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 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="2009.13603")

Code

Syntology Ran 3 of 9 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 3 ran · our draft was wrong.

By repository: official repository: 9 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

cambridgeltl/eva officialmentioned on GitHubpytorchMIT report
sayands/sgaligner 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

9 samples harvested; 3 ran; 0 honoured the contract we drafted; 6 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.

3ran · our draft was wrong
6unverified

Licence: 0 of the 9 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 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. “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.

cosine_sim cambridgeltl/eva/src/models.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 9b0a787b92a87023 · report
normalize_adj cambridgeltl/eva/src/utils.py official repository ran · our draft was wrong MIT (permissive) · d45f434d25f2e870 · report
normalize_features cambridgeltl/eva/src/utils.py official repository ran · our draft was wrong MIT (permissive) · 39cba20da9f36113 · report
attention cambridgeltl/eva/src/models.py official repository unverified MIT (permissive) · bebe16d3aeca99f3 · report
get_ent2id cambridgeltl/eva/src/Load.py official repository unverified MIT (permissive) · bebaa42d5e2dcdf3 · report
get_ids cambridgeltl/eva/src/Load.py official repository unverified MIT (permissive) · 7c1bdadfedbe321c · report
l2norm cambridgeltl/eva/src/models.py official repository unverified MIT (permissive) · 433bcbe46a942d69 · report
loadfile cambridgeltl/eva/src/Load.py official repository unverified MIT (permissive) · 4564d89c4036e373 · report
sparse_mx_to_torch_sparse_tensor cambridgeltl/eva/src/utils.py official repository unverified MIT (permissive) · edf110cbd4fe5ec5 · 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