Alpha-Beta Sampling for Pairwise Ranking in One-Class Collaborative Filtering

This paper introduces Alpha-Beta Sampling (ABS) strategy, which is particularly intended for the sampling problem of pairwise ranking in one-class collaborative filtering (PROCCF). Specifically, ABS strategy places more emphasis on such training examples, including positive item with a lower preference score and negative items with a higher preference score for each gradient step. Then, we provide the corresponding proofs for the ABS strategy from both gradient and ranking perspectives. First, we prove that sampled training examples by ABS strategy can update the model parameters with a large magnitude and analyze two instantiations by combining two specific pairwise algorithms. Second, it can be proved that ABS strategy is equivalent to optimizing for ranking-aware evaluation metrics like Normalized Discounted Cumulative Gain (NDCG). Furthermore, ABS strategy can be very general and applicable in a lot of pairwise structures of pairwise algorithms. Based on ABS strategy, we provide an effective sampling algorithm to dynamically draw items for each SGD update. Finally, we evaluate the ABS strategy by conducting sampling tasks in two representative pairwise algorithms. The experiment results show that the ABS strategy performs significantly better than the baseline strategies.