Dynamic Multi-Objective Optimization Framework With Interactive Evolution for Sequential Recommendation

In contrast to traditional recommender systems which usually pay attention to users' general and long-term preferences, sequential recommendation (SR) can model users' dynamic intents based on their behaviour sequences and suggest the next item(s) to them. However, most of existing sequential models learn the ranking score of an item only based on its relevance property, and the personalized user demands in terms of different learning objectives, such as diversity, tail novelty or recency, which have been played essential roles in multi-objective recommendation (MOR), are often neglected in SR. In this paper, we first discuss the importance of considering multiple different objectives within a learning model for recommender system. Next, to capture users' objective-level preferences by utilizing interactive information in the sequential context, we propose a novel Dynamic Multi-objective Recommendation (DMORec) framework with interactive evolution for SR. In particular, DMORec formulates a dynamic multi-objective optimization task to simultaneously optimize more than two varying objectives in an interactive recommendation process. Moreover, to resolve this optimization task in SR, we develop an evolutionary algorithm with supervised learning approach to obtain the Pareto-optimal solutions of the formulated problem. Comprehensive experiments on four real-world datasets demonstrate the effectiveness of the proposed DMORec for dynamic multi-objective recommendation in sequential recommender systems.

I. Introduction

Recommender systems are essential to cope with information overload in online services and have been widely applied to various domains, such as social media [1], [2], E-Commerce [3], [4], film [5], [6], Internet of things [7] and so on. Conventional recommender systems mostly aim to discover user's intrinsic and general preferences, which are also known as long-term preferences that usually assumed to be static [8], [9], [10], [11]. However, temporary influences over user's behavior are pervasive in reality, the short-term preferences of users may be dynamic and evolving over time. Therefore, static models may lead to obsolete recommendations in practice. Recently, Sequential Recommendation (SR) has attracted extensive attentions in addressing this limitation by exploiting user's sequential behavior patterns to predict subsequent items that the user could interact with [12], [13], [14]. These methods typically leverage the target user's sequential behaviors (e.g., sequences of purchase or review history with the corresponding time stamps), and model both her/his long-term and short-term preferences to inform the future interactions with other items, which have illustrated superior capacity in improving recommendation quality.