research-article

MINES: message intercommunication for inductive relation reasoning over neighbor-enhanced subgraphs

AUTHORs:

Xinwang LiuAuthors Info & Claims

AAAI'24/IAAI'24/EAAI'24: Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symposium on Educational Advances in Artificial Intelligence

Article No.: 1187, Pages 10645 - 10653

https://doi.org/10.1609/aaai.v38i9.28935

Published: 20 February 2024 Publication History

Abstract

GraIL and its variants have shown their promising capacities for inductive relation reasoning on knowledge graphs. However, the uni-directional message-passing mechanism hinders such models from exploiting hidden mutual relations between entities in directed graphs. Besides, the enclosing subgraph extraction in most GraIL-based models restricts the model from extracting enough discriminative information for reasoning. Consequently, the expressive ability of these models is limited. To address the problems, we propose a novel GraIL-based framework, termed MINES, by introducing a Message Intercommunication mechanism on the Neighbor-Enhanced Subgraph. Concretely, the message intercommunication mechanism is designed to capture the omitted hidden mutual information. It introduces bi-directed information interactions between connected entities by inserting an undirected/bi-directed GCN layer between uni-directed RGCN layers. Moreover, inspired by the success of involving more neighbors in other graph-based tasks, we extend the neighborhood area beyond the enclosing subgraph to enhance the information collection for inductive relation reasoning. Extensive experiments prove the promising capacity of the proposed MINES from various aspects, especially for the superiority, effectiveness, and transfer ability.

References

[1]

Bi, W.; Cheng, X.; Xu, B.; Sun, X.; Xu, L.; and Shen, H. 2023a. Bridged-GNN: Knowledge Bridge Learning for Effective Knowledge Transfer. In CIKM, 99-109.

[2]

Bi, W.; Xu, B.; Sun, X.; Xu, L.; Shen, H.; and Cheng, X. 2023b. Predicting the silent majority on graphs: Knowledge transferable graph neural network. In Proceedings of the ACM Web Conference 2023, 274-285.

[3]

Bordes, A.; Usunier, N.; Garcia-Duran, A.; Weston, J.; and Yakhnenko, O. 2013. Translating embeddings for modeling multi-relational data. NeurIPs, 26: 2787-2795.

[4]

Chen, H.; Huang, Z.; Xu, Y.; Deng, Z.; Huang, F.; He, P.; and Li, Z. 2022a. Neighbor enhanced graph convolutional networks for node classification and recommendation. KBS, 246: 108594.

Digital Library

[5]

Chen, J.; He, H.; Wu, F.; and Wang, J. 2021. Topology-Aware Correlations Between Relations for Inductive Link Prediction in Knowledge Graphs. AAAI, 35: 6271-6278.

[6]

Chen, M.; Zhang, W.; Geng, Y.; Xu, Z.; Pan, J. Z.; and Chen, H. 2023a. Generalizing to Unseen Elements: A Survey on Knowledge Extrapolation for Knowledge Graphs. arXiv preprint arXiv:2302.01859.

[7]

Chen, M.; Zhang, W.; Yao, Z.; Chen, X.; Ding, M.; Huang, F.; and Chen, H. 2022b. Meta-learning based knowledge extrapolation for knowledge graphs in the federated setting. arXiv preprint arXiv:2205.04692.

[8]

Chen, M.; Zhang, W.; Zhu, Y.; Zhou, H.; Yuan, Z.; Xu, C.; and Chen, H. 2022c. Meta-Knowledge Transfer for Inductive Knowledge Graph Embedding. In SIGIR.

[9]

Chen, W.; Wan, H.; Guo, S.; Huang, H.; Zheng, S.; Li, J.; Lin, S.; and Lin, Y. 2022d. Building and exploiting spatial-temporal knowledge graph for next POI recommendation. KBS.

[10]

Chen, W.; Wan, H.; Wu, Y.; Zhao, S.; Cheng, J.; Li, Y.; and Lin, Y. 2023b. Local-Global History-aware Contrastive Learning for Temporal Knowledge Graph Reasoning. arXiv preprint arXiv:2312.01601.

[11]

Chen, X.; Zhang, J.; Wang, X.; Wu, T.; Deng, S.; Wang, Y.; Si, L.; Chen, H.; and Zhang, N. 2023c. Continual Multimodal Knowledge Graph Construction. arXiv preprint arXiv:2305.08698.

[12]

Chen, X.; Zhang, N.; Xie, X.; Deng, S.; Yao, Y.; Tan, C.; Huang, F.; Si, L.; and Chen, H. 2022e. Knowprompt: Knowledge-aware prompt-tuning with synergistic optimization for relation extraction. In Proceedings of the ACM Web conference 2022, 2778-2788.

