Papers › Improving Collaborative Metric Learning with Efficient Negative Sampling

Improving Collaborative Metric Learning with Efficient Negative Sampling

24 Sep 2019arXiv:1909.10912archive 2025-07-28

Viet-Anh Tran, Romain Hennequin, Jimena Royo-Letelier, Manuel Moussallam

Distance metric learning based on triplet loss has been applied with success in a wide range of applications such as face recognition, image retrieval, speaker change detection and recently recommendation with the CML model. However, as we show in this article, CML requires large batches to work reasonably well because of a too simplistic uniform negative sampling strategy for selecting triplets. Due to memory limitations, this makes it difficult to scale in high-dimensional scenarios. To alleviate this problem, we propose here a 2-stage negative sampling strategy which finds triplets that are highly informative for learning. Our strategy allows CML to work effectively in terms of accuracy and popularity bias, even when the batch size is an order of magnitude smaller than what would be needed with the default uniform sampling. We demonstrate the suitability of the proposed strategy for recommendation and exhibit consistent positive results across various datasets.

PaperPDFCode

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

Code

deezer/sigir2019-2stagesampling officialmentioned in papertf 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

Change DetectionFace RecognitionImage RetrievalMetric LearningRetrieval

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Triplet Loss

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