Gradient Coordination for Quantifying and Maximizing Knowledge Transference in Multi-Task Learning

no code implementations • 10 Mar 2023 • Xuanhua Yang, Jianxin Zhao, Shaoguo Liu, Liang Wang, Bo Zheng

Multi-task learning (MTL) has been widely applied in online advertising and recommender systems.

Multi-Task Learning Recommendation Systems

Architecture and Operation Adaptive Network for Online Recommendations

1 code implementation • KDD 2021 • Lang Lang, Zhenlong Zhu, Xuanye Liu, Jianxin Zhao, Jixing Xu, Minghui Shan

We proved that GIN is a generalized form of a wide range of state-of-the-art models, which means GIN can automatically search for the best operation among these models as well as a broader underlying architecture space.

User-centric Composable Services: A New Generation of Personal Data Analytics

no code implementations • 25 Oct 2017 • Jianxin Zhao, Richard Mortier, Jon Crowcroft, Liang Wang

Machine Learning (ML) techniques, such as Neural Network, are widely used in today's applications.

BIG-bench Machine Learning