Papers › Beyond Homophily: Structure-aware Path Aggregation Graph Neural Network

Beyond Homophily: Structure-aware Path Aggregation Graph Neural Network

20 Jul 2022Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence 2022 7archive 2025-07-28

Yifei Sun, Haoran Deng, Yang Yang, Chunping Wang, Jiarong Xu, Renhong Huang, Linfeng Cao, Yang Wang, Lei Chen

Graph neural networks (GNNs) have been intensively studied in various real-world tasks. However, the homophily assumption of GNNs' aggregation function limits their representation learning ability in heterophily graphs. In this paper, we shed light on the path level patterns in graphs that can explicitly reflect rich semantic and structural information. We therefore propose a novel Structure-aware Path Aggregation Graph Neural Network (PathNet) aiming to generalize GNNs for both homophily and heterophily graphs. Specifically, we first introduce a maximal entropy path sampler, which helps us sample a number of paths containing structural context. Then, we introduce a structure-aware recurrent cell consisting of order-preserving and distance-aware components to learn the semantic information of neighborhoods. Finally, we model the preference of different paths to target node after path encoding. Experimental results demonstrate that our model obtains significant improvements in node classification on both heterophily and homophily graphs.

PaperPDFCode

Code

zjunet/PathNet mentioned in paperpytorchMIT 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 MiningGraph Neural NetworkNode ClassificationRepresentation Learning

Datasets

Introduced by this paper, per the archive.

BGPElectronicsNBA

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Classification BGP PathNet Accuracy (%) 65.71 #1 of 1 Archive leaderboard report
Node Classification Citeseer PathNet Accuracy (%) 77.98 #70 of 71 Archive leaderboard report
Node Classification Cornell PathNet Accuracy (%) 91.35 #60 of 60 Archive leaderboard report
Node Classification Electronics PathNet Accuracy (%) 76.97 #1 of 1 Archive leaderboard report
Node Classification NBA PathNet Accuracy (%) 71.69 #1 of 1 Archive leaderboard report
Node Classification Pubmed PathNet Accuracy (%) 88.92 #69 of 70 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

Graph 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