Reinforcement Learning-enhanced Shared-account Cross-domain Sequential Recommendation

TL;DR

This paper introduces RL-ISN, a reinforcement learning-based method for shared-account cross-domain sequential recommendation, focusing on user-specific account representation and domain filtering to improve recommendation accuracy.

Contribution

The paper proposes a novel RL-based framework that models user-specific account behaviors and employs hierarchical reinforcement learning for effective domain filtering in SCSR.

Findings

RL-ISN outperforms state-of-the-art methods on real-world datasets.

The hierarchical RL domain filter effectively reduces irrelevant domain influence.

User-specific account modeling improves recommendation precision.

Abstract

Shared-account Cross-domain Sequential Recommendation (SCSR) is an emerging yet challenging task that simultaneously considers the shared-account and cross-domain characteristics in the sequential recommendation. Existing works on SCSR are mainly based on Recurrent Neural Network (RNN) and Graph Neural Network (GNN) but they ignore the fact that although multiple users share a single account, it is mainly occupied by one user at a time. This observation motivates us to learn a more accurate user-specific account representation by attentively focusing on its recent behaviors. Furthermore, though existing works endow lower weights to irrelevant interactions, they may still dilute the domain information and impede the cross-domain recommendation. To address the above issues, we propose a reinforcement learning-based solution, namely RL-ISN, which consists of a basic cross-domain recommender and a reinforcement learning-based domain filter. Specifically, to model the account representation in the shared-account scenario, the basic recommender first clusters users' mixed behaviors as latent users, and then leverages an attention model over them to conduct user identification. To reduce the impact of irrelevant domain information, we formulate the domain filter as a hierarchical reinforcement learning task, where a high-level task is utilized to decide whether to revise the whole transferred sequence or not, and if it does, a low-level task is further performed to determine whether to remove each interaction within it or not. To evaluate the performance of our solution, we conduct extensive experiments on two real-world datasets, and the experimental results demonstrate the superiority of our RL-ISN method compared with the state-of-the-art recommendation methods.