90 citations · 132 across the 9 of their papers we have counts for
9 papers
FraQ: Efficient Coordinate-Space Recompression for Federated Low-Rank Adaptation
Shenghui Li, Thiemo Voigt
Federated fine-tuning with Low-Rank Adaptation (LoRA) enables efficient collaborative adaptation of Large Language Models (LLMs) without centralizing private data. However, LoRA's…
PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning
Shenghui Li, Edith C. -H. Ngai, Fanghua Ye +1
Federated Parameter-Efficient Fine-Tuning (FedPEFT) has emerged as a promising paradigm for privacy-preserving and efficient adaptation of Pre-trained Language Models (PLMs) in Fed…
Synergizing Foundation Models and Federated Learning: A Survey
Shenghui Li, Fanghua Ye, Meng Fang +4
Over the past few years, the landscape of Artificial Intelligence (AI) has been reshaped by the emergence of Foundation Models (FMs). Pre-trained on massive datasets, these models…
Enhancing Conversational Search: Large Language Model-Aided Informative Query Rewriting
Fanghua Ye, Meng Fang, Shenghui Li +1
Query rewriting plays a vital role in enhancing conversational search by transforming context-dependent user queries into standalone forms. Existing approaches primarily leverage h…
An Experimental Study of Byzantine-Robust Aggregation Schemes in Federated Learning
Shenghui Li, Edith C. -H. Ngai, Thiemo Voigt
Byzantine-robust federated learning aims at mitigating Byzantine failures during the federated training process, where malicious participants may upload arbitrary local updates to…
MetaASSIST: Robust Dialogue State Tracking with Meta Learning
Fanghua Ye, Xi Wang, Jie Huang +3
Existing dialogue datasets contain lots of noise in their state annotations. Such noise can hurt model training and ultimately lead to poor generalization performance. A general fr…
Blades: A Unified Benchmark Suite for Byzantine Attacks and Defenses in Federated Learning
Shenghui Li, Edith Ngai, Fanghua Ye +3
Federated learning (FL) facilitates distributed training across different IoT and edge devices, safeguarding the privacy of their data. The inherent distributed structure of FL int…
Slot Self-Attentive Dialogue State Tracking
Fanghua Ye, Jarana Manotumruksa, Qiang Zhang +2
An indispensable component in task-oriented dialogue systems is the dialogue state tracker, which keeps track of users' intentions in the course of conversation. The typical approa…
Auto-weighted Robust Federated Learning with Corrupted Data Sources
Shenghui Li, Edith Ngai, Fanghua Ye +1
Federated learning provides a communication-efficient and privacy-preserving training process by enabling learning statistical models with massive participants while keeping their…