mlsanityData to 14 Oct 2026

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

arXiv 2311.06444 ↗First posted 11 Nov 2023cs.IR cs.LGcited by 0

Not on the map. Why?

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.

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

24 of 36 references.

References · 24

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  3. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
  4. 2017Neural Collaborative Filteringcited by 1,111
  5. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 849
  6. 2019Passage Re-ranking with BERTcited by 645
  7. 2020Contrastive Learning with Hard Negative Samplescited by 628
  8. 2020RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answeringcited by 413
  9. 2020Hard Negative Mixing for Contrastive Learningcited by 402
  10. 2017Deep & Cross Network for Ad Click Predictionscited by 393
  11. 2021Optimizing Dense Retrieval Model Training with Hard Negativescited by 155
  12. 2020Boosting Contrastive Self-Supervised Learning with False Negative Cancellationcited by 119
12 more
  1. 2021Adversarial Retriever-Ranker for dense text retrievalcited by 83
  2. 2020Distilling Dense Representations for Ranking using Tightly-Coupled Teacherscited by 52
  3. 2022ERNIE-Search: Bridging Cross-Encoder with Dual-Encoder via Self On-the-fly Distillation for Dense Passage Retrievalcited by 41
  4. 2022Curriculum Learning for Dense Retrieval Distillationcited by 38
  5. 2021Shallow pooling for sparse labelscited by 13
  6. 2022Hard Negative Sampling Strategies for Contrastive Representation Learningcited by 13
  7. 2021From Intrinsic to Counterfactual: On the Explainability of Contextualized Recommender Systemscited by 9
  8. 2022False: False Negative Samples Aware Contrastive Learning for Semantic Segmentation of High-Resolution Remote Sensing Imagecited by 8
  9. 2021Improving Bi-encoder Document Ranking Models with Two Rankers and Multi-teacher Distillationcited by 7
  10. 2022Hard Negatives or False Negatives: Correcting Pooling Bias in Training Neural Ranking Modelscited by 6
  11. 2022An Embedding-Based Grocery Search Model at Instacartcited by 5
  12. 2017Active Sampling for Large-scale Information Retrieval Evaluationcited by 3

Built on by

Not cited yet.