Ziqi Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ziqi Wang has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Daogao Liu
University of Washington
1 shared publication - Frederick Liu
Google DeepMind
1 shared publication - Heng Ji
University of Illinois Urbana-Champaign
1 shared publication - Hongkun Yu
Google Research 3 Google Inc
1 shared publication - Jing Li
Harbin Institute of Technology, Shenzhen, China
1 shared publication Le Hou
1 shared publication
Latest Publications
- Open Access
Augmentation with Projection: Towards an Effective and Efficient Data Augmentation Paradigm for Distillation
Knowledge distillation is one of the primary methods of transferring knowledge from large to small models. However, it requires massive task-specific data, which may not be plausible in many real-world applications. Data augmentation methods such as representation interpolation, token replacement, or augmentation with models are applied to tackle this problem. However, these data augmentation methods either potentially cause shifts in decision boundaries (representation interpolation), are not expressive enough (token replacement), or introduce too much computational overhead (augmentation with models). To this end, we propose AugPro (Augmentation with Projection), an effective and efficient data augmentation method for distillation. Our method builds on top of representation interpolation augmentation methods to maintain the diversity of expressions and converts the augmented data to tokens to avoid shifting decision boundaries. It uses simple operations that come with little computational overhead. The results on multiple GLUE tasks show that our methods can improve distillation performance by a large margin at a low time cost. Codes are available at https://github.com/google-research/google-research/tree/master/augpro.
Open AccessAugmentation with Projection: Towards an Effective and Efficient Data Augmentation Paradigm for Distillation
Knowledge distillation is one of the primary methods of transferring knowledge from large to small models. However, it requires massive task-specific data, which may not be plausible in many real-world applications. Data augmentation methods such as representation interpolation, token replacement, or augmentation with models are applied to tackle this problem. However, these data augmentation methods either potentially cause shifts in decision boundaries (representation interpolation), are not expressive enough (token replacement), or introduce too much computational overhead (augmentation with models). To this end, we propose AugPro (Augmentation with Projection), an effective and efficient data augmentation method for distillation. Our method builds on top of representation interpolation augmentation methods to maintain the diversity of expressions and converts the augmented data to tokens to avoid shifting decision boundaries. It uses simple operations that come with little computational overhead. The results on multiple GLUE tasks show that our methods can improve distillation performance by a large margin at a low time cost. Codes are available at https://github.com/google-research/google-research/tree/master/augpro.