Haar Graph Pooling

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review

4 Scopus Citations
View graph of relations

Author(s)

  • Yu Guang Wang
  • Ming Li
  • Zheng Ma
  • Guido Montufar
  • Yanan Fan

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationProceedings of the 37th International Conference on Machine Learning
EditorsHal Daumé III, Aarti Singh
PublisherML Research Press
Pages9952-9962
ISBN (Print)9781713821120
Publication statusPublished - Jul 2020

Publication series

NameProceedings of the International Conference on Machine Learning
Volume119
ISSN (Print)2640-3498

Conference

Title37th International Conference on Machine Learning (ICML 2020)
LocationVirtual
Period12 - 18 July 2020

Abstract

Deep Graph Neural Networks (GNNs) are useful models for graph classification and graph-based regression tasks. In these tasks, graph pooling is acritical ingredient by which GNNs adapt to input graphs of varying size and structure. We propose a new graph pooling operation based on compressive Haar transforms — HaarPooling. HaarPooling implements a cascade of pooling operations; it is computed by following a sequence of clusterings of the input graph. A HaarPooling layer transforms a given input graph to an output graph with a smaller node number and the same feature dimension; the compressive Haar transform filters out fine detail information in the Haar wavelet domain. In this way, all the HaarPooling layers together synthesize the features of any given input graph into a feature vector of uniform size. Such transforms provide a sparse characterization of the data and preserve the structure information of the input graph. GNNs implemented with standard graph convolution layers and HaarPooling layers achieve state of the art performance on diverse graph classification and regression problems.

Citation Format(s)

Haar Graph Pooling. / Wang, Yu Guang; Li, Ming; Ma, Zheng; Montufar, Guido; Zhuang, Xiaosheng; Fan, Yanan.

Proceedings of the 37th International Conference on Machine Learning. ed. / Hal Daumé III; Aarti Singh. ML Research Press, 2020. p. 9952-9962 (Proceedings of the International Conference on Machine Learning; Vol. 119).

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review