Papers › NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphs

NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphs

23 Jun 2021ICLR 2022 4arXiv:2106.12144archive 2025-07-28

Mikhail Galkin, Etienne Denis, Jiapeng Wu, William L. Hamilton

Conventional representation learning algorithms for knowledge graphs (KG) map each entity to a unique embedding vector. Such a shallow lookup results in a linear growth of memory consumption for storing the embedding matrix and incurs high computational costs when working with real-world KGs. Drawing parallels with subword tokenization commonly used in NLP, we explore the landscape of more parameter-efficient node embedding strategies with possibly sublinear memory requirements. To this end, we propose NodePiece, an anchor-based approach to learn a fixed-size entity vocabulary. In NodePiece, a vocabulary of subword/sub-entity units is constructed from anchor nodes in a graph with known relation types. Given such a fixed-size vocabulary, it is possible to bootstrap an encoding and embedding for any entity, including those unseen during training. Experiments show that NodePiece performs competitively in node classification, link prediction, and relation prediction tasks while retaining less than 10% of explicit nodes in a graph as anchors and often having 10x fewer parameters. To this end, we show that a NodePiece-enabled model outperforms existing shallow models on a large OGB WikiKG 2 graph having 70x fewer parameters.

PaperPDFConference PDFCodeCode 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="2106.12144")

Code

Syntology Ran 0 of 7 code samples harvested from 2 repositories linked to this paper; 7 have no recorded run.

By repository: official repository: 1 sample from 1 repository, 0 ran; community (archive-listed): 6 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.

migalkin/NodePiece officialmentioned in papermentioned on GitHubpytorch report
AutoML-Research/KGBench mentioned on GitHubpytorchMIT report
migalkin/NodePiece mentioned on GitHubpytorch report
pykeen/ilpc2022 mentioned on GitHubpytorchMIT 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

7 samples harvested; 0 ran; 0 honoured the contract we drafted; 7 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.

7unverified

Licence: 0 of the 7 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

parse_args migalkin/NodePiece/ogb/run_ogb.py official repository unverified MIT (permissive) · f7fbea47d530863f · report
index_KvsAll AutoML-Research/KGBench/kgbench/indexing.py community (archive-listed) unverified MIT (permissive) · 79e8c86b8cbf34bf · report
index_relation_types AutoML-Research/KGBench/kgbench/indexing.py community (archive-listed) unverified MIT (permissive) · 8de5ea6adbb76af2 · report
index_relations_per_type AutoML-Research/KGBench/kgbench/indexing.py community (archive-listed) unverified MIT (permissive) · 016f6033e3fdf5c1 · report
init_from AutoML-Research/KGBench/kgbench/misc.py community (archive-listed) unverified MIT (permissive) · c04bd04c3945c863 · report
is_number AutoML-Research/KGBench/kgbench/misc.py community (archive-listed) unverified MIT (permissive) · 3087bb1d9186ca95 · report
which AutoML-Research/KGBench/kgbench/misc.py community (archive-listed) unverified MIT (permissive) · 5ebd841a3319a390 · report

Tasks

Knowledge GraphsLink PredictionNode ClassificationRelation PredictionRepresentation Learning

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Link Property Prediction ogbl-wikikg2 NodePiece + AutoSF Ext. data No #18 of 30 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 NodePiece + AutoSF Number of params 6860602 #18 of 30 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 NodePiece + AutoSF Test MRR 0.5703 ± 0.0035 #18 of 30 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 NodePiece + AutoSF Validation MRR 0.5806 ± 0.0047 #18 of 30 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