Bayesian Negative Sampling for Recommendation
This work addresses a specific bottleneck in recommendation systems by providing an unbiased negative sampling method, which is incremental as it builds on existing approaches to enhance training efficiency.
The paper tackled the problem of sampling high-quality negative instances for training implicit collaborative filtering and contrastive learning models by discriminating false negatives from true negatives, resulting in improved sampling quality and recommendation performance as validated in experiments.
How to sample high quality negative instances from unlabeled data, i.e., negative sampling, is important for training implicit collaborative filtering and contrastive learning models. Although previous studies have proposed some approaches to sample informative instances, few has been done to discriminating false negative from true negative for unbiased negative sampling. On the basis of our order relation analysis of negatives' scores, we first derive the class conditional density of true negatives and that of false negatives. We next design a Bayesian classifier for negative classification, from which we define a model-agnostic posterior probability estimate of an instance being true negative as a quantitative negative signal measure. We also propose a Bayesian optimal sampling rule to sample high-quality negatives. The proposed Bayesian Negative Sampling (BNS) algorithm has a linear time complexity. Experimental studies validate the superiority of BNS over the peers in terms of better sampling quality and better recommendation performance.