Papers › Online Graph Dictionary Learning

Online Graph Dictionary Learning

12 Feb 2021arXiv:2102.06555archive 2025-07-28

Cédric Vincent-Cuaz, Titouan Vayer, Rémi Flamary, Marco Corneli, Nicolas Courty

Dictionary learning is a key tool for representation learning, that explains the data as linear combination of few basic elements. Yet, this analysis is not amenable in the context of graph learning, as graphs usually belong to different metric spaces. We fill this gap by proposing a new online Graph Dictionary Learning approach, which uses the Gromov Wasserstein divergence for the data fitting term. In our work, graphs are encoded through their nodes' pairwise relations and modeled as convex combination of graph atoms, i.e. dictionary elements, estimated thanks to an online stochastic algorithm, which operates on a dataset of unregistered graphs with potentially different number of nodes. Our approach naturally extends to labeled graphs, and is completed by a novel upper bound that can be used as a fast approximation of Gromov Wasserstein in the embedding space. We provide numerical evidences showing the interest of our approach for unsupervised embedding of graph datasets and for online graph subspace estimation and tracking.

PaperPDFCode

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

Code

cedricvincentcuaz/GDL officialmentioned in papermentioned 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

Dictionary LearningGraph ClassificationGraph LearningRepresentation Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Classification BZR GDL-g (ADJ) Accuracy 87.81 #1 of 1 Archive leaderboard report
Graph Classification COX2 GDL-g (ADJ) Accuracy(10-fold) 78.11 #2 of 3 Archive leaderboard report
Graph Classification ENZYMES GDL-g (SP) Accuracy 71.47 #10 of 54 Archive leaderboard report
Graph Classification IMDb-B GDL Accuracy 72.06% #41 of 51 Archive leaderboard report
Graph Classification IMDb-B GDL Rand index 51.64 #41 of 51 Archive leaderboard report
Graph Classification IMDb-M GDL Accuracy 50.64% #20 of 36 Archive leaderboard report
Graph Classification MUTAG GDL-g (SP) Accuracy 87.09% #50 of 74 Archive leaderboard report
Graph Classification MUTAG GDL-g (ADJ) Accuracy 58.45% #72 of 74 Archive leaderboard report
Graph Classification PROTEINS GDL-g (SP) Accuracy 74.86 #75 of 103 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