SE-GSL: A General and Effective Graph Structure Learning Framework through Structural Entropy Optimization
arXiv:2303.09778 · doi:10.1145/3543507.3583453
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 are fused to enhance the original graph. A new scheme of constructing optimal encoding trees is 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.
arXiv comment12 pages,5 figures, accepted by WWW2023
References in corpus (25)
- A Comprehensive Survey on Graph Neural Networks
- Neural Message Passing for Quantum Chemistry
- Graph Contrastive Learning with Adaptive Augmentation
- Hierarchical Graph Representation Learning with Differentiable Pooling
- Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
- GNNExplainer: Generating Explanations for Graph Neural Networks
- DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
- AM-GCN: Adaptive Multi-channel Graph Convolutional Networks
- GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
- Predict then Propagate: Graph Neural Networks meet Personalized PageRank
- Simple and Deep Graph Convolutional Networks
- Adversarial Attack and Defense on Graph Data: A Survey
- Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings
- Learning Discrete Structures for Graph Neural Networks
- Diffusion Improves Graph Learning
- Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
- GNNGuard: Defending Graph Neural Networks against Adversarial Attacks
- Graph Information Bottleneck
- Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNN
- GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks
- Position-aware Structure Learning for Graph Topology-imbalance by Relieving Under-reaching and Over-squashing
- CAGNN: Cluster-Aware Graph Neural Networks for Unsupervised Graph Representation Learning
- Structural Entropy Guided Graph Hierarchical Pooling
- NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphs
- An Information-theoretic Perspective of Hierarchical Clustering