Papers › Visual Pivoting for (Unsupervised) Entity Alignment

Visual Pivoting for (Unsupervised) Entity Alignment

28 Sep 2020arXiv:2009.13603archive 2025-07-28

Fangyu Liu, Muhao Chen, Dan Roth, Nigel Collier

This work studies the use of visual semantic representations to align entities in heterogeneous knowledge graphs (KGs). Images are natural components of many existing KGs. By combining visual knowledge with other auxiliary information, we show that the proposed new approach, EVA, creates a holistic entity representation that provides strong signals for cross-graph entity alignment. Besides, previous entity alignment methods require human labelled seed alignment, restricting availability. EVA provides a completely unsupervised solution by leveraging the visual similarity of entities to create an initial seed dictionary (visual pivots). Experiments on benchmark data sets DBP15k and DWY15k show that EVA offers state-of-the-art performance on both monolingual and cross-lingual entity alignment tasks. Furthermore, we discover that images are particularly useful to align long-tail KG entities, which inherently lack the structural contexts necessary for capturing the correspondences.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 9 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 1 repository, 6 ran (3 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 6 samples that ran has no recorded date.

cambridgeltl/eva officialmentioned on GitHubpytorchMITSyntology: 9 samples, 6 ran (3 instrument-failed) · 3 unverified report
sayands/sgaligner mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SGAligner : 3D Scene Alignment with Scene Graphs (arXiv:2304.14880; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

9 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
3ran
3unverified

Licence: 3 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from cambridgeltl/eva. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

cambridgeltl/eva official repository 9 samples, 6 ran (3 instrument-failed) · 3 unverified
cosine_sim in 34 papers src/models.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 9b0a787b92a87023 · report fixture: signature im:Tensor/2/float, s:Tensor/2/float · returned Tensor · level recorded 2026-09-22
l2norm in 84 papers
census: 12 implementations from 20 papers, 3 distinct outputs on one shared input
src/models.py ran fingerprinted MIT (permissive) · 433bcbe46a942d69 · report fixture: signature X:Tensor/2/float · returned Tensor · level recorded 2026-09-25
loadfile in 5 papers src/Load.py ran MIT (permissive) · 4564d89c4036e373 · report fixture: signature fn:str/0/str, num:int/0/int · returned list · level recorded 2026-09-25
normalize_adj in 55 papers src/utils.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · d45f434d25f2e870 · report fixture: signature mx:csr_matrix/2/float · returned csc_matrix · level recorded, date not recorded
normalize_features in 20 papers src/utils.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 39cba20da9f36113 · report fixture: signature mx:csr_matrix/2/float · returned csr_matrix · level recorded 2026-09-22
sparse_mx_to_torch_sparse_tensor in 41 papers src/utils.py ran MIT (permissive) · edf110cbd4fe5ec5 · report fixture: signature sparse_mx:coo_matrix/2/float · returned Tensor · level recorded 2026-09-25
get_ent2id src/Load.py unverified MIT (permissive) · bebaa42d5e2dcdf3 · report
get_ids in 12 papers src/Load.py unverified MIT (permissive) · 7c1bdadfedbe321c · report

Tasks

Entity AlignmentKnowledge GraphsMulti-modal Entity Alignment

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Entity Alignment DBP15k zh-en EVA Hits@1 0.761 #16 of 38 Archive leaderboard report
Entity Alignment dbp15k fr-en EVA Hits@1 0.793 #13 of 14 Archive leaderboard report
Entity Alignment dbp15k ja-en EVA Hits@1 0.762 #13 of 14 Archive leaderboard report
Multi-modal Entity Alignment UMVM-dbp-fr-en EVA (w/o surf) Hits@1 0.765 #6 of 10 Archive leaderboard report
Multi-modal Entity Alignment UMVM-dbp-fr-en EVA (w/o surf & w/o iter) Hits@1 0.686 #8 of 10 Archive leaderboard report
Multi-modal Entity Alignment UMVM-dbp-ja-en EVA (w/o surf) Hits@1 0.741 #6 of 10 Archive leaderboard report
Multi-modal Entity Alignment UMVM-dbp-ja-en EVA (w/o surf & w/o iter) Hits@1 0.669 #8 of 10 Archive leaderboard report
Multi-modal Entity Alignment UMVM-dbp-zh-en EVA (w/o surf) Hits@1 0.750 #6 of 10 Archive leaderboard report
Multi-modal Entity Alignment UMVM-dbp-zh-en EVA (w/o surf & w/o iter) Hits@1 0.683 #8 of 10 Archive leaderboard report
Multi-modal Entity Alignment UMVM-oea-d-w-v1 EVA (w/o surf) Hits@1 0.915 #3 of 8 Archive leaderboard report
Multi-modal Entity Alignment UMVM-oea-d-w-v1 EVA (w/o surf & w/o iter) Hits@1 0.858 #6 of 8 Archive leaderboard report
Multi-modal Entity Alignment UMVM-oea-d-w-v2 EVA (w/o surf) Hits@1 0.925 #5 of 7 Archive leaderboard report
Multi-modal Entity Alignment UMVM-oea-d-w-v2 EVA (w/o surf & w/o iter) Hits@1 0.890 #6 of 7 Archive leaderboard report
Multi-modal Entity Alignment UMVM-oea-en-de EVA (w/o surf) Hits@1 0.956 #3 of 8 Archive leaderboard report
Multi-modal Entity Alignment UMVM-oea-en-de EVA (w/o surf & w/o iter) Hits@1 0.922 #6 of 8 Archive leaderboard report
Multi-modal Entity Alignment UMVM-oea-en-fr EVA (w/o surf) Hits@1 0.849 #3 of 8 Archive leaderboard report
Multi-modal Entity Alignment UMVM-oea-en-fr EVA (w/o surf & w/o iter) Hits@1 0.785 #6 of 8 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