Every Little Bit Helps: A Semantic-aware Tail Label Understanding Framework
IEEE/ACM International Symposium on Quality of Service (IWQoS), 2024
Abstract
The rapid expansion of AI technology, driven by high-speed networks and high-performance mobile devices, enables personalized and cross-content recommendations across diverse applications. Recent methods consider a large number of textual content keywords or topics as labels for recommendations, transforming the problem into Extreme Multi-label Learning (XML). However, addressing the XML problem in AI-driven recommendation systems that handle extensive user-generated data while ensuring Quality of Service (QoS) faces two main challenges: significant computational costs and inferior tail label prediction performance. We propose SAT, a semantic-aware framework with a tree architecture that effectively tackles these challenges and demonstrates improved performance compared to well-established approaches.
BibTeX
@inproceedings{pan2024every,
title = {Every Little Bit Helps: A Semantic-aware Tail Label Understanding Framework},
author = {Pan, Cheng and Wang, Feng and Zhang, Cong and Li, Jiaxing and Ngai, Edith C. H. and Liu, Jiangchuan},
booktitle = {2024 IEEE/ACM 32nd International Symposium on Quality of Service (IWQoS)},
pages = {1--2},
year = {2024},
doi = {10.1109/IWQoS61813.2024.10682841}
}