Papers › Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones

Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones

28 Oct 2021NeurIPS 2021 12arXiv:2110.14923archive 2025-07-28

Yushi Bai, Rex Ying, Hongyu Ren, Jure Leskovec

Hierarchical relations are prevalent and indispensable for organizing human knowledge captured by a knowledge graph (KG). The key property of hierarchical relations is that they induce a partial ordering over the entities, which needs to be modeled in order to allow for hierarchical reasoning. However, current KG embeddings can model only a single global hierarchy (single global partial ordering) and fail to model multiple heterogeneous hierarchies that exist in a single KG. Here we present ConE (Cone Embedding), a KG embedding model that is able to simultaneously model multiple hierarchical as well as non-hierarchical relations in a knowledge graph. ConE embeds entities into hyperbolic cones and models relations as transformations between the cones. In particular, ConE uses cone containment constraints in different subspaces of the hyperbolic embedding space to capture multiple heterogeneous hierarchies. Experiments on standard knowledge graph benchmarks show that ConE obtains state-of-the-art performance on hierarchical reasoning tasks as well as knowledge graph completion task on hierarchical graphs. In particular, our approach yields new state-of-the-art Hits@1 of 45.3% on WN18RR and 16.1% on DDB14 (0.231 MRR). As for hierarchical reasoning task, our approach outperforms previous best results by an average of 20% across the three datasets.

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="2110.14923")

Code

Syntology Ran 2 of 2 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 2 ran with no contract checked.

By repository: official repository: 2 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

snap-stanford/ConE officialmentioned 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

2 samples harvested; 2 ran; 0 honoured the contract we drafted; 0 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.

2ran

Licence: 0 of the 2 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 snap-stanford/ConE. “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.

EnergyFunction snap-stanford/ConE/codes/utils/energy_function.py official repository ran · metamorphic tier: deterministic MIT (permissive) · cf120f6a24cc78a6 · report
EntailmentConeEnergyFunction snap-stanford/ConE/codes/utils/energy_function.py official repository ran · metamorphic tier: deterministic MIT (permissive) · d6bdad4b6beebc35 · report

Tasks

Ancestor-descendant predictionKnowledge Graph CompletionLink Prediction

1 archive task tag without a task page not shown.

Datasets

Introduced by this paper, per the archive.

GO21

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Ancestor-descendant prediction WN18RR ConE mAP-0% 0.895 #1 of 1 Archive leaderboard report
Ancestor-descendant prediction WN18RR ConE mAP-100% 0.679 #1 of 1 Archive leaderboard report
Ancestor-descendant prediction WN18RR ConE mAP-50% 0.801 #1 of 1 Archive leaderboard report
Link Prediction DDB14 ConE Hits@1 0.161 #1 of 1 Archive leaderboard report
Link Prediction DDB14 ConE Hits@10 0.364 #1 of 1 Archive leaderboard report
Link Prediction DDB14 ConE Hits@3 0.252 #1 of 1 Archive leaderboard report
Link Prediction DDB14 ConE MRR 0.231 #1 of 1 Archive leaderboard report
Link Prediction FB15k-237 ConE Hits@1 0.247 #40 of 75 Archive leaderboard report
Link Prediction FB15k-237 ConE Hits@10 0.54 #40 of 75 Archive leaderboard report
Link Prediction FB15k-237 ConE Hits@3 0.381 #40 of 75 Archive leaderboard report
Link Prediction FB15k-237 ConE MRR 0.345 #40 of 75 Archive leaderboard report
Link Prediction GO21 ConE Hit@1 0.14 #1 of 1 Archive leaderboard report
Link Prediction GO21 ConE Hits@10 0.347 #1 of 1 Archive leaderboard report
Link Prediction GO21 ConE Hits@3 0.237 #1 of 1 Archive leaderboard report
Link Prediction GO21 ConE MRR 0.211 #1 of 1 Archive leaderboard report
Link Prediction WN18RR ConE Hits@1 0.453 #26 of 75 Archive leaderboard report
Link Prediction WN18RR ConE Hits@10 0.579 #26 of 75 Archive leaderboard report
Link Prediction WN18RR ConE Hits@3 0.515 #26 of 75 Archive leaderboard report
Link Prediction WN18RR ConE MRR 0.496 #26 of 75 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