Multi-Objective Optimization and Recommendations

Tutorial at IEEE International Conference on Data Mining (ICDM), Orlando, USA, 2022
Schedule: Nov 29, 2022 (Eastern Time, USA)


Recommender systems have been widely applied to several domains and applications. Traditional recommender systems usually deal with a single objective, such as minimizing the prediction errors or maximizing the ranking of the recommendation list. There is an emerging demand for multi-objective optimization so that the development of recommendation models can take multiple objectives into consideration.

Currently, the multi-objective optimization methodologies have been well developed, and they have been reused in the area of recommender systems. This tutorial aims to provide a comprehensive introduction of the multi-objective optimization and the multi-objective recommender systems. More specifically, we identify the circumstances in which a multi-objective recommender system could be useful, summarize the methodologies and evaluation approaches in these systems, point out existing problems by a critical analysis, and provide guidelines for the usage of multi-objective optimization in recommender systems.


Part 1: Multi-Objective Optimization (MOO) by Dr. David (Xuejun) Wang
Schedule: 10:30 AM – 12:00 PM, Nov 29, 2022

  • Background and History
  • Multi Objective Optimization (MOO)
  • MOO Solutions
  • Selection of the best solution in Pareto set
  • MOO libraries
  • Summary & QA

Break/Lunch: 12:00 PM - 1:00 PM, Nov 29, 2022

Part 2: Recommender Systems with MOO by Dr. Yong Zheng
Schedule: 1:00 PM – 3:00 PM, Nov 29, 2022

  • Intro to RecSys
  • Why MOO in RecSys
  • RecSys with MOO (1): Recommendation Task as a MOO Process
  • RecSys with MOO (2): Enhanced RecSys with Dominance Relations
  • Summary, Guideline, Challenges & QA



Yong Zheng

Assistant Professor

Illinois Institute of Technology, USA


David (Xuejun) Wang

Principal Data Scientist

Morningstar, Inc., USA


Copyright ©2019 - All rights reserved | This template is made with by Colorlib. Web traffic by Google Analytics.