Jinghui Chen

Communication-Compressed Adaptive Gradient Method for Distributed Nonconvex Optimization

2021 · arXiv (Cornell University)

Due to the explosion in the size of the training datasets, distributed learning has received growing interest in recent years. One of the major bottlenecks is the large communication cost between the central server and …

Communication-Efficient Adaptive Federated Learning

2022 · arXiv (Cornell University)

Federated learning is a machine learning training paradigm that enables clients to jointly train models without sharing their own localized data. However, the implementation of federated learning in practice still faces numerous challenges, such as …

How Powerful is Implicit Denoising in Graph Neural Networks

2022 · arXiv (Cornell University)

Graph Neural Networks (GNNs), which aggregate features from neighbors, are widely used for graph-structured data processing due to their powerful representation learning capabilities. It is generally believed that GNNs can implicitly remove the non-predictive noises. …

WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response

2024 · arXiv (Cornell University)

The recent breakthrough in large language models (LLMs) such as ChatGPT has revolutionized production processes at an unprecedented pace. Alongside this progress also comes mounting concerns about LLMs' susceptibility to jailbreaking attacks, which leads to …