MLGIB: Multi-Label Graph Information Bottleneck for Expressive and Robust Message Passing

ArXi:2605.13126v1 Announce Type: cross Graph Neural Networks (GNNs) suffer from over-squashing in deep message passing, where information from exponentially growing neighborhoods is compressed into fixed-dimensional representations. We show that this issue becomes a distinct failure mode in multi-label graphs: neighboring nodes often share only limited labels while differing across many irrelevant ones, causing predictive signals to be diluted by noisy label information.