</> Code with Papers by Syntology

Papers › Reconsidering the Performance of GAE in Link Prediction

Reconsidering the Performance of GAE in Link Prediction

6 Nov 2024arXiv:2411.03845archive 2025-07-28

Weishuo Ma, Yanbo Wang, Xiyuan Wang, Muhan Zhang

Various graph neural networks (GNNs) with advanced training techniques and model designs have been proposed for link prediction tasks. However, outdated baseline models may lead to an overestimation of the benefits provided by these novel approaches. To address this, we systematically investigate the potential of Graph Autoencoders (GAE) by meticulously tuning hyperparameters and utilizing the trick of orthogonal embedding and linear propagation. Our findings reveal that a well-optimized GAE can match the performance of more complex models while offering greater computational efficiency.

PaperPDFCode

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

Code

graphpku/refined-gae officialmentioned in papermentioned on GitHubpytorch report
GraphPKU/Refined-GAE 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

Computational EfficiencyLink PredictionPrediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Link Property Prediction ogbl-collab Refined-GAE Ext. data No #9 of 34 Archive leaderboard report
Link Property Prediction ogbl-collab Refined-GAE Number of params 126669825 #9 of 34 Archive leaderboard report
Link Property Prediction ogbl-collab Refined-GAE Test Hits@50 0.6816 ± 0.0041 #9 of 34 Archive leaderboard report
Link Property Prediction ogbl-collab Refined-GAE Validation Hits@50 1.0000 ± 0.0000 #9 of 34 Archive leaderboard report
Link Property Prediction ogbl-ddi Refined-GAE Ext. data No #6 of 31 Archive leaderboard report
Link Property Prediction ogbl-ddi Refined-GAE Number of params 13816833 #6 of 31 Archive leaderboard report
Link Property Prediction ogbl-ddi Refined-GAE Test Hits@20 0.9443 ± 0.0057 #6 of 31 Archive leaderboard report
Link Property Prediction ogbl-ddi Refined-GAE Validation Hits@20 0.7979 ± 0.0159 #6 of 31 Archive leaderboard report
Link Property Prediction ogbl-ppa Refined-GAE Ext. data No #2 of 26 Archive leaderboard report
Link Property Prediction ogbl-ppa Refined-GAE Number of params 295848449 #2 of 26 Archive leaderboard report
Link Property Prediction ogbl-ppa Refined-GAE Test Hits@100 0.7334 ± 0.0092 #2 of 26 Archive leaderboard report
Link Property Prediction ogbl-ppa Refined-GAE Validation Hits@100 0.7391 ± 0.0178 #2 of 26 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