Dynamic heterogeneous graph representation based on adaptive negative sample mining via high-fidelity instances and context-aware uncertainty learning

被引:0
作者
Bai, Wenhao [1 ]
Qiu, Liqing [1 ]
Zhao, Weidong [1 ]
机构
[1] Shandong Univ Sci & Technol, Coll Comp Sci & Engn, Qingdao 266590, Peoples R China
关键词
Graph encoder; Dynamic heterogeneous graph; Graph contrastive learning; Negative sample mining; NETWORKS;
D O I
10.1016/j.eswa.2025.127291
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Graph contrastive learning is a self-supervised learning method widely used in dynamic heterogeneous graph representation in recent years, demonstrating great potential and achieving excellent results. However, most graph contrastive learning methods randomly select negative samples and treat all negative samples as equally important to the model. This ignores that some negative samples can provide more information due to their closer proximity to positive samples in the feature space or higher semantic similarity. Therefore, this paper proposes a HCUAN model that aims to utilize high-fidelity anchor instances and corresponding positive and negative samples for context-aware uncertainty learning to adaptively mine prioritized negative samples, which in turn improves the performance of graph contrastive learning. Specifically, the HCUAN first designs a new GNN encoder (LGE) for generating high-fidelity anchor instances and corresponding positive and negative samples, which efficiently fuses between local and global information to prevents the introduction of easy negative samples and enhance the model's discriminative ability. Then, the HCUAN utilizes an uncertainty discriminator to perform an adaptive assessment of the correlation between each negative sample and the anchor instance, which provides more accurate references for graph contrastive learning, thus helping the model to distinguish the really prioritized negative samples more clearly. Next, the HCUAN designs an unified graph contrastive learning, which incorporates the modeling method of dynamic heterogeneous graphs in graph contrastive learning, the method of generating high-fidelity anchor instances and corresponding positive and negative samples, and the method of prioritized negative samples mining in the form of modules into the traditional processes of graph contrastive learning. Each module in the unified graph contrastive learning can be disassembled and updated according to the needs of the task, providing powerful flexibility and scalability for practical applications. Finally, numerous experiments on twelve datasets show that HCUAN can significantly improve the performance of graph contrastive learning.
引用
收藏
页数:17
相关论文
共 69 条
[1]   CommonGraph: Graph Analytics on Evolving Data [J].
Afarin, Mahbod ;
Gao, Chao ;
Rahman, Shafiur ;
Abu-Ghazaleh, Nael ;
Gupta, Rajiv .
PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON ARCHITECTURAL SUPPORT FOR PROGRAMMING LANGUAGES AND OPERATING SYSTEMS, VOL 2, ASPLOS 2023, 2023, :133-145
[2]   Make Heterophilic Graphs Better Fit GNN: A Graph Rewiring Approach [J].
Bi, Wendong ;
Du, Lun ;
Fu, Qiang ;
Wang, Yanlin ;
Han, Shi ;
Zhang, Dongmei .
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2024, 36 (12) :8744-8757
[3]   Improving Augmentation Consistency for Graph Contrastive Learning [J].
Bu, Weixin ;
Cao, Xiaofeng ;
Zheng, Yizhen ;
Pan, Shirui .
PATTERN RECOGNITION, 2024, 148
[4]  
Caron M, 2020, ADV NEUR IN, V33
[5]   Heterogeneous Graph Contrastive Learning for Recommendation [J].
Chen, Mengru ;
Huang, Chao ;
Xia, Lianghao ;
Wei, Wei ;
Xu, Yong ;
Luo, Ronghua .
PROCEEDINGS OF THE SIXTEENTH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING, WSDM 2023, VOL 1, 2023, :544-552
[6]  
Cong WL, 2023, Arxiv, DOI arXiv:2302.11636
[7]  
Feng Yunzhen, 2023, 12 INT C LEARN REPR
[8]   Legislative cosponsorship networks in the US House and Senate [J].
Fowler, James H. .
SOCIAL NETWORKS, 2006, 28 (04) :454-465
[9]   Collaborative graph neural networks for augmented graphs: A local-to-global perspective [J].
Guo, Qihang ;
Yang, Xibei ;
Li, Ming ;
Qian, Yuhua .
PATTERN RECOGNITION, 2025, 158
[10]   Convolutional gated recurrent unit-driven multidimensional dynamic graph neural network for subject-independent emotion recognition [J].
Guo, Wenhui ;
Wang, Yanjiang .
EXPERT SYSTEMS WITH APPLICATIONS, 2024, 238