[2603.27723] TMTE: Effective Multimodal Graph Learning with Task-aware Modality and Topology Co-evolution

Computer Science > Machine Learning arXiv:2603.27723 (cs) [Submitted on 29 Mar 2026] Title:TMTE: Effective Multimodal Graph Learning with Task-aware Modality and Topology Co-evolution Authors:Yinlin Zhu, Xunkai Li, Di Wu, Wang Luo, Miao Hu, Di Wu View a PDF of the paper titled TMTE: Effective Multimodal Graph Learning with Task-aware Modality and Topology Co-evolution, by Yinlin Zhu and 5 other authors View PDF HTML (experimental) Abstract:Multimodal-attributed graphs (MAGs) are a fundamental data structure for multimodal graph learning (MGL), enabling both graph-centric and modality-centric tasks. However, our empirical analysis reveals inherent topology quality limitations in real-world MAGs, including noisy interactions, missing connections, and task-agnostic relational structures. A single graph derived from generic relationships is therefore unlikely to be universally optimal for diverse downstream tasks. To address this challenge, we propose Task-aware Modality and Topology co-Evolution (TMTE), a novel MGL framework that jointly and iteratively optimizes graph topology and multimodal representations toward the target task. TMTE is motivated by the bidirectional coupling between modality and topology: multimodal attributes induce relational structures, while graph topology shapes modality representations. Concretely, TMTE casts topology evolution as multi-perspective metric learning over modality embeddings with an anchor-based approximation, and formulates modality e...