Papers › Neural Common Neighbor with Completion for Link Prediction

Neural Common Neighbor with Completion for Link Prediction

2 Feb 2023arXiv:2302.00890archive 2025-07-28

Xiyuan Wang, Haotong Yang, Muhan Zhang

In this work, we propose a novel link prediction model and further boost it by studying graph incompleteness. First, we introduce MPNN-then-SF, an innovative architecture leveraging structural feature (SF) to guide MPNN's representation pooling, with its implementation, namely Neural Common Neighbor (NCN). NCN exhibits superior expressiveness and scalability compared with existing models, which can be classified into two categories: SF-then-MPNN, augmenting MPNN's input with SF, and SF-and-MPNN, decoupling SF and MPNN. Second, we investigate the impact of graph incompleteness -- the phenomenon that some links are unobserved in the input graph -- on SF, like the common neighbor. Through dataset visualization, we observe that incompleteness reduces common neighbors and induces distribution shifts, significantly affecting model performance. To address this issue, we propose to use a link prediction model to complete the common neighbor structure. Combining this method with NCN, we propose Neural Common Neighbor with Completion (NCNC). NCN and NCNC outperform recent strong baselines by large margins, and NCNC further surpasses state-of-the-art models in standard link prediction benchmarks. Our code is available at https://github.com/GraphPKU/NeuralCommonNeighbor.

PaperPDFCode

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

Code

GraphPKU/NeuralCommonNeighbor officialmentioned in papermentioned 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

Link PredictionPrediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Link Property Prediction ogbl-ddi NeuralCommonNeighbor Ext. data No #13 of 31 Archive leaderboard report
Link Property Prediction ogbl-ddi NeuralCommonNeighbor Number of params 1412098 #13 of 31 Archive leaderboard report
Link Property Prediction ogbl-ddi NeuralCommonNeighbor Test Hits@20 0.8232 ± 0.0610 #13 of 31 Archive leaderboard report
Link Property Prediction ogbl-ddi NeuralCommonNeighbor Validation Hits@20 0.7172 ± 0.0025 #13 of 31 Archive leaderboard report
Link Property Prediction ogbl-ppa **Neural Common Neighbor ** Ext. data No #7 of 26 Archive leaderboard report
Link Property Prediction ogbl-ppa **Neural Common Neighbor ** Number of params 33538 #7 of 26 Archive leaderboard report
Link Property Prediction ogbl-ppa **Neural Common Neighbor ** Test Hits@100 0.6119 ± 0.0085 #7 of 26 Archive leaderboard report
Link Property Prediction ogbl-ppa **Neural Common Neighbor ** Validation Hits@100 0.6021 ± 0.0037 #7 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.

Methods

MPNNTest

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