Papers › Spectral Heterogeneous Graph Convolutions via Positive Noncommutative Polynomials

Spectral Heterogeneous Graph Convolutions via Positive Noncommutative Polynomials

31 May 2023arXiv:2305.19872archive 2025-07-28

Mingguo He, Zhewei Wei, Shikun Feng, Zhengjie Huang, Weibin Li, Yu Sun, dianhai yu

Heterogeneous Graph Neural Networks (HGNNs) have gained significant popularity in various heterogeneous graph learning tasks. However, most existing HGNNs rely on spatial domain-based methods to aggregate information, i.e., manually selected meta-paths or some heuristic modules, lacking theoretical guarantees. Furthermore, these methods cannot learn arbitrary valid heterogeneous graph filters within the spectral domain, which have limited expressiveness. To tackle these issues, we present a positive spectral heterogeneous graph convolution via positive noncommutative polynomials. Then, using this convolution, we propose PSHGCN, a novel Positive Spectral Heterogeneous Graph Convolutional Network. PSHGCN offers a simple yet effective method for learning valid heterogeneous graph filters. Moreover, we demonstrate the rationale of PSHGCN in the graph optimization framework. We conducted an extensive experimental study to show that PSHGCN can learn diverse heterogeneous graph filters and outperform all baselines on open benchmarks. Notably, PSHGCN exhibits remarkable scalability, efficiently handling large real-world graphs comprising millions of nodes and edges. Our codes are available at https://github.com/ivam-he/PSHGCN.

PaperPDFCode

Code

ivam-he/pshgcn officialmentioned in papermentioned on GitHubpytorch report
ivam-he/PSHGCN mentioned on GitHubpytorch 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 LearningNode ClassificationNode Property Prediction

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Property Prediction ogbn-mag PSHGCN (ComplEx embs) Ext. data No #7 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag PSHGCN (ComplEx embs) Number of params 4852434 #7 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag PSHGCN (ComplEx embs) Test Accuracy 0.5752 ± 0.0011 #7 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag PSHGCN (ComplEx embs) Validation Accuracy 0.5943 ± 0.0015 #7 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag PSHGCN Ext. data No #8 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag PSHGCN Number of params 4852434 #8 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag PSHGCN Test Accuracy 0.5752 ± 0.0011 #8 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag PSHGCN Validation Accuracy 0.5943 ± 0.0015 #8 of 39 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