Papers › Cleora: A Simple, Strong and Scalable Graph Embedding Scheme

Cleora: A Simple, Strong and Scalable Graph Embedding Scheme

3 Feb 2021arXiv:2102.02302archive 2025-07-28

Barbara Rychalska, Piotr Bąbel, Konrad Gołuchowski, Andrzej Michałowski, Jacek Dąbrowski

The area of graph embeddings is currently dominated by contrastive learning methods, which demand formulation of an explicit objective function and sampling of positive and negative examples. This creates a conceptual and computational overhead. Simple, classic unsupervised approaches like Multidimensional Scaling (MSD) or the Laplacian eigenmap skip the necessity of tedious objective optimization, directly exploiting data geometry. Unfortunately, their reliance on very costly operations such as matrix eigendecomposition make them unable to scale to large graphs that are common in today's digital world. In this paper we present Cleora: an algorithm which gets the best of two worlds, being both unsupervised and highly scalable. We show that high quality embeddings can be produced without the popular step-wise learning framework with example sampling. An intuitive learning objective of our algorithm is that a node should be similar to its neighbors, without explicitly pushing disconnected nodes apart. The objective is achieved by iterative weighted averaging of node neigbors' embeddings, followed by normalization across dimensions. Thanks to the averaging operation the algorithm makes rapid strides across the embedding space and usually reaches optimal embeddings in just a few iterations. Cleora runs faster than other state-of-the-art CPU algorithms and produces embeddings of competitive quality as measured on downstream tasks: link prediction and node classification. We show that Cleora learns a data abstraction that is similar to contrastive methods, yet at much lower computational cost. We open-source Cleora under the MIT license allowing commercial use under https://github.com/Synerise/cleora.

PaperPDFCode

Code

Synerise/cleora officialmentioned in papermentioned on GitHubpytorch report
Synerise/booking-challenge 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

Contrastive LearningGraph EmbeddingLink PredictionNode ClassificationRecommendation Systems

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Classification Citeseer Cleora Accuracy 75.7 #20 of 71 Archive leaderboard report
Node Classification Cora Cleora Accuracy 86.80% #19 of 73 Archive leaderboard report
Node Classification Pubmed Cleora Accuracy 80.2 #34 of 70 Archive leaderboard report
Node Classification YouTube Cleora Macro-F1@2% 30.77 #2 of 2 Archive leaderboard report
Node Classification YouTube Cleora Micro-F1@2% 38.59 #2 of 2 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

Contrastive Learning

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