Papers › A Persistent Weisfeiler–Lehman Procedure for Graph Classification

A Persistent Weisfeiler–Lehman Procedure for Graph Classification

9 Jun 2019Proceedings of the 36th International Conference on Machine Learning 2019 6archive 2025-07-28

Bastian Rieck, Christian Bock, Karsten Borgwardt

The Weisfeiler–Lehman graph kernel exhibits competitive performance in many graph classification tasks. However, its subtree features are not able to capture connected components and cycles, topological features known for characterising graphs. To extract such features, we leverage propagated node label information and transform unweighted graphs into metric ones. This permits us to augment the subtree features with topological information obtained using persistent homology, a concept from topological data analysis. Our method, which we formalise as a generalisation of Weisfeiler–Lehman subtree features, exhibits favourable classification accuracy and its improvements in predictive performance are mainly driven by including cycle information.

PaperPDFCode

Code

BorgwardtLab/P-WL mentioned in paper 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 ClassificationTopological Data Analysis

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Classification MUTAG P-WL-C Mean Accuracy 90.51 #73 of 74 Archive leaderboard report
Graph Classification PROTEINS P-WL-UC Accuracy 75.36% #67 of 103 Archive leaderboard report
Graph Property Prediction ogbg-molhiv P-WL Ext. data No #19 of 43 Archive leaderboard report
Graph Property Prediction ogbg-molhiv P-WL Number of params 4600000 #19 of 43 Archive leaderboard report
Graph Property Prediction ogbg-molhiv P-WL Test ROC-AUC 0.8039 ± 0.0040 #19 of 43 Archive leaderboard report
Graph Property Prediction ogbg-molhiv P-WL Validation ROC-AUC 0.8279 ± 0.0059 #19 of 43 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