Unsupervised Learning of Graph Hierarchical Abstractions with Differentiable Coarsening and Optimal Transport

Authors

  • Tengfei Ma IBM Research
  • Jie Chen MIT-IBM Watson AI Lab

Keywords:

Graph-based Machine Learning

Abstract

Hierarchical abstractions are a methodology for solving large-scale graph problems in various disciplines. Coarsening is one such approach: it generates a pyramid of graphs whereby the one in the next level is a structural summary of the prior one. With a long history in scientific computing, many coarsening strategies were developed based on mathematically driven heuristics. Recently, resurgent interests exist in deep learning to design hierarchical methods learnable through differentiable parameterization. These approaches are paired with downstream tasks for supervised learning. In practice, however, supervised signals (e.g., labels) are scarce and are often laborious to obtain. In this work, we propose an unsupervised approach, coined OTCoarsening, with the use of optimal transport. Both the coarsening matrix and the transport cost matrix are parameterized, so that an optimal coarsening strategy can be learned and tailored for a given set of graphs. We demonstrate that the proposed approach produces meaningful coarse graphs and yields competitive performance compared with supervised methods for graph classification and regression.

Downloads

Published

2021-05-18

How to Cite

Ma, T., & Chen, J. (2021). Unsupervised Learning of Graph Hierarchical Abstractions with Differentiable Coarsening and Optimal Transport. Proceedings of the AAAI Conference on Artificial Intelligence, 35(10), 8856-8864. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17072

Issue

Section

AAAI Technical Track on Machine Learning III