Papers › Pairwise Learning for Neural Link Prediction

Pairwise Learning for Neural Link Prediction

6 Dec 2021arXiv:2112.02936archive 2025-07-28

Zhitao Wang, Yong Zhou, Litao Hong, Yuanhang Zou, Hanjing Su, Shouzhi Chen

In this paper, we aim at providing an effective Pairwise Learning Neural Link Prediction (PLNLP) framework. The framework treats link prediction as a pairwise learning to rank problem and consists of four main components, i.e., neighborhood encoder, link predictor, negative sampler and objective function. The framework is flexible that any generic graph neural convolution or link prediction specific neural architecture could be employed as neighborhood encoder. For link predictor, we design different scoring functions, which could be selected based on different types of graphs. In negative sampler, we provide several sampling strategies, which are problem specific. As for objective function, we propose to use an effective ranking loss, which approximately maximizes the standard ranking metric AUC. We evaluate the proposed PLNLP framework on 4 link property prediction datasets of Open Graph Benchmark, including ogbl-ddi, ogbl-collab, ogbl-ppa and ogbl-ciation2. PLNLP achieves top 1 performance on ogbl-ddi and ogbl-collab, and top 2 performance on ogbl-ciation2 only with basic neural architecture. The performance demonstrates the effectiveness of PLNLP.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2112.02936")

Code

Syntology Ran 1 of 3 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: official repository: 3 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

zhitao-wang/plnlp officialmentioned in papermentioned on GitHubpytorch report
zhitao-wang/PLNLP 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

3 samples harvested; 1 ran; 0 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
2unverified

Licence: 3 of the 3 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from zhitao-wang/PLNLP. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

create_input_layer zhitao-wang/PLNLP/plnlp/model.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · e6bb9922628f848a · report
create_gnn_layer zhitao-wang/PLNLP/plnlp/model.py official repository unverified no licence file found · pointer only · a56bfc04a5dba811 · report
create_predictor_layer zhitao-wang/PLNLP/plnlp/model.py official repository unverified no licence file found · pointer only · 8c798721c3345583 · report

Tasks

Learning-To-RankLink PredictionLink Property PredictionPredictionProperty Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Link Property Prediction ogbl-citation2 PLNLP Ext. data No #13 of 23 Archive leaderboard report
Link Property Prediction ogbl-citation2 PLNLP Number of params 146514551 #13 of 23 Archive leaderboard report
Link Property Prediction ogbl-citation2 PLNLP Test MRR 0.8492 ± 0.0029 #13 of 23 Archive leaderboard report
Link Property Prediction ogbl-citation2 PLNLP Validation MRR 0.8490 ± 0.0031 #13 of 23 Archive leaderboard report
Link Property Prediction ogbl-collab PLNLP (random walk aug.) Ext. data No #5 of 34 Archive leaderboard report
Link Property Prediction ogbl-collab PLNLP (random walk aug.) Number of params 34980864 #5 of 34 Archive leaderboard report
Link Property Prediction ogbl-collab PLNLP (random walk aug.) Test Hits@50 0.7059 ± 0.0029 #5 of 34 Archive leaderboard report
Link Property Prediction ogbl-collab PLNLP (random walk aug.) Validation Hits@50 1.0000 ± 0.0000 #5 of 34 Archive leaderboard report
Link Property Prediction ogbl-collab PLNLP (val as input) Ext. data No #8 of 34 Archive leaderboard report
Link Property Prediction ogbl-collab PLNLP (val as input) Number of params 35112192 #8 of 34 Archive leaderboard report
Link Property Prediction ogbl-collab PLNLP (val as input) Test Hits@50 0.6872 ± 0.0052 #8 of 34 Archive leaderboard report
Link Property Prediction ogbl-collab PLNLP (val as input) Validation Hits@50 1.0000 ± 0.0000 #8 of 34 Archive leaderboard report
Link Property Prediction ogbl-ddi PLNLP Ext. data No #8 of 31 Archive leaderboard report
Link Property Prediction ogbl-ddi PLNLP Number of params 3497473 #8 of 31 Archive leaderboard report
Link Property Prediction ogbl-ddi PLNLP Test Hits@20 0.9088 ± 0.0313 #8 of 31 Archive leaderboard report
Link Property Prediction ogbl-ddi PLNLP Validation Hits@20 0.8242 ± 0.0253 #8 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

Convolution

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