Yuheng Xiong

Multi-Track Message Passing: Tackling Oversmoothing and Oversquashing in Graph Learning via Preventing Heterophily Mixing

The advancement toward deeper graph neural networks is currently obscured by two inherent issues in message passing, *oversmoothing* and *oversquashing*. We identify the root cause of these issues as information loss due to *heterophily mixing* in aggregation, where messages of diverse category sema…