Papers › Beyond Homophily: Structure-aware Path Aggregation Graph Neural Network
Beyond Homophily: Structure-aware Path Aggregation Graph Neural Network
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.
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
Datasets
Introduced by this paper, per the archive.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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
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