Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Deep Neural Sheaf Diffusion

About

Deep Graph Neural Networks (GNNs) are essential for capturing complex dependencies in graph-structured data. However, scaling GNNs to depth remains challenging, as stacking layers leads to representation collapse and diminishing sensitivity due to repeated aggregation. While Neural Sheaf Diffusion (NSD) provides strong theoretical guarantees against such collapse, these guarantees do not translate to practice: as depth increases, the disagreement signal of the sheaf Laplacian vanishes, limiting the contribution of deeper layers. We identify mechanisms that hinder NSD effectiveness at depth and propose \emph{Deep Neural Sheaf Diffusion} (DNSD), which replaces the sheaf Laplacian with a sheaf adjacency operator to maintain informative signals across layers. This is complemented by normalization, odd nonlinearities, and gating. To provide a principled explanation of the expected performance improvement, we contrast sheaf diffusion to graph attention mechanisms, highlighting that DNSD replaces scalar attention scores with matrix-valued edge functions and normalizes node representations rather than attention scores. We demonstrate empirically that DNSD effectively utilizes deep aggregation in graph tasks, outperforming GNN and NSD baselines with up to 30pp accuracy on synthetic long-range datasets, and consistently outperforming them on real-world benchmarks. These results position sheaf-based architectures as a promising building block for graph foundation models by supporting effective deep architectures.

R\'emi Bourgerie, \v{S}ar\=unas Girdzijauskas, Viktoria Fodor• 2026

Related benchmarks

TaskDatasetResultRank
Node ClassificationRoman-Empire
Accuracy83.4
327
Node Classificationamazon-ratings
Accuracy49.1
309
Node ClassificationActor (test)
Mean Accuracy0.364
286
Node ClassificationAmazon-Ratings (test)
Accuracy49.1
155
Node ClassificationMinesweeper (test)--
134
Node ClassificationMinesweeper
Accuracy89.4
113
Node ClassificationPenn94
Accuracy80
79
Node ClassificationRoman-empire (test)
Accuracy83.4
66
Node Classificationquestions
Accuracy97.2
64
Node Classificationpenn94 (test)
Accuracy80
48
Showing 10 of 12 rows

Other info

Follow for update