[13]

Chen, Z.; Li, D.; Zhao, X.; Hu, B.; and Zhang, M. 2023d. Temporal Knowledge Question Answering via Abstract Reasoning Induction. arXiv preprint arXiv:2311.09149.

[14]

Chen, Z.; Liao, J.; and Zhao, X. 2023. Multi-granularity Temporal Question Answering over Knowledge Graphs. In ACL, 11378-11392. Toronto, Canada.

[15]

Devlin, J.; Chang, M.-W.; Lee, K.; and Toutanova, K. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NACCL.

[16]

Feng, Y.; You, H.; Zhang, Z.; Ji, R.; and Gao, Y. 2019. Hypergraph neural networks. In AAAI.

[17]

Galárraga, L. A.; Teflioudi, C.; Hose, K.; and Suchanek, F. 2013. AMIE: Association Rule Mining under Incomplete Evidence in Ontological Knowledge Bases. In WWW.

Digital Library

[18]

Geng, Y.; Chen, J.; Pan, J. Z.; Chen, M.; Jiang, S.; Zhang, W.; and Chen, H. 2023. Relational message passing for fully inductive knowledge graph completion. In ICDE, 1221-1233. IEEE.

[19]

Hamilton, W. L.; Ying, R.; and Leskovec, J. 2017. Inductive representation learning on large graphs. In NeurIPs.

[20]

Li, Q.; Guo, S.; Ji, C.; Peng, X.; Cui, S.; and Li, J. 2023. Dual-Gated Fusion with Prefix-Tuning for Multi-Modal Relation Extraction. arXiv preprint arXiv:2306.11020.

[21]

Liang, K.; Meng, L.; Liu, M.; Liu, Y.; Tu, W.; Wang, S.; Zhou, S.; Liu, X.; and Sun, F. 2022. Reasoning over different types of knowledge graphs: Static, temporal and multimodal. arXiv preprint arXiv:2212.05767.

[22]

Liu, S.; Ying, R.; Dong, H.; Li, L.; Xu, T.; Rong, Y.; Zhao, P.; Huang, J.; and Wu, D. 2022. Local augmentation for graph neural networks. In ICML, 14054-14072. Baltimore, Maryland USA: PMLR.

[23]

Long, X.; Huang, C.; Xu, Y.; Xu, H.; Dai, P.; Xia, L.; and Bo, L. 2021. Social recommendation with self-supervised metagraph informax network. In CIKM.

[24]

Luo, L.; Li, Y.-F.; Haffari, G.; and Pan, S. 2023a. Normalizing flow-based neural process for few-shot knowledge graph completion. In SIGIR.

[25]

Luo, L.; Li, Y.-F.; Haffari, G.; and Pan, S. 2023b. Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning. arXiv preprint arxiv:2310.01061.

[26]

Mai, S.; Zheng, S.; Yang, Y.; and Hu, H. 2021. Communicative Message Passing for Inductive Relation Reasoning. In AAAI.

[27]

Meilicke, C.; Fink, M.; Wang, Y.; Ruffinelli, D.; Gemulla, R.; and Stuckenschmidt, H. 2018. Fine-grained evaluation of rule-and embedding-based systems for knowledge graph completion. In ISWC, 3-20. Monterey: Springer.

[28]

Mo, Y.; Chen, Y.; Lei, Y.; Peng, L.; Shi, X.; Yuan, C.; and Zhu, X. 2023a. Multiplex Graph Representation Learning Via Dual Correlation Reduction.

[29]

Mo, Y.; Lei, Y.; Shen, J.; Shi, X.; Shen, H. T.; and Zhu, X. 2023b. Disentangled Multiplex Graph Representation Learning. In ICML.

[30]

Niu, G.; Li, Y.; Tang, C.; Geng, R.; Dai, J.; Liu, Q.; Wang, H.; Sun, J.; Huang, F.; and Si, L. 2021. Relational learning with gated and attentive neighbor aggregator for few-shot knowledge graph completion. In SIGIR, 213-222. Montréal, Quebec: ACM.

[31]

Pan, S.; Luo, L.; Wang, Y.; Chen, C.; Wang, J.; and Wu, X. 2023. Unifying Large Language Models and Knowledge Graphs: A Roadmap. arXiv preprint arxiv:2306.08302.

[32]

Pan, Y.; Liu, J.; Zhang, L.; Hu, X.; Zhao, T.; and Lin, Q. 2021. Learning First-Order Rules with Relational Path Contrast for Inductive Relation Reasoning. In arXiv preprint arXiv:2110.08810.

[33]

Sadeghian, A.; Armandpour, M.; Ding, P.; and Wang, D. Z. 2019. Drum: End-to-end differentiable rule mining on knowledge graphs. NeurIPs, 32.

