1. Institute of Physical Science and Information Technology, Anhui University, Hefei 230601; 2. Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui University, Hefei 230601; 3. School of Mathematical Sciences, Anhui University, Hefei 230601
Abstract：Network alignment is intended to mine node correspondences between different networks, and it is crucial for integrating information across diverse domains. However, most existing methods focus on ordinary graphs and overlook the prevalent high-order group interactions in real-world systems. There are only a few hypergraph alignment methods relying solely on shallow local topological information and failing to capture the deep structural semantics of nodes. To address this issue, a multi-view contrastive learning method for hypergraph alignment is proposed, named hypergraph-clique expansion contrastive learning (HCCL). A multi-view contrastive learning framework is constructed. Node structural features are collaboratively captured from both higher-order and lower-order complementary perspectives to more effectively leverage the rich structural information of hypergraphs for alignment tasks. The original hypergraph and its clique expansion graph are utilized as dual views simultaneously. The original hypergraph learns higher-order group relationships through hypergraph neural networks, while its clique expansion graph captures lower-order pairwise relationships via graph convolutional networks. On this basis, a cross-view contrastive learning mechanism is introduced to extract more robust and intrinsic node features spanning different structural scales by maximizing the consistency of node embeddings across both views. Extensive experiments on real-world datasets fully validate the effectiveness and robustness of HCCL.
[1] TANG R, YONG Z Y, JIANG S Y, et al. Network Alignment. Phy-sics Reports, 2025, 1107: 1-45. [2] TRUNG H T, TOAN N T, VAN VINH T,et al. A Comparative Study on Network Alignment Techniques. Expert Systems with Appli-cations, 2020, 140. DOI: 10.1016/j.eswa.2019.112883. [3] CHU X K, FAN X X, YAO D, et al. Cross-Network Embedding for Multi-network Alignment // Proc of the World Wide Web Confe-rence. New York, USA: ACM, 2019: 273-284. [4] SHU K, WANG S H, TANG J L, et al. User Identity Linkage Across Online Social Networks: A Review. ACM SIGKDD Explorations Newsletter, 2017, 18(2): 5-17. [5] BURKE D F, BRYANT P, BARRIO-HERNANDEZ I, et al. Towards a Structurally Resolved Human Protein Interaction Network. Nature Structural & Molecular Biology, 2023, 30(2): 216-225. [6] 段乐乐,李博一,丁滋钊,等.目标域特征感知与互补用户迁移的跨域推荐模型.小型微型计算机系统, 2024, 45(1): 93-100. (DUAN L L, LI B Y, DING Z Z, et al. Cross-Domain Recommendation Model Based on Target Domain Feature Awareness and Complementary User Transfer. Journal of Chinese Computer Systems, 2024, 45(1): 93-100.) [7] XIAN J J, LIU M H, CHENG X, et al. Modelling Multiscale Infectious Disease in Complex Systems. Physics Reports, 2025, 1113: 1-57. [8] OUVRARD X.Hypergraphs: An Introduction and Review[C/OL]. [2025-11-15].https://arxiv.org/pdf/2002.05014. [9] ANTELMI A, CORDASCO G, POLATO M, et al. A Survey on Hypergraph Representation Learning. ACM Computing Surveys, 2024, 56(1). DOI: 10.1145/3605776. [10] GAO Y, ZHANG Z Z, LIN H J, et al. Hypergraph Learning: Me-thods and Practices. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(5): 2548-2566. [11] GUO X Y, LIU Y, GONG D F, et al. Dual Graph Convolutional Networks for Social Network Alignment. IEEE Transactions on Big Data, 2025, 11(2): 684-695. [12] MAN T, SHEN H W, LIU S H, et al. Predict Anchor Links Across Social Networks via an Embedding Approach // Proc of the 25th International Joint Conference on Artificial Intelligence. San Francisco, USA: IJCAI, 2016: 1823-1829. [13] PENG H, LI S Z, ZHAO D D, et al. Network Alignment Based on Multiple Hypernetwork Attributes. The European Physical Journal Special Topics, 2024, 233(4): 843-861. [14] WU X, LI Z H, HU Z J, et al. Aligning Users Across Social Networks Based on Hypergraph Embedding // Proc of the IEEE 9th International Conference on Data Science in Cyberspace. Washington, USA: IEEE, 2024: 691-698. [15] BAI S, ZHANG F H, TORR P H S. Hypergraph Convolution and Hypergraph Attention. Pattern Recognition, 2021, 110. DOI: 10.1016/j.patcog.2020.107637. [16] KIPF T N, WELLING M.Semi-supervised Classification with Graph Convolutional Networks[C/OL]. [2025-11-15].https://arxiv.org/pdf/1609.02907. [17] LEE D, SHIN K.I'm Me, We're Us, and I'm Us: Tri-Directional Contrastive Learning on Hypergraphs. Proc of the AAAI Confe-rence on Artificial Intelligence, 2023, 37(7): 8456-8464. [18] KUMAR T, DARWIN K, PARTHASARATHY S, et al. HPRA: Hyperedge Prediction