PANDA: Expanded Width-Aware Message Passing Beyond Rewiring
This addresses a critical bottleneck in GNNs for researchers and practitioners, offering a novel alternative to graph rewiring.
The paper tackles the over-squashing problem in graph neural networks by introducing PANDA, a message passing paradigm that selectively expands node width instead of rewiring graphs, outperforming existing rewiring methods.
Recent research in the field of graph neural network (GNN) has identified a critical issue known as "over-squashing," resulting from the bottleneck phenomenon in graph structures, which impedes the propagation of long-range information. Prior works have proposed a variety of graph rewiring concepts that aim at optimizing the spatial or spectral properties of graphs to promote the signal propagation. However, such approaches inevitably deteriorate the original graph topology, which may lead to a distortion of information flow. To address this, we introduce an expanded width-aware (PANDA) message passing, a new message passing paradigm where nodes with high centrality, a potential source of over-squashing, are selectively expanded in width to encapsulate the growing influx of signals from distant nodes. Experimental results show that our method outperforms existing rewiring methods, suggesting that selectively expanding the hidden state of nodes can be a compelling alternative to graph rewiring for addressing the over-squashing.