# Improving Collaborative Metric Learning with Efficient Negative Sampling

arXiv: https://arxiv.org/abs/1909.10912 · HTML: https://mlsanity.com/paper/1909.10912/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Sep 2019.

## Built on by (most cited first, 11 of 11)

- [ConvFiT: Conversational Fine-Tuning of Pretrained Language Models](https://mlsanity.com/paper/2109.10126/) (2021)
- [Does Negative Sampling Matter? A Review with Insights into its Theory and Applications](https://mlsanity.com/paper/2402.17238/) (2024)
- [Rethinking Collaborative Metric Learning: Toward an Efficient Alternative without Negative Sampling](https://mlsanity.com/paper/2206.11549/) (2022)
- [The Minority Matters: A Diversity-Promoting Collaborative Metric Learning Algorithm](https://mlsanity.com/paper/2209.15292/) (2022)
- [Improved Diversity-Promoting Collaborative Metric Learning for Recommendation](https://mlsanity.com/paper/2409.01012/) (2024)
- [Exploring the Algorithm-Dependent Generalization of AUPRC Optimization with List Stability](https://mlsanity.com/paper/2209.13262/) (2022)
- [Hierarchical Latent Relation Modeling for Collaborative Metric Learning](https://mlsanity.com/paper/2108.04655/) (2021)
- [Dynamic Slate Recommendation with Gated Recurrent Units and Thompson Sampling](https://mlsanity.com/paper/2104.15046/) (2021)
- [Semantically-Conditioned Negative Samples for Efficient Contrastive Learning](https://mlsanity.com/paper/2102.06603/) (2021)
- [Transformers Meet ACT-R: Repeat-Aware and Sequential Listening Session Recommendation](https://mlsanity.com/paper/2408.16578/) (2024)
- [Proxy-based Item Representation for Attribute and Context-aware Recommendation](https://mlsanity.com/paper/2312.06145/) (2023)

## Abstract (arXiv)

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.