Search

Few-shot relation extraction uses only limited labeled data to predict relations between entities. Recently, several studies have introduced prompts to better guide models in understanding relations between entities. Although effective, these approaches ignore the hidden interaction information between support instances and relations, which causes the prompts without effective guidance. In addition, due to the limited labeled data, the model cannot get enough information for training, leading to the problems of relation confusion. In this paper, we propose RelPromptCL, a few-shot relation extraction method that consists of Prompt learning with Relation information and Contrastive Learning. Specifically, RelPromptCL first gets more helpful information by utilizing prompt templates with relation information and then fuses the instance features with the relation features to obtain prototype representation. At the same time, the use of multi-level contrastive learning allows the model to discriminate more between different classes and improves the discriminative capability of the model. Finally, the similarity between the query instance and the prototypes is computed for relation classification. We carried out extensive experiments on both public datasets, the FewRel1.0 datasets and the FewRel2.0 datasets. The results clearly show the efficiency of RelPromptCL.

Accurate and timely traffic forecasting is an important task for the realization of urban smart traffic. The random occurrence of social events such as traffic accidents will make traffic prediction particularly difficult. At the same time, most of the existing prediction methods rely on prior knowledge to obtain traffic maps and the obtained map structure cannot be guaranteed to be accurate for the current learning task. In addition, traffic data is highly non-linear and long-term dependent, so it is more difficult to achieve accurate prediction. In response to the above problems, this paper proposes a new integrated unified architecture for traffic prediction based on heterogeneous graph attention network combined with residual-time-series convolutional network, which is called HGA-ResTCN. First, the heterogeneous graph attention is used to capture the changes in the relationship between the traffic graph nodes caused by social events, so as to learn the link weights between the target node and its neighbor nodes; at the same time, by introducing the timing of residual links convolutional network to capture the long-term dependence of complex traffic data. These two models are integrated into a unified framework to learn in an end-to-end manner. Through testing on real-world data sets, the results show that the accuracy of the model in this paper is better than other proposed baselines.

Deep learning techniques have demonstrated significant advancements in the task of text classification. Regrettably, the majority of these techniques necessitate a substantial corpus of annotated data to achieve optimal performance. Meta-learning has yielded intriguing outcomes in few-shot learning tasks, showcasing its potential in advancing the field. However, the current meta-learning methodologies are susceptible to overfitting due to the mismatch between a small number of samples and the complexity of the model. To mitigate this concern, we propose a Prompt-based Graph Convolutional Adversarial (PGCA) meta-learning framework, aiming to improve the adaptability of complex models in a few-shot scenario. Firstly, leveraging prompt learning, we generate embedding representations that bridge the downstream tasks. Then, we design a meta-knowledge extractor based on a graph convolutional neural network (GCN) to capture inter-class dependencies through instance-level interactions. We also integrate the adversarial network architecture into a meta-learning framework to extend sample diversity through adversarial training and improve the ability of the model to adapt to new tasks. Specifically, we mitigate the impact of extreme samples by introducing external knowledge to construct a list of class prototype extensions. Finally, we conduct a series of experiments on four public datasets to demonstrate the effectiveness of our proposed method.

Named entity recognition involves two main types: nested named entity recognition and flat named entity recognition. The span-based approach treats nested entities and flat entities uniformly by classifying entities on a span representation. However, the span-based approach ignores the local features within the entities and the relative position features between the head and tail tokens, which affects the performance of entity recognition. To address these issues, we propose a nested entity recognition model using a convolutional block attention module and rotary position embedding for local features and relative position features enhancement. Specifically, we apply rotary position embedding to the sentence representation and capture the semantic information between the head and tail tokens using a biaffine attention mechanism. Meanwhile, the convolution module captures the local features within the entity to generate the span representation. Finally, the two parts of the representation are fused for entity classification. Extensive experiments were conducted on five widely used benchmark datasets to demonstrate the effectiveness of our proposed model.

