DeepAI AI Chat
Log In Sign Up

AI-KD: Adversarial learning and Implicit regularization for self-Knowledge Distillation

by   Hyungmin Kim, et al.

We present a novel adversarial penalized self-knowledge distillation method, named adversarial learning and implicit regularization for self-knowledge distillation (AI-KD), which regularizes the training procedure by adversarial learning and implicit distillations. Our model not only distills the deterministic and progressive knowledge which are from the pre-trained and previous epoch predictive probabilities but also transfers the knowledge of the deterministic predictive distributions using adversarial learning. The motivation is that the self-knowledge distillation methods regularize the predictive probabilities with soft targets, but the exact distributions may be hard to predict. Our method deploys a discriminator to distinguish the distributions between the pre-trained and student models while the student model is trained to fool the discriminator in the trained procedure. Thus, the student model not only can learn the pre-trained model's predictive probabilities but also align the distributions between the pre-trained and student models. We demonstrate the effectiveness of the proposed method with network architectures on multiple datasets and show the proposed method achieves better performance than state-of-the-art methods.


MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillation

The advent of large pre-trained language models has given rise to rapid ...

RoSearch: Search for Robust Student Architectures When Distilling Pre-trained Language Models

Pre-trained language models achieve outstanding performance in NLP tasks...

Feature-map-level Online Adversarial Knowledge Distillation

Feature maps contain rich information about image intensity and spatial ...

Be Your Own Best Competitor! Multi-Branched Adversarial Knowledge Transfer

Deep neural network architectures have attained remarkable improvements ...

Self-Distillation Amplifies Regularization in Hilbert Space

Knowledge distillation introduced in the deep learning context is a meth...

Safe Distillation Box

Knowledge distillation (KD) has recently emerged as a powerful strategy ...

Knowledge Distillation Leveraging Alternative Soft Targets from Non-Parallel Qualified Speech Data

This paper describes a novel knowledge distillation framework that lever...