Ye Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Ye Wang has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Bin Zhou
National university of defense technology, Changsha, China
7 shared publications - Xin Song
National university of defense technology, Changsha, China
6 shared publications - Aiping Li
College of Computer Science and Technology, National University of Defense Technology, Changsha 410073, China
4 shared publications - Binxing Fang
Guangzhou University
3 shared publications - Haiyang Wang
National University of Defense Technology Changsha China
3 shared publications - Kai Chen
National university of defense technology, Changsha, China
3 shared publications
Latest Publications
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (11) , 11481-11489
LLM-DR: A Novel LLM-Aided Diffusion Model for Rule Generation on Temporal Knowledge Graphs
Among various temporal knowledge graph (TKG) extrapolation methods, rule-based approaches stand out for their explicit rules and transparent reasoning paths. However, the vast search space for rule extraction poses a challenge in identifying high-quality logic rules. To navigate this challenge, we explore the use of generation models to generate new rules, thereby enriching our rule base and enhancing our reasoning capabilities. In this paper, we introduce LLM-DR, an innovative rule-based method for TKG extrapolation, which harnesses diffusion models to generate rules that are consistent with the distribution of the source data, while also amalgamating the rich semantic insights of Large Language Models (LLMs). Specifically, our LLM-DR generates semantically relevant and high-quality rules, employing conditional diffusion models in a classifier-free guidance fashion and refining them with LLM-based constraints. To assess rule efficacy, we meticulously design a coarse-to-fine evaluation strategy that initiates with coarse-grained filtering to eliminate less plausible rules and proceeds with fine-grained scoring to quantify the reliability of the retained. Extensive experiments demonstrate the promising capacity of our LLM-DR.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (11) , 11481-11489
Open AccessLLM-DR: A Novel LLM-Aided Diffusion Model for Rule Generation on Temporal Knowledge Graphs
Among various temporal knowledge graph (TKG) extrapolation methods, rule-based approaches stand out for their explicit rules and transparent reasoning paths. However, the vast search space for rule extraction poses a challenge in identifying high-quality logic rules. To navigate this challenge, we explore the use of generation models to generate new rules, thereby enriching our rule base and enhancing our reasoning capabilities. In this paper, we introduce LLM-DR, an innovative rule-based method for TKG extrapolation, which harnesses diffusion models to generate rules that are consistent with the distribution of the source data, while also amalgamating the rich semantic insights of Large Language Models (LLMs). Specifically, our LLM-DR generates semantically relevant and high-quality rules, employing conditional diffusion models in a classifier-free guidance fashion and refining them with LLM-based constraints. To assess rule efficacy, we meticulously design a coarse-to-fine evaluation strategy that initiates with coarse-grained filtering to eliminate less plausible rules and proceeds with fine-grained scoring to quantify the reliability of the retained. Extensive experiments demonstrate the promising capacity of our LLM-DR.
- 25 March 2025
- Published by Springer Nature in World Wide Web
- Vol. 28 (3) , 1-25
Geometry fusion representation for knowledge graph completion using multi-view information bottleneck
- 25 March 2025
- Published by Springer Nature in World Wide Web
- Vol. 28 (3) , 1-25
Geometry fusion representation for knowledge graph completion using multi-view information bottleneck
- 6 March 2025
- Published by Springer Nature
- p. 148-180
The Application of the MDATA Cognitive Model in Open Source Intelligence Analysis
- 6 March 2025
- Published by Springer Nature
- p. 148-180
The Application of the MDATA Cognitive Model in Open Source Intelligence Analysis
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 10042-10060
MusKGC: A Flexible Multi-source Knowledge Enhancement Framework for Open-World Knowledge Graph Completion
Xin Song, Liu Haiyan, Haiyang Wang, Ye Wang, Kai Chen, Bin Zhou. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 10042-10060
Open AccessMusKGC: A Flexible Multi-source Knowledge Enhancement Framework for Open-World Knowledge Graph Completion
Xin Song, Liu Haiyan, Haiyang Wang, Ye Wang, Kai Chen, Bin Zhou. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- 18 December 2024
- Published by Springer Nature in World Wide Web
- Vol. 28 (1) , 1-22
Incorporating structural knowledge into language models for open knowledge graph completion
- 18 December 2024
- Published by Springer Nature in World Wide Web
- Vol. 28 (1) , 1-22
Incorporating structural knowledge into language models for open knowledge graph completion
- 3 December 2024
- Published by Springer Nature
- p. 41-55
Target-Specific Hate Trend Prediction on Social Network
- 3 December 2024
- Published by Springer Nature
- p. 41-55
Target-Specific Hate Trend Prediction on Social Network
- Open Access
- 1 August 2024
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 4, 3281-3289
Mitigating Message Imbalance in Fraud Detection with Dual-View Graph Representation Learning
Graph representation learning has become a mainstream method for fraud detection due to its strong expressive power, which focuses on enhancing node representations through improved neighborhood knowledge capture. However, the focus on local interactions leads to imbalanced transmission of global topological information and increased risk of node-specific information being overwhelmed during aggregation due to the imbalance between fraud and benign nodes. In this paper, we first summarize the impact of topology and class imbalance on downstream tasks in GNN-based fraud detection, as the problem of imbalanced supervisory messages is caused by fraudsters' topological behavior obfuscation and identity feature concealment. Based on statistical validation, we propose a novel dual-view graph representation learning method to mitigate Message imbalance in Fraud Detection (MimbFD). Specifically, we design a topological message reachability module for high-quality node representation learning to penetrate fraudsters' camouflage and alleviate insufficient propagation. Then, we introduce a local confounding debiasing module to adjust node representations, enhancing the stable association between node representations and labels to balance the influence of different classes. Finally, we conducted experiments on three public fraud datasets, and the results demonstrate that MimbFD exhibits outstanding performance in fraud detection.
