paper-with-me

Papers

Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and Method

2024-09-29 · Bikang Pan, Wei Huang, Ye Shi

Integrating pretrained vision-language foundation models like CLIP into federated learning has attracted significant attention for enhancing generalization across diverse tasks. Typically, federated learning of vision-language models employs prompt learning to reduce communication and computational costs, i.e., prompt-based federated learning. However, there is limited theoretical analysis to understand the performance of prompt-based federated learning. In this work, we construct a theoretical analysis framework for prompt-based federated learning via feature learning theory. Specifically, we monitor the evolution of signal learning and noise memorization in prompt-based federated learning, demonstrating that performance can be assessed by the ratio of task-relevant to task-irrelevant coefficients. Furthermore, we draw an analogy between income and risk in portfolio optimization and the task-relevant and task-irrelevant terms in feature learning. Leveraging inspiration from portfolio optimization that combining two independent assets will maintain the income while reducing the risk, we introduce two prompts: global prompt and local prompt to construct a prompt portfolio to balance the generalization and personalization. Consequently, we showed the performance advantage of the prompt portfolio and derived the optimal mixing coefficient. These theoretical claims have been further supported by empirical experiments.

📄 PDF Abstract BibTeX arXiv:2409.19610

Code (1)

PanBikang/PromptFolio 공식 구현 pytorch

Tasks

Federated LearningLearning TheoryMemorizationPortfolio OptimizationPrompt Learning

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

ZooPFL: Exploring Black-box Foundation Models for Personalized Federated Learning

2023-10-08 · Wang Lu, Hao Yu, Jindong Wang, Damien Teney 외

When personalized federated learning (FL) meets large foundation models, new challenges arise from various limitations in resources. In addition to typical limitations such as data, computation, and communication costs, …

Federated LearningPersonalized Federated Learning

DeCAF: Decentralized Consensus-And-Factorization for Low-Rank Adaptation of Foundation Models

2025-05-27 · Nastaran Saadati, Zhanhong Jiang, Joshua R. Waite, Shreyan Ganguly 외

Low-Rank Adaptation (LoRA) has emerged as one of the most effective, computationally tractable fine-tuning approaches for training Vision-Language Models (VLMs) and Large Language Models (LLMs). LoRA accomplishes this by…

Federated Learning

Sequential Compression Layers for Efficient Federated Learning in Foundational Models

2024-12-09 · Navyansh Mahla, Sunny Gupta, Amit Sethi

Federated Learning (FL) has gained popularity for fine-tuning large language models (LLMs) across multiple nodes, each with its own private data. While LoRA has been widely adopted for parameter efficient federated fine-…

Federated Learningparameter-efficient fine-tuning

Theoretical Analysis of Privacy Leakage in Trustworthy Federated Learning: A Perspective from Linear Algebra and Optimization Theory

2024-07-23 · Xiaojin Zhang, Wei Chen

Federated learning has emerged as a promising paradigm for collaborative model training while preserving data privacy. However, recent studies have shown that it is vulnerable to various privacy attacks, such as data rec…

Federated LearningPrivacy Preserving

ED-SAM: An Efficient Diffusion Sampling Approach to Domain Generalization in Vision-Language Foundation Models

2024-06-03 · Thanh-Dat Truong, Xin Li, Bhiksha Raj, Jackson Cothren 외

The Vision-Language Foundation Model has recently shown outstanding performance in various perception learning tasks. The outstanding performance of the vision-language model mainly relies on large-scale pre-training dat…

Data AugmentationDomain GeneralizationLanguage ModelingLanguage Modelling