Self-supervised Time-aware Heterogeneous Hypergraph Learning for Dynamic Graph-level Classification
Pages 213 - 221
Abstract
Graph-level learning has gained significant importance in understanding complex systems, such as social and biological networks, but often fails to capture evolving and multi-entity interaction. Current dynamic graph-level classification methods struggle with evolving structures, global properties, and high-order interactions. To address these challenges, we propose DyH2GNet, a novel time-aware self-supervised heterogeneous hypergraph neural network that models complex, non-pairwise interactions and their temporal dynamics by integrating k-hop nodes and attribute correlations into a heterogeneous hypergraph. It features a temporal embedding method that captures high-order proximity and the dynamic context of heterogeneous interactions through intra- and inter-snapshot attention. Furthermore, a graph-level pooling layer aggregates node features with temporal context, supported by self-supervised learning that leverages temporal contrastive learning to maximize the use of unlabeled data. Experiments on real-world datasets demonstrated significant improvements in capturing dynamic graph-level features through unsupervised graph-level tasks, including graph similarity ranking, anomaly detection, and trend analysis.
References
[1]
Bijaya Adhikari, Yao Zhang, Naren Ramakrishnan, and B Aditya Prakash. 2018. Sub2vec: Feature learning for subgraphs. In Advances in Knowledge Discovery and Data Mining: 22nd Pacific-Asia Conf., PAKDD 2018, Melbourne, VIC, Australia, June 3--6, 2018, Proceedings, Part II 22. Springer, 170--182.
[2]
Yunsheng Bai, Hao Ding, Yang Qiao, Agustin Marinovic, Ken Gu, Ting Chen, Yizhou Sun, and Wei Wang. 2019. Unsupervised inductive graph-level representation learning via graph-graph proximity. arXiv preprint arXiv:1904.01098 (2019).
[3]
Moran Beladev, Gilad Katz, Lior Rokach, Uriel Singer, and Kira Radinsky. 2023. GraphERT--Transformers-based Temporal Dynamic Graph Embedding. In Proceedings of the 32nd ACM Intl. Conf. on Info. and Knowledge Management. 68--77.
[4]
Moran Beladev, Lior Rokach, Gilad Katz, Ido Guy, and Kira Radinsky. 2020. tdgraphembed: Temporal dynamic graph-level embedding. In Proceedings of the 29th ACM Intl. Conf. on Information & Knowledge Management. 55--64.
[5]
Horst Bunke and Kim Shearer. 1998. A graph distance metric based on the maximal common subgraph. Pattern recognition letters, Vol. 19, 3--4 (1998), 255--259.
[6]
Ke Chen, Ying Weng, Akram A Hosseini, Tom Dening, Guokun Zuo, and Yiming Zhang. 2024. A comparative study of GNN and MLP based machine learning for the diagnosis of Alzheimer's Disease involving data synthesis. Neural Networks, Vol. 169 (2024), 442--452.
[7]
Yuxiao Dong, Nitesh V Chawla, and Ananthram Swami. 2017. metapath2vec: Scalable representation learning for heterogeneous networks. In Proceedings of the 23rd ACM SIGKDD Intl. Conf. on Knowledge Discovery and Data Mining. 135--144.
[8]
Boxin Du, Changhe Yuan, Robert Barton, Tal Neiman, and Hanghang Tong. 2022. Self-supervised Hypergraph Representation Learning. In 2022 IEEE Intl. Conf. on Big Data (Big Data). IEEE, 505--514.
[9]
Yifan Feng, Haoxuan You, Zizhao Zhang, Rongrong Ji, and Yue Gao. 2019. Hypergraph neural networks. In Proceedings of the AAAI Conf. on Artificial Intelligence, Vol. 33. 3558--3565.
[10]
Xinyu Fu, Jiani Zhang, Ziqiao Meng, and Irwin King. 2020. Magnn: Metapath aggregated graph neural network for heterogeneous graph embedding. In Proceedings of the Web Conference 2020. 2331--2341.