[34]

Scarselli, F.; Gori, M.; Tsoi, A. C.; Hagenbuchner, M.; and Monfardini, G. 2008. The graph neural network model. TNN.

[35]

Schlichtkrull, M.; Kipf, T. N.; Bloem, P.; Berg, R. v. d.; Titov, I.; and Welling, M. 2018. Modeling relational data with graph convolutional networks. In ESWC.

[36]

Song, S.; Li, X.; and Li, S. 2023. How to Bridge the Gap between Modalities: A Comprehensive Survey on Multimodal Large Language Model. arXiv preprint arXiv:2311.07594.

[37]

Sun, Z.; Deng, Z.-H.; Nie, J.-Y.; and Tang, J. 2018. RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space. In ICLR.

[38]

Teru, K. K.; Denis, E.; and Hamilton, W. L. 2020. Inductive Relation Prediction by Subgraph Reasoning. ICML.

[39]

Trouillon, T.; Dance, C. R.; Gaussier, É.; Welbl, J.; Riedel, S.; and Bouchard, G. 2017. Knowledge Graph Completion via Complex Tensor Factorization. JMLR, 18: 1-38.

Digital Library

[40]

Tu, W.; Zhou, S.; Liu, X.; Ge, C.; Cai, Z.; and Liu, Y. 2023. Hierarchically Contrastive Hard Sample Mining for Graph Self-Supervised Pretraining. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 1-14.

[41]

Tu, W.; Zhou, S.; Liu, X.; Liu, Y.; Cai, Z.; Zhu, E.; Zhang, C.; and Cheng, J. 2022. Initializing Then Refining: A Simple Graph Attribute Imputation Network. In Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI), 3494-3500.

[42]

Vashishth, S.; Sanyal, S.; Nitin, V.; and Talukdar, P. 2019. Composition-based Multi-Relational Graph Convolutional Networks. In ICLR.

[43]

Veličković, P.; Cucurull, G.; Casanova, A.; Romero, A.; Liò, P.; and Bengio, Y. 2018. Graph Attention Networks. In ICLR.

[44]

Wang, P.; Agarwal, K.; Ham, C.; Choudhury, S.; and Reddy, C. K. 2021. Self-supervised learning of contextual embeddings for link prediction in heterogeneous networks. In WWW.

[45]

Wang, X.; Ji, H.; Shi, C.; Wang, B.; Ye, Y.; Cui, P.; and Yu, P. S. 2019. Heterogeneous graph attention network. In WWW.

[46]

Wei, W.; Ren, X.; Tang, J.; Wang, Q.; Su, L.; Cheng, S.; Wang, J.; Yin, D.; and Huang, C. 2023. LLMRec: Large Language Models with Graph Augmentation for Recommendation. arXiv preprint arXiv:2311.00423.

[47]

Welling, M.; and Kipf, T. N. 2017. Semi-supervised classification with graph convolutional networks. In ICLR.

[48]

Wen, Y.; Liu, S.; Wan, X.; Wang, S.; Liang, K.; Liu, X.; Yang, X.; and Zhang, P. 2023a. Efficient Multi-View Graph Clustering with Local and Global Structure Preservation. In MM.

[49]

Wen, Y.; Wang, S.; Liao, Q.; Liang, W.; Liang, K.; Wan, X.; and Liu, X. 2023b. Unpaired Multi-View Graph Clustering with Cross-View Structure Matching. T-NNLS.

[50]

Xia, J.; Zhu, Y.; Du, Y.; and Li, S. Z. 2022. A survey of pre-training on graphs: Taxonomy, methods, and applications. arXiv preprint arXiv:2202.07893.

[51]

Yang, F.; Yang, Z.; and Cohen, W. W. 2017. Differentiable learning of logical rules for knowledge base reasoning. NeurIPs, 30.

[52]

Yang, X.; Jin, J.; Wang, S.; Liang, K.; Liu, Y.; Wen, Y.; Liu, S.; Zhou, S.; Liu, X.; and Zhu, E. 2023a. DealMVC: Dual Contrastive Calibration for Multi-view Clustering. In ACM MM.

[53]

Yang, X.; Tan, C.; Liu, Y.; Liang, K.; Wang, S.; Zhou, S.; Xia, J.; Li, S. Z.; Liu, X.; and Zhu, E. 2023b. CONVERT: Contrastive Graph Clustering with Reliable Augmentation. In ACM MM.

[54]

Yang, Z.; Cohen, W.; and Salakhudinov, R. 2016. Revisiting semi-supervised learning with graph embeddings. In ICLR, 40-48. New York, USA: PMLR.

