4.7 Article

Ranking-Based Implicit Regularization for One-Class Collaborative Filtering

Journal

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
Volume 34, Issue 12, Pages 5951-5963

Publisher

IEEE COMPUTER SOC
DOI: 10.1109/TKDE.2021.3069057

Keywords

Optimization; Recommender systems; Collaboration; Time complexity; Computer science; Task analysis; Stochastic processes; One-class collaborative filtering; implicit regularization; item recommendation; coordinate descent; alternating least square

Funding

  1. National Natural Science Foundation of China [61976198, 62022077, 61972069, 61836007, 61832017]
  2. Fundamental Research Funds for the Central Universities
  3. Sichuan Science and Technology Program [2020JDTD0007]

Ask authors/readers for more resources

One-class collaborative filtering (OCCF) problems are common in recommendation systems, but suffer from data sparsity and lack of negative items. To address these challenges, a ranking-based implicit regularizer is proposed and used in a framework to improve recommendation quality. Efficient algorithms are developed to optimize model parameters and extensive evaluations are conducted on multiple datasets.
One-class collaborative filtering (OCCF) problems are ubiquitous in real-world recommendation systems, such as news recommendation, but suffer from data sparsity and lack of negative items. To address the challenge, the state-of-the-art algorithm assigns uninteracted items with smaller weights of being negative and performs low-rank approximation over the user-item interaction matrix. However, the prior ratings are usually suggested to be zero but may not be well-defined. To avert the direct utilization of prior ratings for uninteracted items, we propose a novel ranking-based implicit regularizer by hypothesizing that users' preference scores for uninteracted items should not deviate a lot from each other. The regularizer is then used in a ranking-based OCCF framework to penalize large differences of preference scores between uninteracted items. To efficiently optimize model parameters in this framework, we develop the scalable alternating least square algorithm and coordinate descent algorithm, whose time complexity is linearly proportional to the data size. Finally, we extensively evaluate the proposed algorithms on six public real-world datasets. The results show that the proposed regularizer significantly improves the recommendation quality of ranking-based OCCF algorithms, such as BPRMF and RankALS. Moreover, the ranking-based framework with the proposed regularizer outperforms the state-of-the-art recommendation algorithms for implicit feedback.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available