Zhuo Zhang

Constrained Optimization with Dynamic Bound-scaling for Effective NLPBackdoor Defense

2022 · arXiv (Cornell University)

We develop a novel optimization method for NLPbackdoor inversion. We leverage a dynamically reducing temperature coefficient in the softmax function to provide changing loss landscapes to the optimizer such that the process gradually focuses on …

When Federated Learning Meets Pre-trained Language Models' Parameter-Efficient Tuning Methods

2022 · arXiv (Cornell University)

With increasing privacy concerns on data, recent studies have made significant progress using federated learning (FL) on privacy-sensitive natural language processing (NLP) tasks. Much literature suggests fully fine-tuning pre-trained language models (PLMs) in the FL …