Graph Size-imbalanced Learning with Energy-guided Structural Smoothing

TL;DR

This paper introduces SIMBA, a novel energy-guided framework that addresses size-imbalance in graph classification by smoothing structural features and re-weighting graphs based on energy propagation, improving performance on imbalanced datasets.

Contribution

The paper proposes a new energy-based learning framework, SIMBA, that effectively mitigates size-imbalance issues in graph classification through structural smoothing and energy-guided re-weighting.

Findings

Outperforms existing methods on five public size-imbalanced datasets.

Effectively reduces structural feature discrepancies between head and tail graphs.

Demonstrates significant improvements in size-imbalanced graph classification tasks.

Abstract

Graph is a prevalent data structure employed to represent the relationships between entities, frequently serving as a tool to depict and simulate numerous systems, such as molecules and social networks. However, real-world graphs usually suffer from the size-imbalanced problem in the multi-graph classification, i.e., a long-tailed distribution with respect to the number of nodes. Recent studies find that off-the-shelf Graph Neural Networks (GNNs) would compromise model performance under the long-tailed settings. We investigate this phenomenon and discover that the long-tailed graph distribution greatly exacerbates the discrepancies in structural features. To alleviate this problem, we propose a novel energy-based size-imbalanced learning framework named \textbf{SIMBA}, which smooths the features between head and tail graphs and re-weights them based on the energy propagation. Specifically, we construct a higher-level graph abstraction named \textit{Graphs-to-Graph} according to the correlations between graphs to link independent graphs and smooths the structural discrepancies. We further devise an energy-based message-passing belief propagation method for re-weighting lower compatible graphs in the training process and further smooth local feature discrepancies. Extensive experimental results over five public size-imbalanced datasets demonstrate the superior effectiveness of the model for size-imbalanced graph classification tasks.