Evidence Before Sampling: Interpretable Implicit Negative Candidate Discovery for Recommendation

Key points

• Since deep learning models require negative signals for training, negative sampling methods typically treat selected unobserved interactions as negatives.1
• We formulate implicit negative candidate discovery to identify unobserved interactions supported by observed customer behavior.1
• Our results show that negative candidate validity can be evaluated separately from downstream recommendation performance.1
• This distinction enables evidence-based, business-aligned, and explainable negative selection, improving both interpretability and model training in sparse, skewed, real-world recommendation settings.1

Sources (1)

• [1]Evidence Before Sampling: Interpretable Implicit Negative Candidate Discovery for Recommendation
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 04:02 AM

  Recommender systems learn from observed user-item interactions, but explicit negative feedback is often unavailable.

  Since deep learning models require negative signals for training, negative sampling methods typically treat selected unobserved interactions as negatives.

Extractive summary: sentences quoted from the sources.