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

arXiv: https://arxiv.org/abs/2511.20222 · HTML: https://mlsanity.com/paper/2511.20222/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 52 references that are in the map.
- First posted on arXiv 25 Nov 2025.

## Builds on (most cited first, 26 of 26)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [Link Prediction Based on Graph Neural Networks](https://mlsanity.com/paper/1802.09691/) (2018)
- [Dataset Condensation with Gradient Matching](https://mlsanity.com/paper/2006.05929/) (2020)
- [Conflict-Averse Gradient Descent for Multi-task Learning](https://mlsanity.com/paper/2110.14048/) (2021)
- [Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models](https://mlsanity.com/paper/2010.05874/) (2020)
- [Graph Condensation for Graph Neural Networks](https://mlsanity.com/paper/2110.07580/) (2021)
- [CoDEx: A Comprehensive Knowledge Graph Completion Benchmark](https://mlsanity.com/paper/2009.07810/) (2020)
- [Condensing Graphs via One-Step Gradient Matching](https://mlsanity.com/paper/2206.07746/) (2022)
- [Dirichlet Energy Constrained Learning for Deep Graph Neural Networks](https://mlsanity.com/paper/2107.02392/) (2021)
- [Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Data](https://mlsanity.com/paper/2306.02664/) (2023)
- [Graph Condensation via Receptive Field Distribution Matching](https://mlsanity.com/paper/2206.13697/) (2022)
- [Efficient Continuous Pareto Exploration in Multi-Task Learning](https://mlsanity.com/paper/2006.16434/) (2020)
- [Does Graph Distillation See Like Vision Dataset Counterpart?](https://mlsanity.com/paper/2310.09192/) (2023)
- [Product Knowledge Graph Embedding for E-commerce](https://mlsanity.com/paper/1911.12481/) (2019)
- [Rethinking Graph Regularization for Graph Neural Networks](https://mlsanity.com/paper/2009.02027/) (2020)
- [Fast Graph Condensation with Structure-based Neural Tangent Kernel](https://mlsanity.com/paper/2310.11046/) (2023)
- [Mosaic of Modalities: A Comprehensive Benchmark for Multimodal Graph Learning](https://mlsanity.com/paper/2406.16321/) (2024)
- [Detecting Beneficial Feature Interactions for Recommender Systems](https://mlsanity.com/paper/2008.00404/) (2020)
- [EXGC: Bridging Efficiency and Explainability in Graph Condensation](https://mlsanity.com/paper/2402.05962/) (2024)
- [Construction and Applications of Billion-Scale Pre-Trained Multimodal Business Knowledge Graph](https://mlsanity.com/paper/2209.15214/) (2022)
- [Beyond Modality Collapse: Representations Blending for Multimodal Dataset Distillation](https://mlsanity.com/paper/2505.14705/) (2025)

## Built on by (most cited first, 2 of 2)

- [LION: A Clifford Neural Paradigm for Multimodal-Attributed Graph Learning](https://mlsanity.com/paper/2608.24795/) (2026)
- [LION: A Clifford Neural Paradigm for Multimodal-Attributed Graph Learning](https://mlsanity.com/paper/2601.21453/) (2026)

## Abstract (arXiv)

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.