[11]
Yue Gao, Yifan Feng, Shuyi Ji, and Rongrong Ji. 2022. HGNN$^$: General Hypergraph Neural Networks. IEEE Trans. on Pattern Analysis and Machine Intelligence (2022).
[12]
Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the thirteenth Intl. Conf. on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings, 249--256.
[13]
Palash Goyal, Sujit Rokka Chhetri, and Arquimedes Canedo. 2020. dyngraph2vec: Capturing network dynamics using dynamic graph representation learning. Knowledge-Based Systems, Vol. 187 (2020), 104816.
[14]
Palash Goyal, Nitin Kamra, Xinran He, and Yan Liu. 2018. Dyngem: Deep embedding method for dynamic graphs. arXiv preprint arXiv:1805.11273 (2018).
[15]
Aditya Grover and Jure Leskovec. 2016. node2vec: Scalable feature learning for networks. In Proceedings of the 22nd ACM SIGKDD Intl. Conf. on Knowledge Discovery and Data Mining. 855--864.
[16]
Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. Advances in Neural Information Processing Systems, Vol. 30 (2017).
[17]
Malik Khizar Hayat, Shan Xue, Jia Wu, and Jian Yang. 2024b. Heterogeneous Hypergraph Embedding for Node Classification in Dynamic Networks. IEEE Trans. on Artificial Intelligence (2024).
[18]
Malik Khizar Hayat, Shan Xue, and Jian Yang. 2023. Self-supervised Heterogeneous Hypergraph Learning with Context-aware Pooling for Graph-level Classification. In 2023 IEEE Intl. Conf. on Data Mining (ICDM). IEEE, 140--149.
[19]
Malik Khizar Hayat, Shan Xue, and Jian Yang. 2024a. Self-supervised multi-hop heterogeneous hypergraph embedding with informative pooling for graph-level classification. Knowledge and Information Systems (2024), 1--24.
[20]
Chenghan Huang, Lili Wang, Xinyuan Cao, Weicheng Ma, and Soroush Vosoughi. 2022. Learning dynamic graph embeddings using random walk with temporal backtracking. In NeurIPS 2022 Temporal Graph Learning Workshop.
[21]
Byung-Hoon Kim, Jong Chul Ye, and Jae-Jin Kim. 2021. Learning dynamic graph representation of brain connectome with spatio-temporal attention. Advances in Neural Information Processing Systems, Vol. 34 (2021), 4314--4327.
[22]
Thomas N Kipf and Max Welling. 2016. Variational graph auto-encoders. (2016).
[23]
Junhyun Lee, Inyeop Lee, and Jaewoo Kang. 2019. Self-attention graph pooling. In Intl. Conf. on machine learning. pmlr, 3734--3743.
[24]
Mengran Li, Yong Zhang, Wei Zhang, Yi Chu, Yongli Hu, and Baocai Yin. 2023b. Self-supervised Nodes-Hyperedges Embedding for Heterogeneous Information Network Learning. IEEE Trans. on Big Data (2023).
[25]
Xiao Li, Li Sun, Mengjie Ling, and Yan Peng. 2023a. A survey of GNN-based recommendation in social networks. Neurocomputing, Vol. 549 (2023), 126--441.
[26]
Zhijun Liu, Chao Huang, Yanwei Yu, and Junyu Dong. 2021. Motif-preserving dynamic attributed network embedding. In Proceedings of the Web Conf. 2021. 1629--1638.
[27]
Zexi Liu, Bohan Tang, Ziyuan Ye, Xiaowen Dong, Siheng Chen, and Yanfeng Wang. 2024. Hypergraph transformer for semi-supervised classification. In ICASSP 2024--2024 IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 7515--7519.
[28]
Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017).
[29]
Annamalai Narayanan, Mahinthan Chandramohan, Rajasekar Venkatesan, Lihui Chen, Yang Liu, and Shantanu Jaiswal. 2017. graph2vec: Learning distributed representations of graphs. arXiv preprint arXiv:1707.05005 (2017).
