A Survey on Trustworthy Recommender Systems

Abstract

Recommender systems (RS), serving at the forefront of Human-centered AI, are widely deployed in almost every corner of the web and facilitate the human decision-making process. However, despite their enormous capabilities and potential, RS may also lead to undesired counter-effects on users, items, producers, platforms, or even the society at large, such as compromised user trust due to non-transparency, unfair treatment of different consumers, or producers, privacy concerns due to extensive use of user's private data for personalization, just to name a few. All of these create an urgent need for Trustworthy Recommender Systems (TRS) so as to mitigate or avoid such adverse impacts and risks. In this survey, we will introduce techniques related to trustworthy and responsible recommendation, including but not limited to explainable recommendation, fairness in recommendation, privacy-aware recommendation, robustness in recommendation, user controllable recommendation, as well as the relationship between these different perspectives in terms of trustworthy and responsible recommendation. Through this survey, we hope to deliver readers with a comprehensive view of the research area and raise attention to the community about the importance, existing research achievements, and future research directions on trustworthy recommendation.

Securing Recommender System via Cooperative Training

“…Reactive Attack detection. Many works have been developed to detect shilling attacks [21,[36][37][38], and such methods can be roughly classified into supervised classification methods and unsupervised clustering methods. The majority of work on supervised classification methods begins with feature engineering and then turns to the development of algorithms.…”

Towards trustworthy recommenders: building explainable and unbiased recommendation systems

“…However, the purpose of recommendation systems goes beyond serving users; they also aim to generate profits for merchants by exposing their products to users [7][8][9]. This multifaceted decision-making process underscores the necessity for a Trustworthy Recommender System (TRS) [10]. Recognizing this need, a growing body of research is dedicated to bolstering users' trust in recommendation systems [11].…”

“…Meanwhile, other works concentrate on delivering equitable exposure for both popular and rare items, aiming to enhance user experience [15,16]. Illustrated in Figure 1.1, these TRS methods foster trust by addressing five pivotal aspects [10]: • Explainability: Explainable recommendation methods play a pivotal role in enhancing the transparency, persuasiveness, user satisfaction, and trustworthiness of recommender systems [17]. Rather than merely suggesting items to users, explainable recommendations elucidate the rationale behind the recommended items [18,19].…”

“…Rather than merely suggesting items to users, explainable recommendations elucidate the rationale behind the recommended items [18,19]. These methods, classified based on the type of explanations, include the following categories [10]:…”

“…• Privacy: People are becoming increasingly aware that privacy protection is essential for building a TRS. Based on the ownership of private information, we categorize privacy into two types [10]:…”