AI RESEARCH

Multimodal Structure Learning: Disentangling Shared and Specific Topology via Cross-Modal Graphical Lasso

arXiv CS.LG

ArXi:2604.03953v1 Announce Type: cross Learning interpretable multimodal representations inherently relies on uncovering the conditional dependencies between heterogeneous features. However, sparse graph estimation techniques, such as Graphical Lasso (GLasso), to visual-linguistic domains is severely bottlenecked by high-dimensional noise, modality misalignment, and the confounding of shared versus category-specific topologies. In this paper, we propose Cross-Modal Graphical Lasso (CM-GLasso) that overcomes these fundamental limitations.