[30]
Aldo Pareja, Giacomo Domeniconi, Jie Chen, Tengfei Ma, Toyotaro Suzumura, Hiroki Kanezashi, Tim Kaler, Tao Schardl, and Charles Leiserson. 2020. Evolvegcn: Evolving graph convolutional networks for dynamic graphs. In Proceedings of the AAAI Conf. on Artificial Intelligence, Vol. 34. 5363--5370.
[31]
Jiezhong Qiu, Qibin Chen, Yuxiao Dong, Jing Zhang, Hongxia Yang, Ming Ding, Kuansan Wang, and Jie Tang. 2020. Gcc: Graph contrastive coding for graph neural network pre-training. In Proceedings of the 26th ACM SIGKDD Intl. Conf. on Knowledge Discovery & Data Mining. 1150--1160.
[32]
Shota Saito. 2022. Hypergraph modeling via spectral embedding connection: Hypergraph cut, weighted kernel k-means, and heat kernel. In Proceedings of the AAAI Conf. on Artificial Intelligence, Vol. 36. 8141--8149.
[33]
Wei Shao, Yao Peng, Chen Zu, Mingliang Wang, Daoqiang Zhang, Alzheimer's Disease Neuroimaging Initiative, et al. 2020. Hypergraph based multi-task feature selection for multimodal classification of Alzheimer's disease. Computerized Medical Imaging and Graphics, Vol. 80 (2020), 101663.
[34]
Gen Shi, Yifan Zhu, Jian K Liu, and Xuesong Li. 2023. Hegcl: Advance self-supervised learning in heterogeneous graph-level representation. IEEE Trans. on Neural Networks and Learning Systems (2023).
[35]
Qingyun Sun, Jianxin Li, Hao Peng, Jia Wu, Yuanxing Ning, Philip S Yu, and Lifang He. 2021. Sugar: Subgraph neural network with reinforcement pooling and self-supervised mutual information mechanism. In Proceedings of the Web Conference 2021. 2081--2091.
[36]
Yunbo Tang, Dan Chen, Jia Wu, Weiping Tu, Jessica JM Monaghan, Paul Sowman, and David Mcalpine. 2023. Functional connectivity learning via Siamese-based SPD matrix representation of brain imaging data. Neural Networks, Vol. 163 (2023), 272--285.
[37]
Sheng Tian, Ruofan Wu, Leilei Shi, Liang Zhu, and Tao Xiong. 2021. Self-supervised representation learning on dynamic graphs. In Proceedings of the 30th ACM Intl. Conf. on Information & Knowledge Management. 1814--1823.
[38]
Daixin Wang, Peng Cui, and Wenwu Zhu. 2016. Structural deep network embedding. In Proceedings of the 22nd ACM SIGKDD Intl. Conf. on Knowledge Discovery and Data Mining. 1225--1234.
[39]
Xiao Wang, Nian Liu, Hui Han, and Chuan Shi. 2021. Self-supervised heterogeneous graph neural network with co-contrastive learning. In Proceedings of the 27th ACM SIGKDD Intl. Conf. on Knowledge Discovery & data mining. 1726--1736.
[40]
Xuemei Wei, Yezheng Liu, Jianshan Sun, Yuanchun Jiang, Qifeng Tang, and Kun Yuan. 2023. Dual subgraph-based graph neural network for friendship prediction in location-based social networks. ACM Trans. on Knowledge Discovery from Data, Vol. 17, 3 (2023), 1--28.
[41]
Zhihao Wen and Yuan Fang. 2022. Trend: Temporal event and node dynamics for graph representation learning. In Proceedings of the ACM Web Conf. 2022. 1159--1169.
[42]
Lianghao Xia, Chao Huang, and Chuxu Zhang. 2022. Self-supervised hypergraph transformer for recommender systems. In Proceedings of the 28th ACM SIGKDD Conf. on Knowledge Discovery and Data Mining. 2100--2109.
[43]
Li Xiao, Junqi Wang, Peyman H Kassani, Yipu Zhang, Yuntong Bai, Julia M Stephen, Tony W Wilson, Vince D Calhoun, and Yu-Ping Wang. 2019. Multi-hypergraph learning-based brain functional connectivity analysis in fMRI data. IEEE Trans. on Medical Imaging, Vol. 39, 5 (2019), 1746--1758.
