Self-Supervised Reinforcement Learning for Recommender Systems
Authors:
Top Cited Papers
Open Access
- 25 July 2020
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 931-940
Abstract
In session-based or sequential recommendation, it is important to consider a number of factors like long-term user engagement, multiple types of user-item interactions such as clicks, purchases etc. The current state-of-the-art supervised approaches fail to model them appropriately. Casting sequential recommendation task as a reinforcement learning (RL) problem is a promising direction. A major component of RL approaches is to train the agent through interactions with the environment. However, it is often problematic to train a recommender in an on-line fashion due to the requirement to expose users to irrelevant recommendations. As a result, learning the policy from logged implicit feedback is of vital importance, which is challenging due to the pure off-policy setting and lack of negative rewards (feedback). In this paper, we propose self-supervised reinforcement learning for sequential recommendation tasks. Our approach augments standard recommendation models with two output layers: one for self-supervised learning and the other for RL. The RL part acts as a regularizer to drive the supervised layer focusing on specific rewards (e.g., recommending items which may lead to purchases rather than clicks) while the self-supervised layer with cross-entropy loss provides strong gradient signals for parameter updates. Based on such an approach, we propose two frameworks namely Self-Supervised Q-learning (SQN) and Self-Supervised Actor-Critic (SAC). We integrate the proposed frameworks with four state-of-the-art recommendation models. Experimental results on two real-world datasets demonstrate the effectiveness of our approach.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- Fusing Similarity Models with Markov Chains for Sparse Sequential Recommendation2016
- Vista2016
- Mastering the game of Go with deep neural networks and tree searchNature, 2016
- General factorization framework for context-aware recommendationsData Mining and Knowledge Discovery, 2015
- Unbiased offline evaluation of contextual-bandit-based news article recommendation algorithms2011
- Factorization Machines2010
- A contextual-bandit approach to personalized news article recommendation2010
- Factorizing personalized Markov chains for next-basket recommendation2010
- Matrix Factorization Techniques for Recommender SystemsComputer, 2009
- Simple statistical gradient-following algorithms for connectionist reinforcement learningMachine Learning, 1992