Urban traffic prediction is essential for intelligent transportation systems. However, traffic data often exhibit highly complex spatio-temporal correlations, posing challenges for accurate forecasting. Graph neural networks have demonstrated an outstanding ability in capturing spatial correlations and are now extensively applied to traffic prediction. However, many graph-based methods neglect the dynamic spatial features between road segments and the continuity of spatial features across adjacent time steps, leading to subpar predictive performance. This paper proposes a Dynamic Spatio-Temporal Graph Fusion Convolutional Network (DSTGFCN) to enhance the accuracy of traffic prediction. Specifically, we designed a dynamic graph fusion module without prior road spatial information, which extracts dynamic spatial information among roads from observed data. Subsequently, we fused the dynamic spatial features of the current time step and adjacent time steps to generate a dynamic graph for each time step. The graph convolutional gated recurrent network was employed to model the spatio-temporal correlations jointly. Additionally, residual connections were added to the model to enhance the ability to extract long-term temporal relationships. Finally, we conducted experiments on six publicly available traffic datasets, and the results demonstrated that DSTGFCN outperforms the baseline models with state-of-the-art predictive performance.

Few-shot named entity recognition requires sufficient prior knowledge to transfer valuable knowledge to the target domain with only a few labeled examples. Existing Chinese few-shot named entity recognition methods suffer from inadequate prior knowledge and limitations in feature representation. In this paper, we utilize enhanced Span and Label semantic representations for Chinese few-shot Named Entity Recognition (SLNER) to address the problem. Specifically, SLNER utilizes two encoders. One encoder is used to encode the text and its spans, and we employ the biaffine attention mechanism and self-attention to obtain enhanced span representations. This approach fully leverages the internal composition of entity mentions, leading to more accurate feature representations. The other encoder encodes the full label names to obtain label representations. Label names are broad representations of specific entity categories and share similar semantic meanings with entities. This similarity allows label names to offer valuable prior knowledge in few-shot scenarios. Finally, our model learns to match span representations with label representations. We conducted extensive experiments on three sampling benchmark Chinese datasets and a self-built food safety risk domain dataset. The experimental results show that our model outperforms the F1 scores of 0.20–6.57% of previous state-of-the-art methods in few-shot settings.

The primary task of few-shot relation extraction is to quickly learn the features of relation classes from a few labelled instances and predict the semantic relations between entity pairs in new instances. Most existing few-shot relation extraction methods do not fully utilize the relation information features in sentences, resulting in difficulties in improving the performance of relation classification. Some researchers have attempted to incorporate external information, but the results have been unsatisfactory when applied to different domains. In this paper, we propose a method that utilizes triple information for data augmentation, which can alleviate the issue of insufficient instances and possesses strong domain adaptation capabilities. Firstly, we extract relation and entity pairs from the instances in the support set, forming relation triple information. Next, the sentence information and relation triple information are encoded using the same sentence encoder. Then, we construct an interactive attention module to enable the query set instances to interact separately with the support set instances and relation triple instances. The module pays greater attention to highly interactive parts between instances and assigns them higher weights. Finally, we merge the interacted support set representation and relation triple representation. To our knowledge, we are the first to propose a method that utilizes triple information for data augmentation in relation extraction. In our experiments on the standard datasets FewRel1.0 and FewRel2.0 (domain adaptation), we observed substantial improvements without including external information.

The significance of vehicle-to everything (V2X) communication in ensuring road safety is undeniable. In addition, real-time vehicle communication requires an ample amount of spectrum resources. However, the existing spectrum resources are seriously scarce, and the utilization rate is not high, leading to high delays in V2X communication and other unfavorable factors in the case of fast-moving vehicles, bringing great safety risks to driving. Load balancing is one of the most effective methods to improve spectrum utilization. However, the existing load balancing schemes merely focus on static conditions, with a lack of joint scheduling schemes, which cannot support the communication framework of dynamic V2X. To address both of these issues, in this paper, a new communication method is proposed. In addition, this paper studies a joint load balancing scheme of mobility vehicle-to-vehicle (V2V) and user association under incomplete channel state information (CSI) and realizes the load balancing management of a cross-cell V2X network. An algorithm combining power control and resource allocation mode selection is proposed. In particular, according to different coverage areas, different allocation algorithms are adopted to maximize the overall system efficiency. The simulation results show that this strategy can maintain low latency and effectively improve the system energy efficiency of vehicle users.

Traffic flow forecasting is the foundation of intelligent transportation systems. Accurate traffic forecasting is crucial for intelligent traffic management and urban development. However, achieving highly accurate traffic flow prediction is challenging due to road networks’ complex dynamic spatial and temporal dependencies. Previous work using predefined static adjacency matrices in graph convolutional networks needs to be revised to reflect the dynamic spatial dependencies in the traffic system. In addition, most current methods ignore the hidden dynamic spatial–temporal correlations between road network nodes as they evolve. We propose a spatial–temporal dynamic graph differential equation network (ST-DGDE) for traffic prediction to address the above problems. First, the model captures the dynamic changes between spatial nodes over time through a dynamic graph learning network. Then, dynamic graph differential equations (DGDE) are used to learn the spatial–temporal dynamic relationships in the global space that change continuously over time. Finally, static adjacency matrices are constructed by static node embedding. The generated dynamic and predefined static graphs are fused and input into a gated temporal causal convolutional network to jointly capture the fixed long-term spatial association patterns and achieve a global receiver domain that facilitates long-term prediction. Experiments of our model on two natural traffic flow datasets show that ST-DGDE outperforms other baselines.

