Set2setRank: Collaborative Set to Set Ranking for Implicit Feedback based Recommendation

TL;DR

Set2setRank introduces a novel, model-agnostic framework for implicit feedback recommendation that improves ranking by comparing items and sets, effectively addressing data sparsity issues.

Contribution

The paper proposes a new set-to-set ranking framework for implicit feedback recommendation, incorporating item-to-set and set-to-set comparisons with adaptive sampling, applicable to various models.

Findings

Outperforms existing methods on three real-world datasets.

Effective in handling sparse implicit feedback data.

Time-efficient and easily integrable with different models.

Abstract

As users often express their preferences with binary behavior data~(implicit feedback), such as clicking items or buying products, implicit feedback based Collaborative Filtering~(CF) models predict the top ranked items a user might like by leveraging implicit user-item interaction data. For each user, the implicit feedback is divided into two sets: an observed item set with limited observed behaviors, and a large unobserved item set that is mixed with negative item behaviors and unknown behaviors. Given any user preference prediction model, researchers either designed ranking based optimization goals or relied on negative item mining techniques for better optimization. Despite the performance gain of these implicit feedback based models, the recommendation results are still far from satisfactory due to the sparsity of the observed item set for each user. To this end, in this paper, we explore the unique characteristics of the implicit feedback and propose Set2setRank framework for recommendation. The optimization criteria of Set2setRank are two folds: First, we design an item to an item set comparison that encourages each observed item from the sampled observed set is ranked higher than any unobserved item from the sampled unobserved set. Second, we model set level comparison that encourages a margin between the distance summarized from the observed item set and the most "hard" unobserved item from the sampled negative set. Further, an adaptive sampling technique is designed to implement these two goals. We have to note that our proposed framework is model-agnostic and can be easily applied to most recommendation prediction approaches, and is time efficient in practice. Finally, extensive experiments on three real-world datasets demonstrate the superiority of our proposed approach.