Papers › Variational Graph Normalized Auto-Encoders
Variational Graph Normalized Auto-Encoders
Seong Jin Ahn, Myoung Ho Kim
Link prediction is one of the key problems for graph-structured data. With the advancement of graph neural networks, graph autoencoders (GAEs) and variational graph autoencoders (VGAEs) have been proposed to learn graph embeddings in an unsupervised way. It has been shown that these methods are effective for link prediction tasks. However, they do not work well in link predictions when a node whose degree is zero (i.g., isolated node) is involved. We have found that GAEs/VGAEs make embeddings of isolated nodes close to zero regardless of their content features. In this paper, we propose a novel Variational Graph Normalized AutoEncoder (VGNAE) that utilize L2-normalization to derive better embeddings for isolated nodes. We show that our VGNAEs outperform the existing state-of-the-art models for link prediction tasks. The code is available at https://github.com/SeongJinAhn/VGNAE.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Link Prediction | Citeseer | VGNAE | AP | 97.1 | #2 of 13 | Archive leaderboard | report |
| Link Prediction | Citeseer | VGNAE | AUC | 97 | #2 of 13 | Archive leaderboard | report |
| Link Prediction | Citeseer | GNAE | AP | 97 | #4 of 13 | Archive leaderboard | report |
| Link Prediction | Citeseer | GNAE | AUC | 96.5 | #4 of 13 | Archive leaderboard | report |
| Link Prediction | Cora | GNAE | AP | 95.7% | #4 of 13 | Archive leaderboard | report |
| Link Prediction | Cora | GNAE | AUC | 95.6% | #4 of 13 | Archive leaderboard | report |
| Link Prediction | Cora | VGNAE | AP | 95.8% | #5 of 13 | Archive leaderboard | report |
| Link Prediction | Cora | VGNAE | AUC | 95.4% | #5 of 13 | Archive leaderboard | report |
| Link Prediction | Pubmed | VGNAE | AP | 97.6% | #4 of 13 | Archive leaderboard | report |
| Link Prediction | Pubmed | VGNAE | AUC | 97.6% | #4 of 13 | Archive leaderboard | report |
| Link Prediction | Pubmed | GNAE | AP | 97.5% | #5 of 13 | Archive leaderboard | report |
| Link Prediction | Pubmed | GNAE | AUC | 97.5% | #5 of 13 | 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