Papers › Multi-hop Attention-based Graph Pooling: A Personalized PageRank Perspective

Multi-hop Attention-based Graph Pooling: A Personalized PageRank Perspective

4 Mar 2024International Conference on Distributed Computing and High Performance Computing (DCHPC) 2024 3archive 2025-07-28

Parsa Haddadian, Roya Booryaee, Rooholah Abedian, Ali Moeini

Over the past ten years, graph representation learning has garnered a lot of attention due to the variety of graph-structured data and its efficiency in both time and space. One essential method for obtaining effective graph representations is graph pooling. Numerous studies on the graph pooling technique have been conducted. Cutting-edge results on a range of graph representation learning tasks were made possible by the combination of graph neural networks and self-attention mechanisms. Nevertheless, the attention mechanism has limitations since it ignores nodes that have no direct connection via an edge but provide valuable network context information. This paper proposes a graph pooling approach based on Personalized PageRank and self-attention, which improves the model to take into account both node properties and graph structure. The experimental findings indicate that, with a suitable number of parameters, the MAGPool approach delivers greater accuracy on the benchmark datasets.

PaperPDFCode

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

Graph ClassificationGraph Representation LearningRepresentation Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Classification D&D MAGPool Accuracy 79.83% #15 of 53 Archive leaderboard report
Graph Classification FRANKENSTEIN MAGPool Accuracy 67.21 #3 of 6 Archive leaderboard report
Graph Classification NCI1 MAGPool Accuracy 72.32% #60 of 69 Archive leaderboard report
Graph Classification NCI109 MAGPool Accuracy 73.43% #32 of 38 Archive leaderboard report
Graph Classification PROTEINS MAGPool Accuracy 80.36% #10 of 103 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

Convolution

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