Papers › FDGATII : Fast Dynamic Graph Attention with Initial Residual and Identity Mapping
FDGATII : Fast Dynamic Graph Attention with Initial Residual and Identity Mapping
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.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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
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