Decoupling and Damping: Structurally-Regularized Gradient Matching for Multimodal Graph Condensation

TL;DR

This paper introduces SR-GM, a novel graph condensation method that decouples gradients and applies structural damping to improve multimodal graph learning efficiency and performance.

Contribution

It proposes a new framework that addresses gradient conflicts and noise amplification in multimodal graph condensation, enhancing stability and effectiveness.

Findings

Achieves state-of-the-art results on four multimodal graph datasets.

Demonstrates improved stability and generalization across different architectures.

Effectively reduces gradient conflicts and noise in graph structure learning.

Abstract

In multimodal graph learning, graph structures that integrate information from multiple sources, such as vision and text, can more comprehensively model complex entity relationships. However, the continuous growth of their data scale poses a significant computational bottleneck for training. Graph condensation methods provide a feasible path forward by synthesizing compact and representative datasets. Nevertheless, existing condensation approaches generally suffer from performance limitations in multimodal scenarios, mainly due to two reasons: (1) semantic misalignment between different modalities leads to gradient conflicts; (2) the message-passing mechanism of graph neural networks further structurally amplifies such gradient noise. Based on this, we propose Structural Regularized Gradient Matching (SR-GM), a condensation framework for multimodal graphs. This method alleviates gradient conflicts between modalities through a gradient decoupling mechanism and introduces a structural damping regularizer to suppress the propagation of gradient noise in the topology, thereby transforming the graph structure from a noise amplifier into a training stabilizer. Extensive experiments on four multimodal graph datasets demonstrate the effectiveness of SR-GM, highlighting its state-of-the-art performance and cross-architecture generalization capabilities in multimodal graph dataset condensation.