.png){kind=icon}
返回
Trustworthy Recommender Systems
.png){kind=icon}
OA
AI
DOI：10.1145/3627826.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recommender systems (RSs) aim at helping users to effectively retrieve items of their interests from a largecatalogue. For a quite long time, researchers and practitioners have been focusing on developing accurateRSs. Recent years have witnessed an increasing number of threats to RSs, coming from attacks, system anduser generated noise, and various types of biases. As a result, it has become clear that the focus on RS ac-curacy is too narrow, and the research must consider other important factors, particularly trustworthiness.A trustworthy recommender system (TRS) should not only be accurate but also transparent, unbiased, fair,and robust to noise and attacks. These observations actually led to a paradigm shift of the research on RSs:from accuracy-oriented RSs to TRSs. However, there is a lack of a systematic overview and discussion of theliterature in this novel and fast-developing field of TRSs. To this end, in this article, we provide an overviewof TRSs, including a discussion of the motivation and basic concepts of TRSs, a presentation of the challengesin building TRSs, and a perspective on the future directions in this area. We also provide a novel conceptualframework to support the construction of TRSs
Keyword:
Recommender systems
trustworthy recommendation
trustworthy AI
期刊
IF:
6.6
论文数:
1.5K
被引数:
6.2K
机构
引用论文
.png){kind=icon}
查看更多内容