Conference proceeding
Implicit Subgraph Neural Network
Proceedings of Machine Learning Research - International Conference on Machine Learning, ICML 2025, Vol.267, pp.78602-78615
2025
Abstract
Subgraph neural networks have recently gained prominence for various subgraph-level predictive tasks. However, existing methods either 1) apply simple standard pooling over graph convolutional networks, failing to capture essential subgraph properties, or 2) rely on rigid subgraph definitions, leading to suboptimal performance. Moreover, these approaches fail to model long-range dependencies both between and within subgraphs—a critical limitation, as many real-world networks contain subgraphs of varying sizes and connectivity patterns. In this paper, we propose a novel implicit subgraph neural network, the first of its kind, designed to capture dependencies across subgraphs. Our approach also integrates label-aware subgraph-level information. We formulate implicit subgraph learning as a bilevel optimization problem and develop a provably convergent algorithm that requires fewer gradient estimations than standard bilevel optimization methods. We evaluate our approach on real-world networks against state-of-the-art baselines, demonstrating its effectiveness and superiority.
Details
- Title: Subtitle
- Implicit Subgraph Neural Network
- Creators
- Yongjian Zhong - Department of Computer Science, University of Iowa, Iowa City, United StatesLiao Zhu - Department of Computer Science, University of Iowa, Iowa City, United StatesHieu Vu - University of IowaBijaya Adhikari - Department of Computer Science, University of Iowa, Iowa City, United States
- Resource Type
- Conference proceeding
- Publication Details
- Proceedings of Machine Learning Research - International Conference on Machine Learning, ICML 2025, Vol.267, pp.78602-78615
- ISSN
- 2640-3498
- eISSN
- 2640-3498
- Grant note
- Centers for Disease Control and Prevention (http://data.elsevier.com/vocabulary/SciValFunders/100000030) National Science Foundation (http://data.elsevier.com/vocabulary/SciValFunders/100000001) U01-CK000594 / Centers for Disease Control and Prevention (http://data.elsevier.com/vocabulary/SciValFunders/100000030) University of Iowa (http://data.elsevier.com/vocabulary/SciValFunders/100008893) 2320980; 2306331 / National Science Foundation (http://data.elsevier.com/vocabulary/SciValFunders/100000001)
- Language
- English
- Date published
- 2025
- Academic Unit
- Computer Science
- Record Identifier
- 9985091808902771
Metrics
1 Record Views