[55]

Yu, S.; Liu, S.; Wang, S.; Tang, C.; Luo, Z.; Liu, X.; and Zhu, E. 2023a. Sparse Low-Rank Multi-View Subspace Clustering With Consensus Anchors and Unified Bipartite Graph. T-NNLS.

[56]

Yu, S.; Wang, S.; Wen, Y.; Wang, Z.; Luo, Z.; Zhu, E.; and Liu, X. 2023b. How to Construct Corresponding Anchors for Incomplete Multiview Clustering. T-CSVT.

[57]

Zhang, M.; Wu, S.; Yu, X.; Liu, Q.; and Wang, L. 2022. Dynamic graph neural networks for sequential recommendation. IEEE T-KDE, 35(5): 4741-4753.

[58]

Zhang, M.; Xia, Y.; Liu, Q.; Wu, S.; and Wang, L. 2023a. Learning Latent Relations for Temporal Knowledge Graph Reasoning. In ACL, 12617-12631.

[59]

Zhang, M.; Xia, Y.; Liu, Q.; Wu, S.; and Wang, L. 2023b. Learning Long-and Short-term Representations for Temporal Knowledge Graph Reasoning. In Proceedings of the ACM Web Conference 2023, 2412-2422.

[60]

Zhao, Y.; Cai, X.; Wu, Y.; Zhang, H.; Zhang, Y.; Zhao, G.; and Jiang, N. 2022. MoSE: Modality Split and Ensemble for Multimodal Knowledge Graph Completion. In EMNLP, 10527-10536.

[61]

Zheng, S.; Mai, S.; Sun, Y.; Hu, H.; and Yang, Y. 2022. Subgraph-aware Few-Shot Inductive Link Prediction via Meta-Learning. T-KDE.

Cited By

Zhang XDang JWang YLi S(2025)Feature enhancement based on hierarchical reconstruction framework for inductive prediction on sparse graphsInformation Processing and Management: an International Journal10.1016/j.ipm.2024.10389462:1Online publication date: 1-Jan-2025
https://dl.acm.org/doi/10.1016/j.ipm.2024.103894
Liang XSi GLi JTian PAn ZZhou F(2025)Relational message passing with mutual information maximization for inductive link predictionThe Journal of Supercomputing10.1007/s11227-024-06749-881:1Online publication date: 1-Jan-2025
https://dl.acm.org/doi/10.1007/s11227-024-06749-8

Index Terms

MINES: message intercommunication for inductive relation reasoning over neighbor-enhanced subgraphs

Index terms have been assigned to the content through auto-classification.

Recommendations

On the Multichromatic Number of s-Stable Kneser Graphs

For positive integers n and s, a subset Sï [n] is s-stable if sï |i-j|ï n-s for distinct i,j∈S . The s-stable r-uniform Kneser hypergraph KGrn,ks-stable is the r-uniform hypergraph that has the collection of all s-stable k-element subsets of [n] as ...
Adjacent vertex-distinguishing edge and total chromatic numbers of hypercubes

An adjacent vertex-distinguishing edge coloring of a simple graph G is a proper edge coloring of G such that incident edge sets of any two adjacent vertices are assigned different sets of colors. A total coloring of a graph G is a coloring of both the ...
Removable edges in a 5-connected graph and a construction method of 5-connected graphs

An edge e of a k-connected graph G is said to be a removable edge if G@?e is still k-connected. A k-connected graph G is said to be a quasi (k+1)-connected if G has no nontrivial k-separator. The existence of removable edges of 3-connected and 4-...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Guide Proceedings

AAAI'24/IAAI'24/EAAI'24: Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symposium on Educational Advances in Artificial Intelligence

February 2024

23861 pages

ISBN:978-1-57735-887-9

Copyright © 2024 Association for the Advancement of Artificial Intelligence.

Sponsors

Association for the Advancement of Artificial Intelligence

Publisher

AAAI Press

Publication History

Published: 20 February 2024

Qualifiers

Research-article
Research
Refereed limited

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 19 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Zhang XDang JWang YLi S(2025)Feature enhancement based on hierarchical reconstruction framework for inductive prediction on sparse graphsInformation Processing and Management: an International Journal10.1016/j.ipm.2024.10389462:1Online publication date: 1-Jan-2025
https://dl.acm.org/doi/10.1016/j.ipm.2024.103894
Liang XSi GLi JTian PAn ZZhou F(2025)Relational message passing with mutual information maximization for inductive link predictionThe Journal of Supercomputing10.1007/s11227-024-06749-881:1Online publication date: 1-Jan-2025
https://dl.acm.org/doi/10.1007/s11227-024-06749-8

View Options

View options

Figures

Tables

Media

View Table of Conten