RoleMAG: Learning Neighbor Roles in Multimodal Graphs
Multimodal attributed graphs (MAGs) combine multimodal node attributes with structured relations. However, existing methods usually perform shared message passing on a single graph and implicitly assume that the same neighbors are equally useful for all modalities. In practice, neighbors that benefit one modality may interfere with another, blurring modality-specific signals under shared propagation. To address this issue, we propose RoleMAG, a multimodal graph framework that learns how different neighbors should participate in propagation. Concretely, RoleMAG distinguishes whether a neighbor should provide shared, complementary, or heterophilous signals, and routes them through separate ...
| Authors | Yilong Zuo, Xunkai Li, Zhihan Zhang et al. |
|---|---|
| Primary category | cs.LG |
| Published | 14 April 2026 |
| Last updated at source | 14 April 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.