[44]
Dongkuan Xu, Wei Cheng, Dongsheng Luo, Haifeng Chen, and Xiang Zhang. 2021. Infogcl: Information-aware graph contrastive learning. Advances in Neural Information Processing Systems, Vol. 34 (2021), 30414--30425.
[45]
Yuning You, Tianlong Chen, Yongduo Sui, Ting Chen, Zhangyang Wang, and Yang Shen. 2020. Graph contrastive learning with augmentations. Advances in Neural Information Processing Systems, Vol. 33 (2020), 5812--5823.
[46]
Haozhen Zhang, Xueting Han, Xi Xiao, and Jing Bai. 2023a. Time-aware Graph Structure Learning via Sequence Prediction on Temporal Graphs. In Proceedings of the 32nd ACM Intl. Conf. on Info. and Knowledge Management. 3288--3297.
[47]
Siwei Zhang, Yun Xiong, Yao Zhang, Yiheng Sun, Xi Chen, Yizhu Jiao, and Yangyong Zhu. 2023b. RDGSL: Dynamic Graph Representation Learning with Structure Learning. In Proceedings of the 32nd ACM Intl. Conf. on Info. and Knowledge Management. 3174--3183.
[48]
Yongqi Zhang, Quanming Yao, Ling Yue, Xian Wu, Ziheng Zhang, Zhenxi Lin, and Yefeng Zheng. 2023c. Emerging drug interaction prediction enabled by a flow-based graph neural network with biomedical network. Nature Computational Science, Vol. 3, 12 (2023), 1023--1033.
[49]
Lekui Zhou, Yang Yang, Xiang Ren, Fei Wu, and Yueting Zhuang. 2018. Dynamic network embedding by modeling triadic closure process. In Proceedings of the AAAI Conf. on Artificial Intelligence, Vol. 32. 571--578.
Index Terms
- Self-supervised Time-aware Heterogeneous Hypergraph Learning for Dynamic Graph-level Classification
Recommendations
Semi-supervised Time Series Classification Model with Self-supervised Learning
AbstractSemi-supervised learning is a powerful machine learning method. It can be used for model training when only part of the data are labeled. Unlike discrete data, time series data generally have some temporal relation, which can be ...
Highlights- Self-supervised temporal relation learning can assist supervised model for time series classification.
Improving Few-Shot Image Classification with Self-supervised Learning
Cloud Computing – CLOUD 2022AbstractFew-Shot Image Classification (FSIC) aims to learn an image classifier with only a few training samples. The key challenge of few-shot image classification is to learn this classifier with scarce labeled data. To tackle the issue, we leverage the ...
A debiased self-training framework with graph self-supervised pre-training aided for semi-supervised rumor detection
AbstractExisting rumor detection models have achieved remarkable performance in fully-supervised settings. However, it is time-consuming and labor-intensive to obtain extensive labeled rumor data. To mitigate the reliance on labeled data, semi-supervised ...
Highlights- A self-training framework for semi-supervised rumor detection is proposed.
- Graph self-supervised pre-training is employed to alleviate confirmation bias.
- Self-adaptive thresholds are designed to generate reliable pseudo-labels.
Comments
Information & Contributors
Information
Published In
March 2025
1151 pages
ISBN:9798400713293
DOI:10.1145/3701551
- General Chairs:
- Wolfgang Nejdl,
- Sören Auer,
- Proceedings Chair:
- Oliver Karras,
- Program Chairs:
- Meeyoung Cha,
- Marie-Francine Moens,
- Marc Najork
Copyright © 2025 Owner/Author.
This work is licensed under a Creative Commons Attribution International 4.0 License.
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 10 March 2025
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- Australian Research Council (ARC)
- MQ Research Acceleration Project (MQRAS)
Conference
WSDM '25: The Eighteenth ACM International Conference on Web Search and Data Mining
March 10 - 14, 2025
Hannover, Germany
Acceptance Rates
Overall Acceptance Rate 498 of 2,863 submissions, 17%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 08 Mar 2025