Papers › Improving zero-shot learning by mitigating the hubness problem

Improving zero-shot learning by mitigating the hubness problem

20 Dec 2014arXiv:1412.6568archive 2025-07-28

Georgiana Dinu, Angeliki Lazaridou, Marco Baroni

The zero-shot paradigm exploits vector-based word representations extracted from text corpora with unsupervised methods to learn general mapping functions from other feature spaces onto word space, where the words associated to the nearest neighbours of the mapped vectors are used as their linguistic labels. We show that the neighbourhoods of the mapped elements are strongly polluted by hubs, vectors that tend to be near a high proportion of items, pushing their correct labels down the neighbour list. After illustrating the problem empirically, we propose a simple method to correct it by taking the proximity distribution of potential neighbours across many mapped vectors into account. We show that this correction leads to consistent improvements in realistic zero-shot experiments in the cross-lingual, image labeling and image retrieval domains.

PaperPDFCode

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

Code

Babylonpartners/fastText_multilingual mentioned on GitHubBSD-3-Clause report
babylonhealth/fastText_multilingual mentioned on GitHubBSD-3-Clause report
facebookresearch/MUSE mentioned on GitHubpytorch report
jiajunhua/facebookresearch-MUSE mentioned on GitHubpytorchNOASSERTION report
ssharoff/cognates mentioned on GitHubGPL-3.0 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image RetrievalRetrievalZero-Shot Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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