Structural Landmarking and Interaction Modelling: on Resolution Dilemmas in Graph Classification

Kai Zhang, Yaokang Zhu, Jun Wang, Haibin Ling, Jie Zhang, Hongyuan Zha

Keywords: Graph Pooling, Graph Classiciation, Interaction Preserving Graph Pooling, Structure Landmarking

Abstract: Graph neural networks are promising architecture for learning and inference with graph-structured data. However, generating informative graph level features has long been a challenge. Current practice of graph-pooling typically summarizes a graph by squeezing it into a single vector. This may lead to significant loss of predictive, iterpretable structural information, because properties of a complex system are believed to arise largely from the interaction among its components. In this paper, we analyze the intrinsic difficulty in graph classification under the unified concept of ``"resolution dilemmas" and propose `SLIM, an inductive neural network model for Structural Landmarking and Interaction Modelling, to remedy the information loss in graph pooling. We show that, by projecting graphs onto end-to-end optimizable, and well-aligned substructure landmarks (representatives), the resolution dilemmas can be resolved effectively, so that explicit interacting relation between component parts of a graph can be leveraged directly in explaining its complexity and predicting its property. Empirical evaluations, in comparison with state-of-the-art, demonstrate promising results of our approach on a number of benchmark datasets for graph classification.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: A new framework for graph pooling that allows explicit modelling of graph substructures and their interacting relations.

Reviewed Version (pdf): https://openreview.net/references/pdf?id=ijo7HfbaRn