Papers › Graph Representation Learning via Hard and Channel-Wise Attention Networks

Graph Representation Learning via Hard and Channel-Wise Attention Networks

5 Jul 2019arXiv:1907.04652archive 2025-07-28

Hongyang Gao, Shuiwang Ji

Attention operators have been widely applied in various fields, including computer vision, natural language processing, and network embedding learning. Attention operators on graph data enables learnable weights when aggregating information from neighboring nodes. However, graph attention operators (GAOs) consume excessive computational resources, preventing their applications on large graphs. In addition, GAOs belong to the family of soft attention, instead of hard attention, which has been shown to yield better performance. In this work, we propose novel hard graph attention operator (hGAO) and channel-wise graph attention operator (cGAO). hGAO uses the hard attention mechanism by attending to only important nodes. Compared to GAO, hGAO improves performance and saves computational cost by only attending to important nodes. To further reduce the requirements on computational resources, we propose the cGAO that performs attention operations along channels. cGAO avoids the dependency on the adjacency matrix, leading to dramatic reductions in computational resource requirements. Experimental results demonstrate that our proposed deep models with the new operators achieve consistently better performance. Comparison results also indicates that hGAO achieves significantly better performance than GAO on both node and graph embedding tasks. Efficiency comparison shows that our cGAO leads to dramatic savings in computational resources, making them applicable to large graphs.

PaperPDFCode

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

Code

dmlc/dgl pytorch 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

Graph AttentionGraph ClassificationGraph EmbeddingGraph Representation LearningHard AttentionNetwork EmbeddingRepresentation Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Classification COLLAB hGANet Accuracy 77.48% #23 of 39 Archive leaderboard report
Graph Classification D&D hGANet Accuracy 81.71% #9 of 53 Archive leaderboard report
Graph Classification IMDb-M hGANet Accuracy 49.06% #29 of 36 Archive leaderboard report
Graph Classification MUTAG hGANet Accuracy 90.00% #24 of 74 Archive leaderboard report
Graph Classification PROTEINS hGANet Accuracy 78.65% #17 of 103 Archive leaderboard report
Graph Classification PROTEINS cGANet Accuracy 78.23% #20 of 103 Archive leaderboard report
Graph Classification PROTEINS GANet Accuracy 77.92% #22 of 103 Archive leaderboard report
Graph Classification PTC hGANet Accuracy 65.02% #23 of 37 Archive leaderboard report
Graph Classification PTC cGANet Accuracy 63.53% #25 of 37 Archive leaderboard report
Graph Classification PTC GANet Accuracy 62.94% #27 of 37 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.

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