Accurate and timely traffic flow forecasting is the key technology to address the issue of urban traffic congestion, which is significant for intelligent transportation system. However, it is a quite challenging task to develop an efficient, robust and automatically generated forecasting model. In this paper, we propose a novel model, ensemble forecasting architecture based on non-negative constrained sparse autoencoder and extreme learning machine(NCAE-ELM-EA). This model is designed using NCAE to extract traffic characteristics layer-by-layer through a greedy unsupervised algorithm, and the prediction network formed by connecting NCAE and ELM serves as base learner of each lag pool. Then, employing adaptive enhanced integration algorithm to build an ensemble optimized forecasting model with scalable size suitable for each road segment. The model was applied to the actual data collected from I5 NB highways in Portland, USA, and J6-J7(N) freeways in the United Kingdom, with higher accuracy and lower labor costs compared with existing predictors.

Food safety is closely related to human health. Therefore, named entity recognition technology is used to extract named entities related to food safety, and building a regulatory knowledge graph in the field of food safety can help relevant authorities to regulate food safety issues and mitigate the hazards caused by food safety problems. However, there is no publicly available named entity recognition dataset in the food safety domain. In contrast, the non-standardized Chinese short texts generated from user comments on the web contain rich implicit information that can help identify named entities in specific domains (e.g., food safety domain) where the corpus is scarce. Therefore, in this paper, named entities related to food safety are extracted from these unstandardized texts on the web. However, the existing Chinese named entity identification methods are mainly for standardized texts. Meanwhile, these unstandardized texts have the following problems: (1) their corpus size is small; (2) there are various new and wrong words and noise; (3) and they do not follow strict syntactic rules. These problems make the recognition of Chinese named entities for online texts more challenging. Therefore, this paper proposes the ERNIE-Adv-BiLSTM-Att-CRF model to improve the recognition of food safety domain entities in unstandardized texts. Specifically, adversarial training is added to the model training as a regularization method to alleviate the influence of noise on the model, while self-attention is added to the BiLSTM-CRF model to capture features that significant impact entity classification and improve the accuracy of entity classification. This paper conducts experiments on the public dataset Weibo NER and the self-built food domain dataset Food. The experimental results show that our model achieves a SOTA performance of 72.64% and a good performance of 69.68% for F1 values on the public and self-built datasets, respectively. The validity and reasonableness of our model are verified. In addition, the paper further analyses the impact of various components and settings on the model. The study has practical implications in the field of food safety.

In this paper, an extreme learning machine (ELM)-based improved layered ensemble architecture (EILEA) for time series forecasting is proposed. Compared with multilayer perceptron (MLP)-based layered ensemble architecture (named LEA), our proposed structure has improved in two aspects. First of all, we proposed an inflection point estimation-based density peaks clustering algorithm to replace K-means algorithm used by LEA, which can automatically determine the number of clusters without the influence of the choice of initial cluster centers on the clustering results. Second, EILEA employs ELM as individual learners, taking advantage of its high learning speed to greatly improve the prediction speed. The proposed architecture has been tested on the time series data of neural network (NN)3 competition. In terms of forecasting accuracy and speed, the experimental results have revealed clearly that our proposed structure is better than LEA.

In this paper, we study the joint optimization problem of the spectrum and power allocation for multiple vehicle-to-infrastructure (V2I) and vehicle-to-vehicle (V2V) users in cellular vehicle-to-everything (C-V2X) communication, aiming to maximize the sum rate of V2I links while satisfying the low latency requirements of V2V links. However, channel state information (CSI) is hard to obtain accurately due to the mobility of vehicles. In addition, the effective sensing of state information among vehicles becomes difficult in an environment with complex and diverse information, which is detrimental to vehicles collaborating for resource allocation. Thus, we propose a framework of multi-agent deep reinforcement learning based on attention mechanism (AMARL) to improve the V2X communication performance. Specifically, for vehicle mobility, we model the problem as a multi-agent reinforcement learning process, where each V2V link is regarded an agent and all agents jointly intercommunicate with the environment. Each agent allocates spectrum and power through its deep Q network (DQN). To enhance effective intercommunication and the sense of collaboration among vehicles, we introduce an attention mechanism to focus on more relevant information, which in turn reduces the signaling overhead and optimizes their communication performance more explicitly. Experimental results show that the proposed AMARL-based approach can satisfy the requirements of a high rate for V2I links and low latency for V2V links. It also has an excellent adaptability to environmental change.

