Papers › Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without...

Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages

16 Jun 2021arXiv:2106.08541archive 2025-07-28

Yi Luo, Aiguo Chen, Ke Yan, Ling Tian

Nowadays, Graph Neural Networks (GNNs) following the Message Passing paradigm become the dominant way to learn on graphic data. Models in this paradigm have to spend extra space to look up adjacent nodes with adjacency matrices and extra time to aggregate multiple messages from adjacent nodes. To address this issue, we develop a method called LinkDist that distils self-knowledge from connected node pairs into a Multi-Layer Perceptron (MLP) without the need to aggregate messages. Experiment with 8 real-world datasets shows the MLP derived from LinkDist can predict the label of a node without knowing its adjacencies but achieve comparable accuracy against GNNs in the contexts of semi- and full-supervised node classification. Moreover, LinkDist benefits from its Non-Message Passing paradigm that we can also distil self-knowledge from arbitrarily sampled node pairs in a contrastive way to further boost the performance of LinkDist.

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="2106.08541")

Code

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

By repository: official repository: 1 sample 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.

cf020031308/LinkDist officialmentioned in papermentioned on GitHubpytorch report
cf020031308/LinkDist 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

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

1unverified

Licence: 1 of the 1 sample is 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 cf020031308/LinkDist. “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.

optimize cf020031308/LinkDist/ogbn.py official repository unverified no licence file found · pointer only · eaab7909ebfb427e · report

