Graph Information Bottleneck for Subgraph Recognition
arXiv:2010.05563
Abstract
Given the input graph and its label/property, several key problems of graph learning, such as finding interpretable subgraphs, graph denoising and graph compression, can be attributed to the fundamental problem of recognizing a subgraph of the original one. This subgraph shall be as informative as possible, yet contains less redundant and noisy structure. This problem setting is closely related to the well-known information bottleneck (IB) principle, which, however, has less been studied for the irregular graph data and graph neural networks (GNNs). In this paper, we propose a framework of Graph Information Bottleneck (GIB) for the subgraph recognition problem in deep graph learning. Under this framework, one can recognize the maximally informative yet compressive subgraph, named IB-subgraph. However, the GIB objective is notoriously hard to optimize, mostly due to the intractability of the mutual information of irregular graph data and the unstable optimization process. In order to tackle these challenges, we propose: i) a GIB objective based-on a mutual information estimator for the irregular graph data; ii) a bi-level optimization scheme to maximize the GIB objective; iii) a connectivity loss to stabilize the optimization process. We evaluate the properties of the IB-subgraph in three application scenarios: improvement of graph classification, graph interpretation and graph denoising. Extensive experiments demonstrate that the information-theoretic IB-subgraph enjoys superior graph properties.
References in corpus (9)
- Inductive Representation Learning on Large Graphs
- Neural Message Passing for Quantum Chemistry
- Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
- The information bottleneck method
- Learning Discrete Structures for Graph Neural Networks
- Multi-Objective Molecule Generation using Interpretable Substructures
- Edge Contraction Pooling for Graph Neural Networks
- Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck
- Unsupervised Speech Decomposition via Triple Information Bottleneck