Papers › Adversarially Regularized Graph Autoencoder for Graph Embedding

Adversarially Regularized Graph Autoencoder for Graph Embedding

13 Feb 2018arXiv:1802.04407archive 2025-07-28

Shirui Pan, Ruiqi Hu, Guodong Long, Jing Jiang, Lina Yao, Chengqi Zhang

Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics. Most existing embedding algorithms typically focus on preserving the topological structure or minimizing the reconstruction errors of graph data, but they have mostly ignored the data distribution of the latent codes from the graphs, which often results in inferior embedding in real-world graph data. In this paper, we propose a novel adversarial graph embedding framework for graph data. The framework encodes the topological structure and node content in a graph to a compact representation, on which a decoder is trained to reconstruct the graph structure. Furthermore, the latent representation is enforced to match a prior distribution via an adversarial training scheme. To learn a robust embedding, two variants of adversarial approaches, adversarially regularized graph autoencoder (ARGA) and adversarially regularized variational graph autoencoder (ARVGA), are developed. Experimental studies on real-world graphs validate our design and demonstrate that our algorithms outperform baselines by a wide margin in link prediction, graph clustering, and graph visualization tasks.

PaperPDFCode

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

Code

Ruiqi-Hu/ARGA mentioned on GitHubtf report
basiralab/HADA mentioned on GitHubtf report
basiralab/HCAE mentioned on GitHubtf report
basiralab/LG-DADA mentioned on GitHubtf 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

ClusteringDecoderGraph ClusteringGraph EmbeddingLink Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Clustering Citeseer ARGE ACC 57.3 #6 of 9 Archive leaderboard report
Graph Clustering Citeseer ARGE ARI 34.1 #6 of 9 Archive leaderboard report
Graph Clustering Citeseer ARGE F1 54.6 #6 of 9 Archive leaderboard report
Graph Clustering Citeseer ARGE NMI 0.35 #6 of 9 Archive leaderboard report
Graph Clustering Citeseer ARGE Precision 57.3 #6 of 9 Archive leaderboard report
Graph Clustering Citeseer ARVGE ACC 54.4 #7 of 9 Archive leaderboard report
Graph Clustering Citeseer ARVGE ARI 24.5 #7 of 9 Archive leaderboard report
Graph Clustering Citeseer ARVGE F1 52.9 #7 of 9 Archive leaderboard report
Graph Clustering Citeseer ARVGE NMI 26.1 #7 of 9 Archive leaderboard report
Graph Clustering Citeseer ARVGE Precision 54.9 #7 of 9 Archive leaderboard report
Graph Clustering Cora ARGE ACC 64 #6 of 9 Archive leaderboard report
Graph Clustering Cora ARGE ARI 35.2 #6 of 9 Archive leaderboard report
Graph Clustering Cora ARGE F1 61.9 #6 of 9 Archive leaderboard report
Graph Clustering Cora ARGE NMI 0.449 #6 of 9 Archive leaderboard report
Graph Clustering Cora ARGE Precision 64.6 #6 of 9 Archive leaderboard report
Graph Clustering Cora ARVGE ACC 63.8 #7 of 9 Archive leaderboard report
Graph Clustering Cora ARVGE ARI 37.4 #7 of 9 Archive leaderboard report
Graph Clustering Cora ARVGE F1 62.7 #7 of 9 Archive leaderboard report
Graph Clustering Cora ARVGE NMI 45 #7 of 9 Archive leaderboard report
Graph Clustering Cora ARVGE Precision 62.4 #7 of 9 Archive leaderboard report
Link Prediction Citeseer ARGE AP 93 #10 of 13 Archive leaderboard report
Link Prediction Citeseer ARGE AUC 91.9 #10 of 13 Archive leaderboard report
Link Prediction Cora ARGE AP 93.2% #11 of 13 Archive leaderboard report
Link Prediction Cora ARGE AUC 92.4% #11 of 13 Archive leaderboard report
Link Prediction Pubmed ARGE AP 97.1% #6 of 13 Archive leaderboard report
Link Prediction Pubmed ARGE AUC 96.8% #6 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