Bridging the Gap: Unpacking the Hidden Challenges in Knowledge Distillation for Online Ranking Systems
Year: 2024
Type: conference-paper
Abstract: Knowledge Distillation (KD) is a powerful approach for compressing a large model into a smaller, more efficient model, particularly beneficial for latency-sensitive applications like recommender systems. However, current KD research predominantly focuses on Computer Vision (CV) and NLP tasks, overlooking unique data characteristics and challenges inherent to recommender systems. This paper addresses these overlooked challenges, specifically: (1) mitigating data distribution shifts between teacher and student models, (2) efficiently identifying optimal teacher configurations within time and budgetary constraints, and (3) enabling computationally efficient and rapid sharing of teacher labels to support multiple students. We present a robust KD system developed and rigorously evaluated on multiple large-scale personalized video recommendation systems within Google. Our live experiment results demonstrate significant improvements in student model performance while ensuring consistent and reliable generation of high-quality teacher labels from a continuous data stream of data.
Authors: Nikhil Khani, Li Wei, Aniruddh Nath, Shawn Andrews, Shuo Yang, Yang Liu, Pendo Abbo, Maciej Kula, Jarrod Kahn, Zhe Zhao, Lichan Hong, Ed Chi
Institution: Google (United States)
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: green
OpenAlex ID: W4403220320