Using Resource Allocation // Proc of the 12th ACM Conference on Web Science. New York, USA: ACM, 2020: 135-143. [19] AMBURG I, VELDT N, BENSON A.Clustering in Graphs and Hypergraphs with Categorical Edge Labels // Proc of the Web Conference. New York, USA: ACM, 2020: 706-717. [20] KIM K, KIM J, KIM M, et al. Therapeutic Gene Target Prediction Using Novel Deep Hypergraph Representation Learning. Briefings in Bioinformatics, 2025, 26(1). DOI: 10.1093/bib/bbaf019. [21] PENG W, LIN J Z, DAI W, et al. Hypergraph Representation Learning for Cancer Drug Response Prediction // Proc of the 20th International Symposium on Bioinformatics Research and Applications. Berlin, Germany: Springer, 2024: 339-349. [22] KHOSHRAFTAR S, AN A J.A Survey on Graph Representation Learning Methods. ACM Transactions on Intelligent Systems and Technology, 2024, 15(1). DOI: 10.1145/363351. [23] MA T Y, QIAN Y Y, ZHANG S N, et al. Adaptive Expansion for Hypergraph Learning[C/OL].[2025-11-15]. https://arxiv.org/pdf/2502.15564. [24] YANG C Q, WANG R J, YAO S C, et al. Semi-supervised Hypergraph Node Classification on Hypergraph Line Expansion // Proc of the 31st ACM International Conference on Information & Knowledge Management. New York, USA: ACM, 2022: 2352-2361. [25] YAN Y G, CHEN Y L, WANG S B, et al. Hypergraph Joint Re-presentation Learning for Hypervertices and Hyperedges via Cross Expansion. Proc of the AAAI Conference on Artificial Intelligence, 2024, 38(8): 9232-9240. [26] CARLETTI T, BATTISTON F, CENCETTI G, et al. Random Walks on Hypergraphs. Physical Review E, 2020, 101(2). DOI: 10.1103/PhysRevE.101.022308. [27] ZHANG L L, ZHANG Z W, WANG G R, et al. Efficiently Sampling and Estimating Hypergraphs by Hybrid Random Walk // Proc of the IEEE 39th International Conference on Data Engineering. Washington, USA: IEEE, 2023: 1273-1285. [28] LUO Q, XIE Z Z, LIU Y, et al. Sampling Hypergraphs via Joint Unbiased Random Walk. World Wide Web, 2024, 27(2). DOI: 10.1007/s11280-024-01253-8. [29] LIANG L, CAI S M, GONG S C.Hypergraph Representation Learning with Weighted- and Clustering-Biased Random Walks. Entropy, 2025, 27(10). DOI: 10.3390/e27101072. [30] FENG Y F, YOU H X, ZHANG Z Z, et al. Hypergraph Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(1): 3558-3565. [31] GAO Y, FENG Y F, JI S Y, et al. HGNN+: General Hypergraph Neural Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(3): 3181-3199. [32] 傅晨波,陈殊杭,胡剑波,等.基于超图嵌入和有限注意力的社会化推荐.小型微型计算机系统, 2024, 45(1): 115-122. (FU C B, CHEN S H, HU J B, et al. Social Recommendation Based on Hypergraph Embedding and Limited Attention. Journal of Chinese Computer Systems, 2024, 45(1): 115-122.) [33] DING X, MA C, ZHANG X Y, et al. SOIDP: Predicting Interlayer Links in Multiplex Networks. IEEE Transactions on Computational Social Systems, 2022, 9(4): 997-1007. [34] TANG R, PENG Y M, LI J X, et al. Compact Network Alignment with Mitigated Sensitive Information Exposing in P2P Networks: A Community Partition-Based Approach. Peer-to-Peer Networking and Applications, 2025, 18(3). DOI: 10.1007/s12083-025-01945-6. [35] LÁZARO T, GUIMERÁ R, SALES-PARDO M. Probabilistic Align-ment of Multiple Networks. Nature Communications, 2025, 16(1). DOI: 10.1038/s41467-025-59077-7. [36] PARK J, TRAN C, SHIN W, et al. On the Power of Gradual Network Alignment Using Dual-Perception Similarities. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(12): 15292-15307. [37] PENG Q Y, WANG Y H, JIAO P F, et al. Alleviate the Impact of Heterogeneity in Network Alignment from Community View. IEEE Transactions on Neural Networks and Learning Systems, 2025, 36(6): 11313-11326. [38] JIAO P F, LIU Y Q, WANG Y H, et al. Interactive Graph Lear-ning for Multilevel Network Alignment. IEEE Transactions on Neural Networks and Learning Systems, 2025, 36(11): 19924-19938. [39] VAN DEN OORD A, LI Y Z, VINYALS O. Representation Lear-ning with Contrastive Predictive Coding[C/OL].[2025-11-15]. https://arxiv.org/pdf/1807.03748. [40] ZHENG C H, PAN L, WU P.CAMU: Cycle-Consistent Adversa-rial Mapping Model for User Alignment Across Social Networks. IEEE Transactions on Cybernetics, 2022, 52(10): 10709-10720. [41] ZENG Z C, DU B X, ZHANG S, et al. Hierarchical Multi-margi-nal Optimal Transport for Network Alignment. Proc of the AAAI Conference on Artificial Intelligence, 2024, 38(15): 16660-16668. [42] ZHANG H F, REN G J, DING X, et al. Collaborative Cross-Network Embedding Framework for Network Alignment. IEEE Transactions on Network Science and Engineering, 2024, 11(3): 2989-3001. [43] YU Q, ZENG Z C, YAN Y C, et al. Joint Optimal Transport and Embedding for Network Alignment // Proc of the ACM on Web Conference. New York, USA: ACM, 2025: 2064-2075.
2025, Vol. 38 
