Adobe PDF (1.38 MB)
Title Details:
New Trends
Authors: Symeonidis, Panagiotis
Description:
Abstract:
In chapter ten, we will discuss new trends in recommender systems. In particular, we will analyze recommendations to groups of people. Furthermore, we will study different methods for combining the preferences of multiple users (e.g., Maximum User Satisfaction Method, Minimum User Dissatisfaction Method etc.). Furthermore, we will extensively address the burning issues of ethics, fairness, accountability and censorship that have emerged and are a current trend in recommender systems. Finally, we will delve into three different privacy policies (architectural topologies of recommender systems, algorithmic techniques, and regulatory legal frameworks). Specializing here, a new trend in recommender systems is that data with user preferences should not go to the company's server for privacy reasons. In this direction, we will present algorithms implemented either in a distributed way (federated learning) or in a decentralized (decentralized matrix factorization with differential privacy) way of training the prediction models.
Linguistic Editors: Sakellarios, Michalis
Technical Editors: Karatzidis, Dimitrios
Graphic Editors: Symeonidis, Panagiotis
Type: Chapter
Creation Date: 29-05-2023
Item Details:
License: Attribution - NonCommercial - ShareAlike 4.0 International (CC BY-NC-SA 4.0)
Handle http://hdl.handle.net/11419/9582
Bibliographic Reference: Symeonidis, P. (2023). New Trends [Chapter]. In Symeonidis, P. 2023. Intelligent Recommender Systems [Postgraduate textbook]. Kallipos, Open Academic Editions. https://hdl.handle.net/11419/9582
Language: Greek
Is Part of: Intelligent Recommender Systems
Publication Origin: Kallipos, Open Academic Editions