AI RESEARCH

Scalable Message Passing Neural Networks: No Need for Attention in Large Graph Representation Learning

arXiv CS.LG

ArXi:2411.00835v2 Announce Type: replace We propose Scalable Message Passing Neural Networks (SMPNNs) and nstrate that, by integrating standard convolutional message passing into a Pre-Layer Normalization Transformer-style block instead of attention, we can produce high-performing deep message-passing-based Graph Neural Networks (GNNs