Accurate urban traffic flow prediction plays a vital role in Intelligent Transportation System (ITS). The complex long-term and long-range spatiotemporal correlations of traffic flow pose a significant challenge to the prediction task. Most current research methods focus only on spatial correlations in local areas, ignoring global geographic contextual information. It is challenging to capture spatial information from distant nodes using shallow graph neural networks (GNNs) to model long-range spatial correlations. To handle this problem, we design a novel spatiotemporal global semantic graph-attentive convolutional network model (STSGAN), which is a deep-level network to achieve the simultaneous modelling of spatiotemporal correlations. First, we propose a graph-attentive convolutional network (GACN) to extract the importance of different spatial features and learn the spatial correlation of local regions and the global spatial semantic information. The temporal causal convolution structure (TCN) is utilized to capture the causal relationships between long-short times, thus enabling an integrated consideration of local and overall spatiotemporal correlations. Several experiments are conducted on two real-world traffic flow datasets, and the results show that our approach outperforms several state-of-the-art baselines.

Spectrum demand has increased with the rapid growth of wireless devices and wireless service usage. The rapid development of 5G smart cities and the industrial Internet of Things makes the problem of spectrum resource shortage and increased energy consumption even more severe. To address the issues of high energy consumption for spectrum sensing and low user access rate in the cognitive radio networks (CRN) model powered entirely by energy harvesting, we propose a novel energy harvesting (EH)-distributed cooperative spectrum sensing (DCSS) architecture that allows SUs to acquire from the surrounding environment and radio frequency (RF) signals energy, and an improved distributed cooperative spectrum sensing scheme based on energy-correlation is proposed. First, we formulate an optimization problem to select a leader for each channel; then formulate another optimization problem to select the corresponding cooperative secondary users (SUs). Each channel has a fixed SUs cluster in each time slot to sense the main user state, which can reduce the energy consumption of SUs sensing and can reduce the sensing time, and the remaining time can be used for data transmission to improve throughput, and finally achieve the purpose of improving energy efficiency. Simulation results show that our proposed scheme significantly outperforms the centralized scheme in terms of SUs access capability and energy efficiency.

Vehicle-to-vehicle (V2V) communication has attracted increasing attention since it can improve road safety and traffic efficiency. In the underlay approach of mode 3, the V2V links need to reuse the spectrum resources preoccupied with vehicle-to-infrastructure (V2I) links, which will interfere with the V2I links. Therefore, how to allocate wireless resources flexibly and improve the throughput of the V2I links while meeting the low latency requirements of the V2V links needs to be determined. This paper proposes a V2V resource allocation framework based on deep reinforcement learning. The base station (BS) uses a double deep Q network to allocate resources intelligently. In particular, to reduce the signaling overhead for the BS to acquire channel state information (CSI) in mode 3, the BS optimizes the resource allocation strategy based on partial CSI in the framework of this article. The simulation results indicate that the proposed scheme can meet the low latency requirements of V2V links while increasing the capacity of the V2I links compared with the other methods. In addition, the proposed partial CSI design has comparable performance to complete CSI.

Accurate traffic flow prediction is essential to building a smart transportation city. Existing research mainly uses a given single-graph structure as a model, only considers local and static spatial dependencies, and ignores the impact of dynamic spatio-temporal data diversity. To fully capture the characteristics of spatio-temporal data diversity, this paper proposes a cross-Attention Fusion Based Spatial-Temporal Multi-Graph Convolutional Network (CAFMGCN) model for traffic flow prediction. First, introduce GCN to model the historical traffic data’s three-time attributes (current, daily, and weekly) to extract time features. Second, consider the relationship between distance and traffic flow, constructing adjacency, connectivity, and regional similarity graphs to capture dynamic spatial topology information. To make full use of global information, a cross-attention mechanism is introduced to fuse temporal and spatial features separately to reduce prediction errors. Finally, the CAFMGCN model is evaluated, and the experimental results show that the prediction of this model is more accurate and effective than the baseline of other models.