Federated Learning on Minghui Chen

Can Textual Gradient Work in Federated Learning?

Fri, 24 Jan 2025 00:00:00 +0000

Authors: Minghui Chen, Ruinan Jin, Wenlong Deng, Yuanyuan Chen, Zhi Huang, Han Yu, Xiaoxiao Li

Published in: The Thirteenth International Conference on Learning Representations (ICLR 2025)

Abstract

Recent studies highlight the promise of LLM-based prompt optimization, especially with TextGrad, which automates “differentiation” via texts and backpropagates textual feedback provided by LLMs. This approach facilitates training in various real-world applications that do not support numerical gradient propagation or loss calculation. It opens new avenues for optimization in decentralized, resource-constrained environments, suggesting that users of black-box LLMs (e.g., ChatGPT) could enhance components of LLM agentic systems (such as prompt optimization) through collaborative paradigms like federated learning (FL).

Local Superior Soups: A Catalyst for Model Merging in Cross-Silo Federated Learning

Tue, 15 Oct 2024 00:00:00 +0000

Authors: Minghui Chen, Meirui Jiang, Xin Zhang, Qi Dou, Zehua Wang, Xiaoxiao Li

Published in: The Thirty-Eighth Conference on Neural Information Processing Systems (NeurIPS 2024)

Abstract

Federated learning (FL) is a learning paradigm that enables collaborative training of models using decentralized data. Recently, the utilization of pre-trained weight initialization in FL has been demonstrated to effectively improve model performance. However, the evolving complexity of current pre-trained models, characterized by a substantial increase in parameters, markedly intensifies the challenges associated with communication rounds required for their adaptation to FL. To address these communication cost issues and increase the performance of pre-trained model adaptation in FL, we propose an innovative model interpolation-based local training technique called “Local Superior Soups.” Our method enhances local training across different clients, encouraging the exploration of a connected low-loss basin within a few communication rounds through regularized model interpolation. This approach acts as a catalyst for the seamless adaptation of pre-trained models in in FL. We demonstrated its effectiveness and efficiency across diverse widely-used FL datasets.

Forgettable Federated Linear Learning with Certified Data Removal

Fri, 20 Sep 2024 00:00:00 +0000

Authors: Ruinan Jin, Minghui Chen, Qiong Zhang, Xiaoxiao Li

Published in: WWW 2024 FL@FM Workshop (Best Paper Award 🏆)

Abstract

Federated learning (FL) is a trending distributed learning framework that enables collaborative model training without data sharing. Machine learning models trained on datasets can potentially expose the private information of the training data, revealing details about individual data records. In this study, we focus on the FL paradigm that grants clients the “right to be forgotten”. The forgettable FL framework should bleach its global model weights as it has never seen that client and hence does not reveal any information about the client. To this end, we propose the Forgettable Federated Linear Learning (2F2L) framework featured with novel training and data removal strategies. The training pipeline, named Federated linear training, employs linear approximation on the model parameter space to enable our 2F2L framework work for deep neural networks while achieving comparable results with canonical neural network training. We also introduce FedRemoval, an efficient and effective removal strategy that tackles the computational challenges in FL by approximating the Hessian matrix using public server data from the pretrained model. Unlike the previous uncertified and heuristic machine unlearning methods in FL, we provide theoretical guarantees by bounding the differences of model weights by our FedRemoval and that from retraining from scratch. Experimental results on MNIST and Fashion-MNIST datasets demonstrate the effectiveness of our method in achieving a balance between model accuracy and information removal, outperforming baseline strategies and approaching retraining from scratch.

Research Associate

Mon, 01 Jul 2024 00:00:00 +0000

Position: Research Associate

Institution: Nanyang Technological University

Advisor: Prof. Xiaoxiao Li & Prof. Han Yu

Period: July 2024 - October 2025

Location: Singapore

Research Focus

Exploring federated learning and multi-agent collaboration, focusing on:

Personalization in heterogeneous federated learning
LLM-driven multi-agent collaboration

Research Associate

Fri, 01 Sep 2023 00:00:00 +0000

Position: Research Associate

Institution: Vector Institute

Advisor: Prof. Xiaoxiao Li

Period: September 2023 - July 2024

Location: Remote

Research Focus

Exploring federated learning, focusing on:

Personalization in heterogeneous federated learning

FedSoup: Improving Generalization and Personalization in Federated Learning via Selective Model Interpolation

Thu, 20 Jul 2023 00:00:00 +0000

Authors: Minghui Chen, Meirui Jiang, Qi Dou, Zehua Wang, Xiaoxiao Li

Published in: The 26th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2023)

Abstract

Cross-silo federated learning (FL) enables the development of machine learning models on datasets distributed across data centers such as hospitals and clinical research laboratories. However, recent research has found that current FL algorithms face a trade-off between local and global performance when confronted with distribution shifts. Specifically, personalized FL methods have a tendency to overfit to local data, leading to a sharp valley in the local model and inhibiting its ability to generalize to out-of-distribution data. In this paper, we propose a novel federated model soup method (i.e., selective interpolation of model parameters) to optimize the trade-off between local and global performance. Specifically, during the federated training phase, each client maintains its own global model pool by monitoring the performance of the interpolated model between the local and global models. This allows us to alleviate overfitting and seek flat minima, which can significantly improve the model’s generalization performance.

Research Associate

Thu, 01 Sep 2022 00:00:00 +0000

Position: Research Associate

Institution: University of British Columbia

Advisor: Prof. Xiaoxiao Li & Prof. Zehua Wang

Period: September 2022 - July 2024

Location: Remote

Research Focus

Exploring federated learning, focusing on:

Personalization in heterogeneous federated learning