FedPFT: Federated Proxy Fine-Tuning of Foundation Models

• URL: http://arxiv.org/abs/2404.11536v2
• Date: Sun, 28 Apr 2024 11:11:16 GMT
• Title: FedPFT: Federated Proxy Fine-Tuning of Foundation Models
• Authors: Zhaopeng Peng, Xiaoliang Fan, Yufan Chen, Zheng Wang, Shirui Pan, Chenglu Wen, Ruisheng Zhang, Cheng Wang,
• Abstract summary: Adapting Foundation Models (FMs) for downstream tasks through Federated Learning (FL) emerges as a promising strategy for protecting data privacy and valuable FMs. Existing methods fine-tune FM by allocating sub-FM to clients in FL, leading to suboptimal performance due to insufficient tuning and inevitable error accumulations of gradients. We propose Federated Proxy Fine-Tuning (FedPFT), a novel method enhancing FMs adaptation in downstream tasks through FL by two key modules.
• Score: 55.58899993272904
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Adapting Foundation Models (FMs) for downstream tasks through Federated Learning (FL) emerges a promising strategy for protecting data privacy and valuable FMs. Existing methods fine-tune FM by allocating sub-FM to clients in FL, however, leading to suboptimal performance due to insufficient tuning and inevitable error accumulations of gradients. In this paper, we propose Federated Proxy Fine-Tuning (FedPFT), a novel method enhancing FMs adaptation in downstream tasks through FL by two key modules. First, the sub-FM construction module employs a layer-wise compression approach, facilitating comprehensive FM fine-tuning across all layers by emphasizing those crucial neurons. Second, the sub-FM alignment module conducts a two-step distillations-layer-level and neuron-level-before and during FL fine-tuning respectively, to reduce error of gradient by accurately aligning sub-FM with FM under theoretical guarantees. Experimental results on seven commonly used datasets (i.e., four text and three vision) demonstrate the superiority of FedPFT.

Related papers

• Large Model for Small Data: Foundation Model for Cross-Modal RF Human Activity Recognition [7.351361666395708]
  We introduce FM-Fi, a cross-modal framework engineered to translate the knowledge of vision-based FMs for enhancing RF-based HAR systems. FM-Fi involves a novel cross-modal contrastive knowledge distillation mechanism, enabling an RF encoder to inherit the interpretative power of FMs. It also employs the intrinsic capabilities of FM and RF to remove extraneous features for better alignment between the two modalities.
  arXiv  Detail & Related papers  (2024-10-13T03:43:59Z)
• Vulnerabilities of Foundation Model Integrated Federated Learning Under Adversarial Threats [34.51922824730864]
  Federated Learning (FL) addresses critical issues in machine learning related to data privacy and security, yet suffering from data insufficiency and imbalance under certain circumstances. The emergence of foundation models (FMs) offers potential solutions to the limitations of existing FL frameworks. We conduct the first investigation on the vulnerability of FM integrated FL (FM-FL) under adversarial threats.
  arXiv  Detail & Related papers  (2024-01-18T20:56:42Z)
• A Survey on Efficient Federated Learning Methods for Foundation Model Training [62.473245910234304]
  Federated Learning (FL) has become an established technique to facilitate privacy-preserving collaborative training across a multitude of clients. In the wake of Foundation Models (FM), the reality is different for many deep learning applications. We discuss the benefits and drawbacks of parameter-efficient fine-tuning (PEFT) for FL applications.
  arXiv  Detail & Related papers  (2024-01-09T10:22:23Z)
• Grounding Foundation Models through Federated Transfer Learning: A General Framework [20.341440265217496]
  Foundation Models (FMs) such as GPT-4 have achieved remarkable success in various natural language processing and computer vision tasks. Grounding FMs by adapting them to domain-specific tasks or augmenting them with domain-specific knowledge enables us to exploit the full potential of FMs. In recent years, the need for grounding FMs leveraging Federated Transfer Learning (FTL) has arisen strongly in both academia and industry. Motivated by the strong growth in FTL-FM research and the potential impact of FTL-FM on industrial applications, we propose an FTL-FM framework that formulates problems of
  arXiv  Detail & Related papers  (2023-11-29T08:21:42Z)
• Federated Fine-Tuning of Foundation Models via Probabilistic Masking [11.192113661738764]
  Foundation Models (FMs) have revolutionized machine learning with their adaptability and high performance across tasks. Their integration into Federated Learning (FL) is challenging due to substantial communication overhead from their extensive parameterization. We present DeltaMask, a novel method that efficiently fine-tunes FMs in FL at an ultra-low, well below 1 bpp.
  arXiv  Detail & Related papers  (2023-11-29T01:10:39Z)
• The Role of Federated Learning in a Wireless World with Foundation Models [59.8129893837421]
  Foundation models (FMs) are general-purpose artificial intelligence (AI) models that have recently enabled multiple brand-new generative AI applications. Currently, the exploration of the interplay between FMs and federated learning (FL) is still in its nascent stage. This article explores the extent to which FMs are suitable for FL over wireless networks, including a broad overview of research challenges and opportunities.
  arXiv  Detail & Related papers  (2023-10-06T04:13:10Z)
• Bridging the Gap Between Foundation Models and Heterogeneous Federated Learning [9.198799314774437]
  Federated learning (FL) offers privacy-preserving decentralized machine learning, optimizing models at edge clients without sharing private data. Foundation models (FMs) have gained traction in the artificial intelligence (AI) community due to their exceptional performance across various tasks. We present an adaptive framework for Resource-aware Federated Foundation Models (RaFFM) to address these challenges.
  arXiv  Detail & Related papers  (2023-09-30T04:31:53Z)
• VideoGLUE: Video General Understanding Evaluation of Foundation Models [89.07145427268948]
  We evaluate video understanding capabilities of foundation models (FMs) using a carefully designed experiment protocol. We jointly profile FMs' hallmark and efficacy efficiency when adapting to general video understanding tasks.
  arXiv  Detail & Related papers  (2023-07-06T17:47:52Z)
• Improving and generalizing flow-based generative models with minibatch optimal transport [90.01613198337833]
  We introduce the generalized conditional flow matching (CFM) technique for continuous normalizing flows (CNFs) CFM features a stable regression objective like that used to train the flow in diffusion models but enjoys the efficient inference of deterministic flow models. A variant of our objective is optimal transport CFM (OT-CFM), which creates simpler flows that are more stable to train and lead to faster inference.
  arXiv  Detail & Related papers  (2023-02-01T14:47:17Z)
• Boosting Factorization Machines via Saliency-Guided Mixup [125.15872106335692]
  We present MixFM, inspired by Mixup, to generate auxiliary training data to boost Factorization machines (FMs) We also put forward a novel Factorization Machine powered by Saliency-guided Mixup (denoted as SMFM)
  arXiv  Detail & Related papers  (2022-06-17T09:49:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.