Trisampler: A Better Negative Sampling Principle For Dense Retrieval

Abstract

Negative sampling stands as a pivotal technique in dense retrieval, essential for training effective retrieval models and significantly impacting retrieval performance. While existing negative sampling methods have made commendable progress by leveraging hard negatives, a comprehensive guiding principle for constructing negative candidates and designing negative sampling distributions is still lacking. To bridge this gap, we embark on a theoretical analysis of negative sampling in dense retrieval. This exploration culminates in the unveiling of the quasi-triangular principle, a novel framework that elucidates the triangular-like interplay between query, positive document, and negative document. Fueled by this guiding principle, we introduce TriSampler, a straightforward yet highly effective negative sampling method. The keypoint of TriSampler lies in its ability to selectively sample more informative negatives within a prescribed constrained region. Experimental evaluation show that Tr

Stats

• citations5
• S2 citations—
• github stars0
• HF likes0
• heat score5.84
• arxiv keyyang2024trisampler

Related papers

• Optimizing Dense Retrieval Model Training With Hard Negatives (2021)16.34
• ESANS: Effective And Semantic-aware Negative Sampling For Large-scale Retrieval Systems (2025)2.26
• Syneg: Llm-driven Synthetic Hard-negatives For Dense Retrieval (2024)0.00
• Learning To Retrieve: How To Train A Dense Retrieval Model Effectively And Efficiently (2020)0.00
• Negative Sample Is Negative In Its Own Way: Tailoring Negative Sentences For Image-text Retrieval (2021)3.81
• From Distillation To Hard Negative Sampling: Making Sparse Neural IR Models More Effective (2022)0.00
• RRRA: Resampling And Reranking Through A Retriever Adapter (2025)0.00
• Efficiently Teaching An Effective Dense Retriever With Balanced Topic Aware Sampling (2021)17.07