Papers › FDGATII : Fast Dynamic Graph Attention with Initial Residual and Identity Mapping

FDGATII : Fast Dynamic Graph Attention with Initial Residual and Identity Mapping

21 Oct 2021arXiv:2110.11464archive 2025-07-28

Gayan K. Kulatilleke, Marius Portmann, Ryan Ko, Shekhar S. Chandra

While Graph Neural Networks have gained popularity in multiple domains, graph-structured input remains a major challenge due to (a) over-smoothing, (b) noisy neighbours (heterophily), and (c) the suspended animation problem. To address all these problems simultaneously, we propose a novel graph neural network FDGATII, inspired by attention mechanism's ability to focus on selective information supplemented with two feature preserving mechanisms. FDGATII combines Initial Residuals and Identity Mapping with the more expressive dynamic self-attention to handle noise prevalent from the neighbourhoods in heterophilic data sets. By using sparse dynamic attention, FDGATII is inherently parallelizable in design, whist efficient in operation; thus theoretically able to scale to arbitrary graphs with ease. Our approach has been extensively evaluated on 7 datasets. We show that FDGATII outperforms GAT and GCN based benchmarks in accuracy and performance on fully supervised tasks, obtaining state-of-the-art results on Chameleon and Cornell datasets with zero domain-specific graph pre-processing, and demonstrate its versatility and fairness.

PaperPDFCode

Code

gayanku/FDGATII officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

FairnessGraph AttentionGraph Neural NetworkNode Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Classification Chameleon FDGATII Accuracy 65.1754 #46 of 61 Archive leaderboard report
Node Classification Citeseer Full-supervised FDGATII Accuracy 75.6434% #5 of 7 Archive leaderboard report
Node Classification Cora Full-supervised FDGATII Accuracy 87.7867% #3 of 9 Archive leaderboard report
Node Classification Cornell FDGATII Accuracy 82.4324 #34 of 60 Archive leaderboard report
Node Classification Pubmed Full-supervised FDGATII Accuracy 90.3524% #3 of 7 Archive leaderboard report
Node Classification Texas FDGATII Accuracy 80.5405 #49 of 62 Archive leaderboard report
Node Classification Wisconsin FDGATII Accuracy 86.2745 #39 of 63 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

GATGCNGraph Neural Network

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