When labeled data is insufficient, semi-supervised learning with the
pse...
Click-Through Rate (CTR) prediction serves as a fundamental component in...
Cascading architecture has been widely adopted in large-scale advertisin...
Knowledge distillation (KD), which can efficiently transfer knowledge fr...
The cross-domain performance of automatic speech recognition (ASR) could...
Industrial recommender systems usually hold data from multiple business
...
Automatic speech recognition (ASR) with federated learning (FL) makes it...
Model-based methods for recommender systems have been studied extensivel...
Most machine learning classifiers only concern classification accuracy, ...
Self-supervised pre-training has dramatically improved the performance o...
How to predict precise user preference and how to make efficient retriev...
Cross-lingual speech adaptation aims to solve the problem of leveraging
...
Matching module plays a critical role in display advertising systems. Wi...
When only limited target domain data is available, domain adaptation cou...
When only a limited amount of accented speech data is available, to prom...
Retrieving relevant targets from an extremely large target set under
com...
Machine learning develops rapidly, which has made many theoretical
break...
Large-scale industrial recommender systems are usually confronted with
c...
We propose a novel recommendation method based on tree. With user behavi...
To better extract users' interest by exploiting the rich historical beha...
Taobao, as the largest online retail platform in the world, provides bil...
Deep networks have been successfully applied to learn transferable featu...