Multi-hop reasoning for incomplete Knowledge Graphs(KGs)demonstrates excellent interpretability with decent *** Learning(RL)based approaches formulate multi-hop reasoning as a typical sequential decision *** intractab...
详细信息
Multi-hop reasoning for incomplete Knowledge Graphs(KGs)demonstrates excellent interpretability with decent *** Learning(RL)based approaches formulate multi-hop reasoning as a typical sequential decision *** intractable shortcoming of multi-hop reasoning with RL is that sparse reward signals make performance *** mainstream methods apply heuristic reward functions to counter this ***,the inaccurate rewards caused by heuristic functions guide the agent to improper inference paths and unrelated object *** this end,we propose a novel adaptive Inverse Reinforcement Learning(IRL)framework for multi-hop reasoning,called AInvR.(1)To counter the missing and spurious paths,we replace the heuristic rule rewards with an adaptive rule reward learning mechanism based on agent’s inference trajectories;(2)to alleviate the impact of over-rewarded object entities misled by inaccurate reward shaping and rules,we propose an adaptive negative hit reward learning mechanism based on agent’s sampling strategy;(3)to further explore diverse paths and mitigate the influence of missing facts,we design a reward dropout mechanism to randomly mask and perturb reward parameters for the reward learning *** results on several benchmark knowledge graphs demonstrate that our method is more effective than existing multi-hop approaches.
New media art is a specific manifestation of the integration of artistic expression and data technology. Its combination with virtual reality technology can enrich the forms of artistic expression and enhance the inte...
详细信息
Safety equipment detection is an important application of object detection, receiving widespread attention in fields such as smart construction sites and video surveillance. Significant progress has been made in objec...
详细信息
As an important task in emotion analysis, Multimodal Emotion-Cause Pair Extraction in conversations (MECPE) aims to extract all the emotion-cause utterance pairs from a conversation. However, there are two shortcoming...
详细信息
As an important task in emotion analysis, Multimodal Emotion-Cause Pair Extraction in conversations (MECPE) aims to extract all the emotion-cause utterance pairs from a conversation. However, there are two shortcomings in the MECPE task: 1) it ignores emotion utterances whose causes cannot be located in the conversation but require contextualized inference;2) it fails to locate the exact causes that occur in vision or audio modalities beyond text. To address these issues, in this paper, we introduce a new task named Multimodal Emotion-Cause Pair Generation in Conversations (MECPG), which aims to identify the emotion utterances with their emotion categories and generate their corresponding causes in a conversation. To tackle the MECPG task, we construct a dataset based on a benchmark corpus for MECPE. We further propose a generative framework named MONICA, which jointly performs emotion recognition and emotion cause generation with a sequence-to-sequence model. Experiments on our annotated dataset show the superiority of MONICA over several competitive systems. Our dataset and source codes will be publicly released. IEEE
Recent advances in wireless sensor networks (WSNs) have brought the sensor based monitoring developments to the surface in many applications. In such a scenario, the security of communication is a major challenge in t...
详细信息
CircRNA-disease association(CDA) can provide a new direction for the treatment of diseases. However,traditional biological experiment is time-consuming and expensive, this urges us to propose the reliable computationa...
详细信息
CircRNA-disease association(CDA) can provide a new direction for the treatment of diseases. However,traditional biological experiment is time-consuming and expensive, this urges us to propose the reliable computational model to predict the associations between circRNAs and diseases. And there is existing more and more evidence indicates that the combination of multi-biomolecular information can improve the prediction accuracy. We propose a novel computational model for CDA prediction named MBCDA, we collect the multi-biomolecular information including circRNA, disease, miRNA and lncRNA based on 6 databases, and construct three heterogeneous network among them, then the multi-heads graph attention networks are applied to these three networks to extract the features of circRNAs and diseases from different views, the obtained features are put into variational graph auto-encoder(VGAE) network to learn the latent distributions of the nodes, a fully connected neural network is adopted to further process the output of VGAE and uses sigmoid function to obtain the predicted probabilities of circRNA-disease *** a result, MBCDA achieved the values of AUC and AUPR under 5-fold cross-validation of 0.893 and 0.887. MBCDA was applied to the analysis of the top-25 predicted associations between circRNAs and diseases, these experimental results show that our proposed MBCDA is a powerful computational model for CDA prediction.
Non-uniformly distributed data in unbalanced datasets have the phenomenon of data stacking and data scattering. However, most traditional metric learning algorithms often overemphasize the intra-class compactness and ...
详细信息
PROBLEM Recent years have witnessed the rapid progress of self-supervised language models (LMs)[1],especially large language models (LLMs)[2].LLMs not only achieved state-of-the-art performance on many natural languag...
PROBLEM Recent years have witnessed the rapid progress of self-supervised language models (LMs)[1],especially large language models (LLMs)[2].LLMs not only achieved state-of-the-art performance on many natural language processing tasks,but also captured widespread attention from the public due to their great potential in a variety of real-world applications (***,search engines,writing assistants,etc.)through providing general-purpose intelligent services.A few of the LLMs are becoming foundation models,an analogy to infrastructure,that empower hundreds of downstream applications.
Cyber Threat Intelligence(CTI)is a valuable resource for cybersecurity defense,but it also poses challenges due to its multi-source and heterogeneous *** personnel may be unable to use CTI effectively to understand th...
详细信息
Cyber Threat Intelligence(CTI)is a valuable resource for cybersecurity defense,but it also poses challenges due to its multi-source and heterogeneous *** personnel may be unable to use CTI effectively to understand the condition and trend of a cyberattack and respond *** address these challenges,we propose a novel approach that consists of three ***,we construct the attack and defense analysis of the cybersecurity ontology(ADACO)model by integrating multiple cybersecurity ***,we develop the threat evolution prediction algorithm(TEPA),which can automatically detect threats at device nodes,correlate and map multisource threat information,and dynamically infer the threat evolution *** leverages knowledge graphs to represent comprehensive threat scenarios and achieves better performance in simulated experiments by combining structural and textual features of ***,we design the intelligent defense decision algorithm(IDDA),which can provide intelligent recommendations for security personnel regarding the most suitable defense *** outperforms the baseline methods in the comparative experiment.
Federated Class-Incremental Learning (FCIL) aims to design privacy-preserving collaborative training methods to continuously learn new classes from distributed datasets. In these scenarios, federated clients face the ...
详细信息
暂无评论