Jiaxi Tang
Research Subjects
Jiaxi Tang has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Ed H. Chi
Google DeepMind, Mountain View, CA, USA
2 shared publications - Lichan Hong
Google, Mountain View, CA, USA
2 shared publications - Benjamin Most
Google, Mountain View, CA, USA
1 shared publication - Chuan He
Google, Mountain View, CA, USA
1 shared publication - Daryl Chang
YouTube, Google, Mountain View, CA, USA
1 shared publication - Diego Uribe Mora
YouTube, Google, Mountain View, CA, USA
1 shared publication
Latest Publications
- Open Access
- 8 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 832-834
Short-form Video Needs Long-term Interests: An Industrial Solution for Serving Large User Sequence Models
Sequential models are invaluable for powering personalized recommendation systems. In the context of short-form video (SFV) feeds, where user behavior history is typically longer, systems must be able to understand users’ long-term interests. However, deploying large sequence models to extensive web-scale applications faces challenges due to high serving cost. To address this, we propose an industrial framework designed for efficiently serving large user sequence models. Specifically, the proposed infrastructure decouples serving of the user sequence model and the main recommendation model, with the user sequence model being served offline (asynchronously) with periodical refresh. The proposed infrastructure is also model-agnostic; thus, it can be used to support any type of user sequence models (even LLMs) with controllable costs. Empirical results show that large user models deployed with our framework significantly and consistently enhance the quality of the main recommendation model with minimal serving costs increase.
- 8 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 832-834
Open AccessShort-form Video Needs Long-term Interests: An Industrial Solution for Serving Large User Sequence Models
Sequential models are invaluable for powering personalized recommendation systems. In the context of short-form video (SFV) feeds, where user behavior history is typically longer, systems must be able to understand users’ long-term interests. However, deploying large sequence models to extensive web-scale applications faces challenges due to high serving cost. To address this, we propose an industrial framework designed for efficiently serving large user sequence models. Specifically, the proposed infrastructure decouples serving of the user sequence model and the main recommendation model, with the user sequence model being served offline (asynchronously) with periodical refresh. The proposed infrastructure is also model-agnostic; thus, it can be used to support any type of user sequence models (even LLMs) with controllable costs. Empirical results show that large user models deployed with our framework significantly and consistently enhance the quality of the main recommendation model with minimal serving costs increase.
- Open Access
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 4882-4893
Improving Training Stability for Multitask Ranking Models in Recommender Systems
Recommender systems play an important role in many content platforms. While most recommendation research is dedicated to designing better models to improve user experience, we found that research on stabilizing the training for such models is severely under-explored. As recommendation models become larger and more sophisticated, they are more susceptible to training instability issues, i.e., loss divergence, which can make the model unusable, waste significant resources and block model developments. In this paper, we share our findings and best practices we learned for improving the training stability of a real-world multitask ranking model for YouTube recommendations. We show some properties of the model that lead to unstable training and conjecture on the causes. Furthermore, based on our observations of training dynamics near the point of training instability, we hypothesize why existing solutions would fail, and propose a new algorithm to mitigate the limitations of existing solutions. Our experiments on YouTube production dataset show the proposed algorithm can significantly improve training stability while not compromising convergence, comparing with several commonly used baseline methods.
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 4882-4893
Open AccessImproving Training Stability for Multitask Ranking Models in Recommender Systems
Recommender systems play an important role in many content platforms. While most recommendation research is dedicated to designing better models to improve user experience, we found that research on stabilizing the training for such models is severely under-explored. As recommendation models become larger and more sophisticated, they are more susceptible to training instability issues, i.e., loss divergence, which can make the model unusable, waste significant resources and block model developments. In this paper, we share our findings and best practices we learned for improving the training stability of a real-world multitask ranking model for YouTube recommendations. We show some properties of the model that lead to unstable training and conjecture on the causes. Furthermore, based on our observations of training dynamics near the point of training instability, we hypothesize why existing solutions would fail, and propose a new algorithm to mitigate the limitations of existing solutions. Our experiments on YouTube production dataset show the proposed algorithm can significantly improve training stability while not compromising convergence, comparing with several commonly used baseline methods.