SE-GSL: A General and Effective Graph Structure Learning Framework through Structural Entropy Optimization
Top Cited Papers
Open Access
- 30 April 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 499-510
Abstract
Graph Neural Networks (GNNs) are de facto solutions to structural data learning. However, it is susceptible to low-quality and unreliable structure, which has been a norm rather than an exception in real-world graphs. Existing graph structure learning (GSL) frameworks still lack robustness and interpretability. This paper proposes a general GSL framework, SE-GSL, through structural entropy and the graph hierarchy abstracted in the encoding tree. Particularly, we exploit the one-dimensional structural entropy to maximize embedded information content when auxiliary neighbourhood attributes is fused to enhance the original graph. A new scheme of constructing optimal encoding trees are proposed to minimize the uncertainty and noises in the graph whilst assuring proper community partition in hierarchical abstraction. We present a novel sample-based mechanism for restoring the graph structure via node structural entropy distribution. It increases the connectivity among nodes with larger uncertainty in lower-level communities. SE-GSL is compatible with various GNN models and enhances the robustness towards noisy and heterophily structures. Extensive experiments show significant improvements in the effectiveness and robustness of structure learning and node representation learning.Keywords
All Related Versions
Funding Information
- National Key R&D Program of China (2021YFB1714800)
- Natural Science Foundation of Beijing Municipality (4222030)
- National Science Foundation of China (62002007)
- National Science Foundation (III-1763325, III-1909323, III-2106758, and SaTC-1930941)
- S&T Program of Hebei (20310101D)
This publication has 24 references indexed in Scilit:
- Learning to Drop: Robust Graph Neural Network via Topological Denoising2021
- Graph Structure Learning for Robust Graph Neural Networks2020
- AM-GCN: Adaptive Multi-channel Graph Convolutional Networks2020
- Motif-Matching Based Subgraph-Level Attentional Convolutional Network for Graph ClassificationProceedings of the AAAI Conference on Artificial Intelligence, 2020
- A Comprehensive Survey on Graph Neural NetworksIEEE Transactions on Neural Networks and Learning Systems, 2020
- Fine-grained Event Categorization with Heterogeneous Graph Convolutional Networks2019
- Adversarial Examples for Graph Data: Deep Insights into Attack and Defense2019
- Explaining Explanations: An Overview of Interpretability of Machine Learning2018
- Structural Information and Dynamical Complexity of NetworksIEEE Transactions on Information Theory, 2016
- Social influence analysis in large-scale networks2009