MAT: Mixed-Strategy Game of Adversarial Training in Fine-tuning

by   Zhehua Zhong, et al.
Hangzhou Dianzi University

Fine-tuning large-scale pre-trained language models has been demonstrated effective for various natural language processing (NLP) tasks. Previous studies have established that incorporating adversarial training during the fine-tuning stage can significantly enhance model generalization and robustness. However, from the perspective of game theory, such utilizations of adversarial training correspond to pure-strategy games, which are inherently limited in terms of the scope of their strategies, thereby still having room for improvement. In order to push the performance boundaries, we propose a novel Mixed-strategy Adversarial Training algorithm (MAT). Methodologically, we derive the Nash equilibrium of a mixed-strategy game for adversarial training using Entropy Mirror Descent to establish MAT by sampling method. To verify the effectiveness of MAT, we conducted extensive benchmark experiments on large-scale pre-trained models, such as BERT and RoBERTa. MAT significantly outperforms the state-of-the-art methods on both the GLUE and ANLI benchmarks in terms of generalization and robustness.


page 1

page 2

page 3

page 4


Adversarial Training for Large Neural Language Models

Generalization and robustness are both key desiderata for designing mach...

Efficient Adversarial Training with Robust Early-Bird Tickets

Adversarial training is one of the most powerful methods to improve the ...

A Simple Fine-tuning Is All You Need: Towards Robust Deep Learning Via Adversarial Fine-tuning

Adversarial Training (AT) with Projected Gradient Descent (PGD) is an ef...

HABERTOR: An Efficient and Effective Deep Hatespeech Detector

We present our HABERTOR model for detecting hatespeech in large scale us...

Adversarial Training as Stackelberg Game: An Unrolled Optimization Approach

Adversarial training has been shown to improve the generalization perfor...

Domain Adversarial Training: A Game Perspective

The dominant line of work in domain adaptation has focused on learning i...

Can Fine-tuning Pre-trained Models Lead to Perfect NLP? A Study of the Generalizability of Relation Extraction

Fine-tuning pre-trained models have achieved impressive performance on s...

Please sign up or login with your details

Forgot password? Click here to reset