Tasks

Node ClassificationNode Property Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Classification Amazon Computers LinkDist Accuracy 89.49% #9 of 12 Archive leaderboard report
Node Classification Amazon Computers LinkDistMLP Accuracy 89.44% #10 of 12 Archive leaderboard report
Node Classification Amazon Computers CoLinkDist Accuracy 89.42% #11 of 12 Archive leaderboard report
Node Classification Amazon Computers CoLinkDistMLP Accuracy 88.85% #12 of 12 Archive leaderboard report
Node Classification Amazon Photo CoLinkDist Accuracy 94.36% #8 of 11 Archive leaderboard report
Node Classification Amazon Photo CoLinkDistMLP Accuracy 94.12% #9 of 11 Archive leaderboard report
Node Classification Amazon Photo LinkDistMLP Accuracy 93.83% #10 of 11 Archive leaderboard report
Node Classification Amazon Photo LinkDist Accuracy 93.75% #11 of 11 Archive leaderboard report
Node Classification CiteSeer with Public Split: fixed 20 nodes per class CoLinkDistMLP Accuracy 70.96% #29 of 40 Archive leaderboard report
Node Classification CiteSeer with Public Split: fixed 20 nodes per class CoLinkDist Accuracy 70.79% #30 of 40 Archive leaderboard report
Node Classification CiteSeer with Public Split: fixed 20 nodes per class LinkDist Accuracy 70.27% #31 of 40 Archive leaderboard report
Node Classification CiteSeer with Public Split: fixed 20 nodes per class LinkDistMLP Accuracy 70.26% #32 of 40 Archive leaderboard report
Node Classification Citeseer CoLinkDist Accuracy 75.79% #17 of 71 Archive leaderboard report
Node Classification Citeseer CoLinkDistMLP Accuracy 75.77% #18 of 71 Archive leaderboard report
Node Classification Citeseer LinkDistMLP Accuracy 75.25% #22 of 71 Archive leaderboard report
Node Classification Citeseer LinkDist Accuracy 74.72% #24 of 71 Archive leaderboard report
Node Classification Coauthor CS CoLinkDist Accuracy 95.80% #6 of 24 Archive leaderboard report
Node Classification Coauthor CS CoLinkDistMLP Accuracy 95.74% #7 of 24 Archive leaderboard report
Node Classification Coauthor CS LinkDistMLP Accuracy 95.68% #9 of 24 Archive leaderboard report
Node Classification Coauthor CS LinkDist Accuracy 95.66% #11 of 24 Archive leaderboard report
Node Classification Coauthor Physics CoLinkDist Accuracy 97.05% #5 of 14 Archive leaderboard report
Node Classification Coauthor Physics LinkDistMLP Accuracy 96.91% #8 of 14 Archive leaderboard report
Node Classification Coauthor Physics CoLinkDistMLP Accuracy 96.87% #10 of 14 Archive leaderboard report
Node Classification Coauthor Physics LinkDist Accuracy 96.87% #11 of 14 Archive leaderboard report
Node Classification Cora LinkDist Accuracy 88.24% #10 of 73 Archive leaderboard report
Node Classification Cora CoLinkDist Accuracy 87.89% #12 of 73 Archive leaderboard report
Node Classification Cora LinkDistMLP Accuracy 87.58% #14 of 73 Archive leaderboard report
Node Classification Cora CoLinkDistMLP Accuracy 87.54% #15 of 73 Archive leaderboard report
Node Classification Cora Full CoLinkDist Accuracy 70.32% #2 of 5 Archive leaderboard report
Node Classification Cora Full LinkDist Accuracy 69.87% #3 of 5 Archive leaderboard report
Node Classification Cora Full CoLinkDistMLP Accuracy 69.83% #4 of 5 Archive leaderboard report
Node Classification Cora Full LinkDistMLP Accuracy 69.53% #5 of 5 Archive leaderboard report
Node Classification Cora Full with Public Split CoLinkDist Accuracy 57.05% #1 of 4 Archive leaderboard report
Node Classification Cora Full with Public Split LinkDist Accuracy 55.87% #2 of 4 Archive leaderboard report
Node Classification Cora Full with Public Split CoLinkDistMLP Accuracy 53.43% #3 of 4 Archive leaderboard report
Node Classification Cora Full with Public Split LinkDistMLP Accuracy 51.78% #4 of 4 Archive leaderboard report
Node Classification Cora with Public Split: fixed 20 nodes per class CoLinkDist Accuracy 81.39% #26 of 36 Archive leaderboard report
Node Classification Cora with Public Split: fixed 20 nodes per class CoLinkDistMLP Accuracy 81.19% #27 of 36 Archive leaderboard report
Node Classification Cora with Public Split: fixed 20 nodes per class LinkDist Accuracy 81.05% #28 of 36 Archive leaderboard report
Node Classification Cora with Public Split: fixed 20 nodes per class LinkDistMLP Accuracy 80.79% #29 of 36 Archive leaderboard report
Node Classification PubMed with Public Split: fixed 20 nodes per class CoLinkDist Accuracy 75.64% #33 of 37 Archive leaderboard report
Node Classification PubMed with Public Split: fixed 20 nodes per class CoLinkDistMLP Accuracy 75.41% #34 of 37 Archive leaderboard report
Node Classification PubMed with Public Split: fixed 20 nodes per class LinkDist Accuracy 74.06% #35 of 37 Archive leaderboard report
Node Classification PubMed with Public Split: fixed 20 nodes per class LinkDistMLP Accuracy 72.41% #36 of 37 Archive leaderboard report
Node Classification Pubmed CoLinkDist Accuracy 89.58% #9 of 70 Archive leaderboard report
Node Classification Pubmed CoLinkDistMLP Accuracy 89.53% #10 of 70 Archive leaderboard report
Node Classification Pubmed LinkDist Accuracy 88.86% #14 of 70 Archive leaderboard report
Node Classification Pubmed LinkDistMLP Accuracy 88.79% #15 of 70 Archive leaderboard report
Node Property Prediction ogbn-arxiv CoLinkDistMLP Ext. data No #83 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv CoLinkDistMLP Number of params 120912 #83 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv CoLinkDistMLP Test Accuracy 0.5638 ± 0.0016 #83 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv CoLinkDistMLP Validation Accuracy 0.5807 ± 0.0011 #83 of 86 Archive leaderboard report
Node Property Prediction ogbn-mag CoLinkDistMLP Ext. data No #38 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag CoLinkDistMLP Number of params 278202 #38 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag CoLinkDistMLP Test Accuracy 0.2761 ± 0.0018 #38 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag CoLinkDistMLP Validation Accuracy 0.2646 ± 0.0013 #38 of 39 Archive leaderboard report
Node Property Prediction ogbn-products CoLinkDistMLP Ext. data No #62 of 64 Archive leaderboard report
Node Property Prediction ogbn-products CoLinkDistMLP Number of params 115806 #62 of 64 Archive leaderboard report
Node Property Prediction ogbn-products CoLinkDistMLP Test Accuracy 0.6259 ± 0.0010 #62 of 64 Archive leaderboard report
Node Property Prediction ogbn-products CoLinkDistMLP Validation Accuracy 0.7721 ± 0.0015 #62 of 64 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