DeepAI AI Chat
Log In Sign Up

TopoImb: Toward Topology-level Imbalance in Learning from Graphs

by   Tianxiang Zhao, et al.
Penn State University
Florida International University

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 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. 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 are provided theoretically, and we empirically verify its effectiveness with both node-level and graph-level classification as the target tasks.


page 2

page 8


Topology-Imbalance Learning for Semi-Supervised Node Classification

The class imbalance problem, as an important issue in learning node repr...

Position-aware Structure Learning for Graph Topology-imbalance by Relieving Under-reaching and Over-squashing

Topology-imbalance is a graph-specific imbalance problem caused by the u...

Characterizing the Effect of Class Imbalance on the Learning Dynamics

Data imbalance is a common problem in the machine learning literature th...

Diving into Unified Data-Model Sparsity for Class-Imbalanced Graph Representation Learning

Even pruned by the state-of-the-art network compression methods, Graph N...

ReGrAt: Regularization in Graphs using Attention to handle class imbalance

Node classification is an important task to solve in graph-based learnin...

TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classification

Learning unbiased node representations under class-imbalanced graph data...