paper-with-me

홈 › Papers

Can Textual Gradient Work in Federated Learning?

2025-02-27 · Minghui Chen, Ruinan Jin, Wenlong Deng, YuanYuan Chen, Zhi Huang, Han Yu, Xiaoxiao Li

Recent studies highlight the promise of LLM-based prompt optimization, especially with TextGrad, which automates differentiation'' via texts and backpropagates textual feedback. This approach facilitates training in various real-world applications that do not support numerical gradient propagation or loss calculation. In this paper, we systematically explore the potential and challenges of incorporating textual gradient into Federated Learning (FL). Our contributions are fourfold. Firstly, we introduce a novel FL paradigm, Federated Textual Gradient (FedTextGrad), that allows clients to upload locally optimized prompts derived from textual gradients, while the server aggregates the received prompts. Unlike traditional FL frameworks, which are designed for numerical aggregation, FedTextGrad is specifically tailored for handling textual data, expanding the applicability of FL to a broader range of problems that lack well-defined numerical loss functions. Secondly, building on this design, we conduct extensive experiments to explore the feasibility of FedTextGrad. Our findings highlight the importance of properly tuning key factors (e.g., local steps) in FL training. Thirdly, we highlight a major challenge in FedTextGrad aggregation: retaining essential information from distributed prompt updates. Last but not least, in response to this issue, we improve the vanilla variant of FedTextGrad by providing actionable guidance to the LLM when summarizing client prompts by leveraging the Uniform Information Density principle. Through this principled study, we enable the adoption of textual gradients in FL for optimizing LLMs, identify important issues, and pinpoint future directions, thereby opening up a new research area that warrants further investigation.

📄 PDF Abstract BibTeX arXiv:2502.19980

Code (1)

ubc-tea/FedTextGrad 공식 구현

Tasks

Federated Learning

Methods 이 논문이 사용한 방법론

TextGrad TextGrad is a powerful framework building automatic ``differentiation'' via text. TextGrad implements backpropagation through text feedback provided by LLMs, strongly building on…

Similar Papers 제목 키워드 기반

LAMP: Extracting Text from Gradients with Language Model Priors

2022-02-17 · Mislav Balunović, Dimitar I. Dimitrov, Nikola Jovanović, Martin Vechev

Recent work shows that sensitive user data can be reconstructed from gradient updates, breaking the key privacy promise of federated learning. While success was demonstrated primarily on image data, these methods do not …

Federated LearningLanguage ModelingLanguage Modelling

Privacy-Preserving Multimodal News Recommendation through Federated Learning

2025-07-21 · Mehdi Khalaj, Shahrzad Golestani Najafabadi, Julita Vassileva arxiv

Personalized News Recommendation systems (PNR) have emerged as a solution to information overload by predicting and suggesting news items tailored to individual user interests. However, traditional PNR systems face sever…

Recommendation SystemsFederated Learning

Federated Zeroth-Order Optimization using Trajectory-Informed Surrogate Gradients

2023-08-08 · Yao Shu, Xiaoqiang Lin, Zhongxiang Dai, Bryan Kian Hsiang Low

Federated optimization, an emerging paradigm which finds wide real-world applications such as federated learning, enables multiple clients (e.g., edge devices) to collaboratively optimize a global function. The clients d…

Adversarial AttackFederated Learning

An End-to-End Encrypted Neural Network for Gradient Updates Transmission in Federated Learning

2019-08-22 · Hongyu Li, Tianqi Han

Federated learning is a distributed learning method to train a shared model by aggregating the locally-computed gradient updates. In federated learning, bandwidth and privacy are two main concerns of gradient updates tra…

Data CompressionFederated Learning

Gradient Obfuscation Gives a False Sense of Security in Federated Learning

2022-06-08 · Kai Yue, Richeng Jin, Chau-Wai Wong, Dror Baron 외

Federated learning has been proposed as a privacy-preserving machine learning framework that enables multiple clients to collaborate without sharing raw data. However, client privacy protection is not guaranteed by desig…

Federated Learningimage-classificationImage ClassificationPrivacy Preserving+2