Structural Landmarking and Interaction Modelling: on Resolution Dilemmas in Graph Classification
Lists
Only you see this
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.
BibTeX
@misc{zhang2020structural,
author = {Kai Zhang and Yaokang Zhu and Jun Wang and Haibin Ling and Jie Zhang and Hongyuan Zha},
title = {{Structural Landmarking and Interaction Modelling: on Resolution Dilemmas in Graph Classification}},
year = {2020},
eprint = {2006.15763},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2006.15763},
}