Beyond the Aggregation Dilemma: Prior-Retaining Decoupled Learning for Multimodal Graphs 事件

Beyond the Aggregation Dilemma: Prior-Retaining Decoupled Learning for Multimodal Graphs arXiv:2605.24684v1 Announce Type: cross Abstract: Multimodal Attributed Graph Learning (MAGL) integrates intrinsic node attributes with structural topology via graph aggregation. However, as pretrained encoders evolve into Large Foundation Models (LFMs), the landscape of MAGL fundamentally shifts: under high-confidence LFM priors, mandatory aggregation introduces topological noise that overwhelms discrimina