Papers › Parameterized Hypercomplex Graph Neural Networks for Graph Classification

Parameterized Hypercomplex Graph Neural Networks for Graph Classification

30 Mar 2021arXiv:2103.16584archive 2025-07-28

Tuan Le, Marco Bertolini, Frank Noé, Djork-Arné Clevert

Despite recent advances in representation learning in hypercomplex (HC) space, this subject is still vastly unexplored in the context of graphs. Motivated by the complex and quaternion algebras, which have been found in several contexts to enable effective representation learning that inherently incorporates a weight-sharing mechanism, we develop graph neural networks that leverage the properties of hypercomplex feature transformation. In particular, in our proposed class of models, the multiplication rule specifying the algebra itself is inferred from the data during training. Given a fixed model architecture, we present empirical evidence that our proposed model incorporates a regularization effect, alleviating the risk of overfitting. We also show that for fixed model capacity, our proposed method outperforms its corresponding real-formulated GNN, providing additional confirmation for the enhanced expressivity of HC embeddings. Finally, we test our proposed hypercomplex GNN on several open graph benchmark datasets and show that our models reach state-of-the-art performance while consuming a much lower memory footprint with 70& fewer parameters. Our implementations are available at https://github.com/bayer-science-for-a-better-life/phc-gnn.

PaperPDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

Code

bayer-science-for-a-better-life/phc-gnn officialmentioned in papermentioned on GitHubpytorchGPL-3.0 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

ClassificationGeneral ClassificationGraph ClassificationRepresentation Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Property Prediction ogbg-molhiv PHC-GNN Ext. data No #24 of 43 Archive leaderboard report
Graph Property Prediction ogbg-molhiv PHC-GNN Number of params 110909 #24 of 43 Archive leaderboard report
Graph Property Prediction ogbg-molhiv PHC-GNN Test ROC-AUC 0.7934 ± 0.0116 #24 of 43 Archive leaderboard report
Graph Property Prediction ogbg-molhiv PHC-GNN Validation ROC-AUC 0.8217 ± 0.0089 #24 of 43 Archive leaderboard report
Graph Property Prediction ogbg-molpcba PHC-GNN Ext. data No #17 of 36 Archive leaderboard report
Graph Property Prediction ogbg-molpcba PHC-GNN Number of params 1690328 #17 of 36 Archive leaderboard report
Graph Property Prediction ogbg-molpcba PHC-GNN Test AP 0.2947 ± 0.0026 #17 of 36 Archive leaderboard report
Graph Property Prediction ogbg-molpcba PHC-GNN Validation AP 0.3068 ± 0.0025 #17 of 36 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