Papers › Can GNNs Learn Link Heuristics? A Concise Review and Evaluation of Link Prediction Methods

Can GNNs Learn Link Heuristics? A Concise Review and Evaluation of Link Prediction Methods

22 Nov 2024arXiv:2411.14711archive 2025-07-28

Shuming Liang, Yu Ding, Zhidong Li, Bin Liang, Siqi Zhang, Yang Wang, Fang Chen

This paper explores the ability of Graph Neural Networks (GNNs) in learning various forms of information for link prediction, alongside a brief review of existing link prediction methods. Our analysis reveals that GNNs cannot effectively learn structural information related to the number of common neighbors between two nodes, primarily due to the nature of set-based pooling of the neighborhood aggregation scheme. Also, our extensive experiments indicate that trainable node embeddings can improve the performance of GNN-based link prediction models. Importantly, we observe that the denser the graph, the greater such the improvement. We attribute this to the characteristics of node embeddings, where the link state of each link sample could be encoded into the embeddings of nodes that are involved in the neighborhood aggregation of the two nodes in that link sample. In denser graphs, every node could have more opportunities to attend the neighborhood aggregation of other nodes and encode states of more link samples to its embedding, thus learning better node embeddings for link prediction. Lastly, we demonstrate that the insights gained from our research carry important implications in identifying the limitations of existing link prediction methods, which could guide the future development of more robust algorithms.

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="2411.14711")

Code

Syntology Ran 0 of 3 code samples harvested from 1 repository linked to this paper; 3 have no recorded run.

By repository: official repository: 3 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

astroming/GNNHE officialpytorchMIT 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; 0 ran; 0 honoured the contract we drafted; 3 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.

3unverified

Licence: 0 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 astroming/GNNHE. “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.

get_loggers astroming/GNNHE/ogbl-citation2_88.91_10runs/utils.py official repository unverified MIT (permissive) · 3a770ee50f27e1b9 · report
get_optimizer astroming/GNNHE/ogbl-citation2_88.91_10runs/models.py official repository unverified MIT (permissive) · 79fa2feaacf5673e · report
maybe_num_nodes astroming/GNNHE/ogbl-citation2_88.91_10runs/utils.py official repository unverified MIT (permissive) · 76ea6d8c225e28b7 · report

Tasks

AttributeLink PredictionPrediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Link Property Prediction ogbl-citation2 GCN + Heuristic Encoding Ext. data No #6 of 23 Archive leaderboard report
Link Property Prediction ogbl-citation2 GCN + Heuristic Encoding Number of params 372674 #6 of 23 Archive leaderboard report
Link Property Prediction ogbl-citation2 GCN + Heuristic Encoding Test MRR 0.8891 ± 0.0005 #6 of 23 Archive leaderboard report
Link Property Prediction ogbl-citation2 GCN + Heuristic Encoding Validation MRR 0.8892 ± 0.0005 #6 of 23 Archive leaderboard report
Link Property Prediction ogbl-ddi GCN (node embedding) Ext. data No #3 of 31 Archive leaderboard report
Link Property Prediction ogbl-ddi GCN (node embedding) Number of params 5125250 #3 of 31 Archive leaderboard report
Link Property Prediction ogbl-ddi GCN (node embedding) Test Hits@20 0.9549 ± 0.0073 #3 of 31 Archive leaderboard report
Link Property Prediction ogbl-ddi GCN (node embedding) Validation Hits@20 0.9098 ± 0.0294 #3 of 31 Archive leaderboard report
Link Property Prediction ogbl-ppa GCN (node embedding) Ext. data No #5 of 26 Archive leaderboard report
Link Property Prediction ogbl-ppa GCN (node embedding) Number of params 148144898 #5 of 26 Archive leaderboard report
Link Property Prediction ogbl-ppa GCN (node embedding) Test Hits@100 0.6354 ± 0.0121 #5 of 26 Archive leaderboard report
Link Property Prediction ogbl-ppa GCN (node embedding) Validation Hits@100 0.6524 ± 0.0096 #5 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.

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