Papers › Path-aware Siamese Graph Neural Network for Link Prediction

Path-aware Siamese Graph Neural Network for Link Prediction

10 Aug 2022arXiv:2208.05781archive 2025-07-28

Jingsong Lv, Zhao Li, Hongyang Chen, Yao Qi, Chunqi Wu

In this paper, we propose a Path-aware Siamese Graph neural network(PSG) for link prediction tasks. First, PSG captures both nodes and edge features for given two nodes, namely the structure information of k-neighborhoods and relay paths information of the nodes. Furthermore, a novel multi-task GNN framework with self-supervised contrastive learning is proposed for differentiation of positive links and negative links while content and behavior of nodes can be captured simultaneously. We evaluate the proposed algorithm PSG on two link property prediction datasets, ogbl-ddi and ogbl-collab. PSG achieves top 1 performance on ogbl-ddi until submission and top 3 performance on ogbl-collab. The experimental results verify the superiority of our proposed PSG

PaperPDFCode

Code

jingsonglv/PSG 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 Neural NetworkLink PredictionLink Property PredictionProperty PredictionRepresentation Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Link Property Prediction ogbl-ddi PSG Ext. data No #7 of 31 Archive leaderboard report
Link Property Prediction ogbl-ddi PSG Number of params 3499009 #7 of 31 Archive leaderboard report
Link Property Prediction ogbl-ddi PSG Test Hits@20 0.9284 ± 0.0047 #7 of 31 Archive leaderboard report
Link Property Prediction ogbl-ddi PSG Validation Hits@20 0.8306 ± 0.0134 #7 of 31 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