Region and relations based multi attention network for graph classification

Aggarwal, M and Murty, MN (2020) Region and relations based multi attention network for graph classification. In: 25th International Conference on Pattern Recognition, 10-15 jan 2021, Virtual, pp. 8101-8108.

PDF ICPR_2020.pdf - Published Version Restricted to Registered users only Download (520kB) | Request a copy

Abstract

Graphs are non-euclidean structures that can represent many relational data efficiently. Many studies have proposed the convolution and the pooling operators on the non-euclidean domain. The graph convolution operators have shown astounding performance on various tasks such as node representation and classification. For graph classification, different pooling techniques are introduced, but none of them has considered both neighborhood of the node and the long-range dependencies of the node. In this paper, we propose a novel graph pooling layer R2POOL, which balances the structure information around the node as well as the dependencies with far away nodes. Further, we propose a new training strategy to learn coarse to fine representations. We add supervision at only intermediate levels to generate predictions using only intermediate-level features. For this, we propose the concept of an alignment score. Moreover, each layer's prediction is controlled by our proposed branch training strategy. This complete training helps in learning dominant class features at each layer for representing graphs. We call the combined model by R2MAN. Experiments show that R2MAN has the potential to improve the performance of graph classification on various datasets. © 2020 IEEE

Item Type:	Conference Paper
Publication:	Proceedings - International Conference on Pattern Recognition
Publisher:	Institute of Electrical and Electronics Engineers Inc.
Additional Information:	The copyright for this article belongs to Institute of Electrical and Electronics Engineers Inc.
Keywords:	Classification (of information); Convolution; Pattern recognition, Combined model; Convolution operators; Graph classification; Intermediate level; Long-range dependencies; Relational data; Structure information; Training strategy, Graph theory
Department/Centre:	Division of Electrical Sciences > Computer Science & Automation
Date Deposited:	16 Nov 2021 11:00
Last Modified:	16 Nov 2021 11:00
URI:	http://eprints.iisc.ac.in/id/eprint/69709

Actions (login required)

View Item