# Mitigating Pooling Bias in E-commerce Search via False Negative Estimation

arXiv: https://arxiv.org/abs/2311.06444 · HTML: https://mlsanity.com/paper/2311.06444/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 36 references that are in the map.
- First posted on arXiv 11 Nov 2023.

## Builds on (most cited first, 24 of 24)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [Passage Re-ranking with BERT](https://mlsanity.com/paper/1901.04085/) (2019)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2010.08191/) (2020)
- [Hard Negative Mixing for Contrastive Learning](https://mlsanity.com/paper/2010.01028/) (2020)
- [Deep & Cross Network for Ad Click Predictions](https://mlsanity.com/paper/1708.05123/) (2017)
- [Optimizing Dense Retrieval Model Training with Hard Negatives](https://mlsanity.com/paper/2104.08051/) (2021)
- [Boosting Contrastive Self-Supervised Learning with False Negative Cancellation](https://mlsanity.com/paper/2011.11765/) (2020)
- [Adversarial Retriever-Ranker for dense text retrieval](https://mlsanity.com/paper/2110.03611/) (2021)
- [Distilling Dense Representations for Ranking using Tightly-Coupled Teachers](https://mlsanity.com/paper/2010.11386/) (2020)
- [ERNIE-Search: Bridging Cross-Encoder with Dual-Encoder via Self On-the-fly Distillation for Dense Passage Retrieval](https://mlsanity.com/paper/2205.09153/) (2022)
- [Curriculum Learning for Dense Retrieval Distillation](https://mlsanity.com/paper/2204.13679/) (2022)
- [Shallow pooling for sparse labels](https://mlsanity.com/paper/2109.00062/) (2021)
- [Hard Negative Sampling Strategies for Contrastive Representation Learning](https://mlsanity.com/paper/2206.01197/) (2022)
- [From Intrinsic to Counterfactual: On the Explainability of Contextualized Recommender Systems](https://mlsanity.com/paper/2110.14844/) (2021)
- [False: False Negative Samples Aware Contrastive Learning for Semantic Segmentation of High-Resolution Remote Sensing Image](https://mlsanity.com/paper/2211.07928/) (2022)
- [Improving Bi-encoder Document Ranking Models with Two Rankers and Multi-teacher Distillation](https://mlsanity.com/paper/2103.06523/) (2021)
- [Hard Negatives or False Negatives: Correcting Pooling Bias in Training Neural Ranking Models](https://mlsanity.com/paper/2209.05072/) (2022)
- [An Embedding-Based Grocery Search Model at Instacart](https://mlsanity.com/paper/2209.05555/) (2022)
- [Active Sampling for Large-scale Information Retrieval Evaluation](https://mlsanity.com/paper/1709.01709/) (2017)

## Abstract (arXiv)

Efficient and accurate product relevance assessment is critical for user experiences and business success. Training a proficient relevance assessment model requires high-quality query-product pairs, often obtained through negative sampling strategies. Unfortunately, current methods introduce pooling bias by mistakenly sampling false negatives, diminishing performance and business impact. To address this, we present Bias-mitigating Hard Negative Sampling (BHNS), a novel negative sampling strategy tailored to identify and adjust for false negatives, building upon our original False Negative Estimation algorithm. Our experiments in the Instacart search setting confirm BHNS as effective for practical e-commerce use. Furthermore, comparative analyses on public dataset showcase its domain-agnostic potential for diverse applications.