Explore an innovative approach to recommendation systems in this 13-minute conference talk from SIGIR 2024. Delve into the MDMTRec framework, an adaptive multi-task multi-domain recommendation system presented by a team of researchers. Learn how this framework addresses challenges in cross-domain recommendations and multi-task learning. Discover the architecture, methodology, and potential applications of MDMTRec in improving personalized recommendations across various domains and tasks. Gain insights into the latest advancements in recommendation algorithms and their implications for enhancing user experiences in diverse digital platforms.
MDMTRec: An Adaptive Multi-Task Multi-Domain Recommendation Framework - SIGIR 2024
Association for Computing Machinery (ACM) via YouTube
Overview
Syllabus
SIGIR 2024 M3.3 [fp] MDMTRec: An Adaptive Multi-Task Multi-Domain Recommendation Framework
Taught by
Association for Computing Machinery (ACM)
Related Courses
-
Behavior-Contextualized Item Preference Modeling for Multi-Behavior Recommendation
-
SIGformer: Sign-aware Graph Transformer for Recommendation
-
Fair Sequential Recommendation without User Demographics - SIGIR 2024
-
Adaptive Fair Representation Learning for Personalized Fairness in Recommendations - Lecture 7
-
Adaptive In-Context Learning with Large Language Models for Bundle Generation - Recommendation Systems
-
Optimal Transport Enhanced Cross-City Site Recommendation - T2.4