- 1 August 2024
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 4, 3281-3289
Open AccessMitigating Message Imbalance in Fraud Detection with Dual-View Graph Representation Learning
Graph representation learning has become a mainstream method for fraud detection due to its strong expressive power, which focuses on enhancing node representations through improved neighborhood knowledge capture. However, the focus on local interactions leads to imbalanced transmission of global topological information and increased risk of node-specific information being overwhelmed during aggregation due to the imbalance between fraud and benign nodes. In this paper, we first summarize the impact of topology and class imbalance on downstream tasks in GNN-based fraud detection, as the problem of imbalanced supervisory messages is caused by fraudsters' topological behavior obfuscation and identity feature concealment. Based on statistical validation, we propose a novel dual-view graph representation learning method to mitigate Message imbalance in Fraud Detection (MimbFD). Specifically, we design a topological message reachability module for high-quality node representation learning to penetrate fraudsters' camouflage and alleviate insufficient propagation. Then, we introduce a local confounding debiasing module to adjust node representations, enhancing the stable association between node representations and labels to balance the influence of different classes. Finally, we conducted experiments on three public fraud datasets, and the results demonstrate that MimbFD exhibits outstanding performance in fraud detection.
- Open Access
DA-PFL: Dynamic Affinity Aggregation for Personalized Federated Learning
Personalized federated learning becomes a hot research topic that can learn a personalized learning model for each client. Existing personalized federated learning models prefer to aggregate similar clients with similar data distribution to improve the performance of learning models. However, similaritybased personalized federated learning methods may exacerbate the class imbalanced problem. In this paper, we propose a novel Dynamic Affinity-based Personalized Federated Learning model (DA-PFL) to alleviate the class imbalanced problem during federated learning. Specifically, we build an affinity metric from a complementary perspective to guide which clients should be aggregated. Then we design a dynamic aggregation strategy to dynamically aggregate clients based on the affinity metric in each round to reduce the class imbalanced risk. Extensive experiments show that the proposed DA-PFL model can significantly improve the accuracy of each client in three real-world datasets with state-of-the-art comparison methods.
Open AccessDA-PFL: Dynamic Affinity Aggregation for Personalized Federated Learning
Personalized federated learning becomes a hot research topic that can learn a personalized learning model for each client. Existing personalized federated learning models prefer to aggregate similar clients with similar data distribution to improve the performance of learning models. However, similaritybased personalized federated learning methods may exacerbate the class imbalanced problem. In this paper, we propose a novel Dynamic Affinity-based Personalized Federated Learning model (DA-PFL) to alleviate the class imbalanced problem during federated learning. Specifically, we build an affinity metric from a complementary perspective to guide which clients should be aggregated. Then we design a dynamic aggregation strategy to dynamically aggregate clients based on the affinity metric in each round to reduce the class imbalanced risk. Extensive experiments show that the proposed DA-PFL model can significantly improve the accuracy of each client in three real-world datasets with state-of-the-art comparison methods.
- 9 August 2023
- Published by Springer Nature in World Wide Web
- Vol. 26 (5) , 3607-3632
Quantifying controversy from stance, sentiment, offensiveness and sarcasm: a fine-grained controversy intensity measurement framework on a Chinese dataset
- 9 August 2023
- Published by Springer Nature in World Wide Web
- Vol. 26 (5) , 3607-3632
Quantifying controversy from stance, sentiment, offensiveness and sarcasm: a fine-grained controversy intensity measurement framework on a Chinese dataset
- Open Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 10902-10913
Aspect-to-Scope Oriented Multi-view Contrastive Learning for Aspect-based Sentiment Analysis
Heyan Chai, Ziyi Yao, Siyu Tang, Ye Wang, Liqiang Nie, Binxing Fang, Qing Liao. Findings of the Association for Computational Linguistics: EMNLP 2023. 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 10902-10913
Open AccessAspect-to-Scope Oriented Multi-view Contrastive Learning for Aspect-based Sentiment Analysis
Heyan Chai, Ziyi Yao, Siyu Tang, Ye Wang, Liqiang Nie, Binxing Fang, Qing Liao. Findings of the Association for Computational Linguistics: EMNLP 2023. 2023.