TopoImb: Toward Topology-level Imbalance in Learning from GraphsDownload PDF

Published: 24 Nov 2022, Last Modified: 05 May 2023LoG 2022 PosterReaders: Everyone
Keywords: Graph, Imbalance, Graph neural network
TL;DR: Focusing on influence of graph imbalance to trained GNNs in sub-class (topology) level, and propose an effective method based on explicit topology modeling and training modulation.
Abstract: Graph serves as a powerful tool for modeling data that has an underlying structure in non-Euclidean space, by encoding relations as edges and entities as nodes. Despite developments in learning from graph-structured data over the years, one obstacle persists: graph imbalance. Although several attempts have been made to target this problem, they are limited to considering only class-level imbalance. In this work, we argue that for graphs, the imbalance is likely to exist at the sub-class topology group level. Due to the flexibility of topology structures, graphs could be highly diverse, and learning a generalizable classification boundary would be difficult. Therefore, several majority topology groups may dominate the learning process, rendering others under-represented. To address this problem, we propose a new framework {\method} and design (1 a topology extractor, which automatically identifies the topology group for each instance with explicit memory cells, (2 a training modulator, which modulates the learning process of the target GNN model to prevent the case of topology-group-wise under-representation. {\method} can be used as a key component in GNN models to improve their performances under the data imbalance setting. Analyses on both topology-level imbalance and the proposed {\method} are provided theoretically, and we empirically verify its effectiveness with both node-level and graph-level classification as the target tasks.
Type Of Submission: Full paper proceedings track submission (max 9 main pages).
Agreement: Check this if you are okay with being contacted to participate in an anonymous survey.
PDF File: pdf
Type Of Submission: Full paper proceedings track submission.
Poster: jpg
Poster Preview: jpg
6 Replies

Loading