Papers › Diffusing Graph Attention

Diffusing Graph Attention

1 Mar 2023arXiv:2303.00613archive 2025-07-28

Daniel Glickman, Eran Yahav

The dominant paradigm for machine learning on graphs uses Message Passing Graph Neural Networks (MP-GNNs), in which node representations are updated by aggregating information in their local neighborhood. Recently, there have been increasingly more attempts to adapt the Transformer architecture to graphs in an effort to solve some known limitations of MP-GNN. A challenging aspect of designing Graph Transformers is integrating the arbitrary graph structure into the architecture. We propose Graph Diffuser (GD) to address this challenge. GD learns to extract structural and positional relationships between distant nodes in the graph, which it then uses to direct the Transformer's attention and node representation. We demonstrate that existing GNNs and Graph Transformers struggle to capture long-range interactions and how Graph Diffuser does so while admitting intuitive visualizations. Experiments on eight benchmarks show Graph Diffuser to be a highly competitive model, outperforming the state-of-the-art in a diverse set of domains.

Paper PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Graph Attention Graph Classification Graph Regression Link Prediction

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Graph Classification	Peptides-func	Graph Diffuser	AP	0.6651±0.0010	#26 of 44	Archive leaderboard	report
Graph Regression	Peptides-struct	Graph Diffuser	MAE	0.2461±0.0010	#12 of 39	Archive leaderboard	report
Link Prediction	PCQM-Contact	Graph Diffuser	Hits@1	0.1369±0.0012	#2 of 18	Archive leaderboard	report
Link Prediction	PCQM-Contact	Graph Diffuser	Hits@10	0.8592±0.0007	#2 of 18	Archive leaderboard	report
Link Prediction	PCQM-Contact	Graph Diffuser	Hits@3	0.4053±0.0011	#2 of 18	Archive leaderboard	report
Link Prediction	PCQM-Contact	Graph Diffuser	MRR	0.3388±0.0011	#2 of 18	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position Encodings Adam Attention BPE Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections