time series is that they may behave chaotically or stochastically. Therefore, applying a reliable synchronization measure which can capture the dynamic features of the system helps to quantify the interdependencies between time series, correctly. In this paper, we employ similarity measures based on visibility graph (VG) algorithms as an alternative and radically different way to measure the synchronization between time series. We assess the performance of VG-based similarity measures on chaotic, noisy and stochastic time series. In our experiments, we use the Rössler system and the noisy Hénon map as representative instances of chaotic systems, and the Kuramoto model for studying detection of synchronization between stochastic time series. Our study suggests that the similarity measure based on the horizontal VG algorithm should be favored to other measures for detecting synchronization between chaotic and stochastic time series. [ABSTRACT FROM AUTHOR]