GOKU improves GNN accuracy by reconstructing a denser latent graph and then spectrally sparsifying it, preserving the original spectrum and edge count while improving connectivity.
Leave Graphs Alone: Addressing Over-Squashing without Rewiring
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Recent works have investigated the role of graph bottlenecks in preventing long-range information propagation in message-passing graph neural networks, causing the so-called `over-squashing' phenomenon. As a remedy, graph rewiring mechanisms have been proposed as preprocessing steps. Graph Echo State Networks (GESNs) are a reservoir computing model for graphs, where node embeddings are recursively computed by an untrained message-passing function. In this paper, we show that GESNs can achieve a significantly better accuracy on six heterophilic node classification tasks without altering the graph connectivity, thus suggesting a different route for addressing the over-squashing problem.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification
GOKU improves GNN accuracy by reconstructing a denser latent graph and then spectrally sparsifying it, preserving the original spectrum and edge count while improving connectivity.