Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated Learning

• URL: http://arxiv.org/abs/2310.18285v4
• Date: Sun, 25 Feb 2024 02:00:07 GMT
• Title: Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated Learning
• Authors: Wenlong Deng, Christos Thrampoulidis, Xiaoxiao Li
• Abstract summary: Vision Transformers (ViT) and Visual Prompt Tuning (VPT) achieve state-of-the-art performance with improved efficiency in various computer vision tasks. We present a novel algorithm, SGPT, that integrates Generalized FL (GFL) and Personalized FL (PFL) approaches by employing a unique combination of both shared and group-specific prompts.
• Score: 49.72857433721424
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision Transformers (ViT) and Visual Prompt Tuning (VPT) achieve state-of-the-art performance with improved efficiency in various computer vision tasks. This suggests a promising paradigm shift of adapting pre-trained ViT models to Federated Learning (FL) settings. However, the challenge of data heterogeneity among FL clients presents a significant hurdle in effectively deploying ViT models. Existing Generalized FL (GFL) and Personalized FL (PFL) methods have limitations in balancing performance across both global and local data distributions. In this paper, we present a novel algorithm, SGPT, that integrates GFL and PFL approaches by employing a unique combination of both shared and group-specific prompts. This design enables SGPT to capture both common and group-specific features. A key feature of SGPT is its prompt selection module, which facilitates the training of a single global model capable of automatically adapting to diverse local client data distributions without the need for local fine-tuning. To effectively train the prompts, we utilize block coordinate descent (BCD), learning from common feature information (shared prompts), and then more specialized knowledge (group prompts) iteratively. Theoretically, we justify that learning the proposed prompts can reduce the gap between global and local performance. Empirically, we conduct experiments on both label and feature heterogeneity settings in comparison with state-of-the-art baselines, along with extensive ablation studies, to substantiate the superior performance of SGPT.

Related papers

• Mixture of Experts Made Personalized: Federated Prompt Learning for Vision-Language Models [7.810284483002312]
  We propose a novel framework that personalizes the prompt learning process through the lens of Mixture of Experts (MoE) pFedMoAP implements a local attention-based gating network that learns to generate enhanced text features for better alignment with local image data on the client. The results show that pFedMoAP consistently outperforms the state-of-the-art alternatives, underscoring its efficacy in personalizing prompt learning for CLIP.
  arXiv  Detail & Related papers  (2024-10-14T03:05:12Z)
• Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformation [12.19025665853089]
  In traditional Federated Learning approaches, the global model underperforms when faced with data heterogeneity. We propose a new PFL framework called FedPFT to address the mismatch problem while enhancing the quality of the feature extractor. Our experiments demonstrate that FedPFT outperforms state-of-the-art methods by up to 7.08%.
  arXiv  Detail & Related papers  (2024-07-23T02:52:52Z)
• FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learning [18.916282151435727]
  Heterogeneous Federated Learning (HtFL) has attracted attention due to its ability to support heterogeneous models and data. We introduce a novel HtFL approach called FedTGP, which leverages our Adaptive-margin-enhanced Contrastive Learning (ACL) to learn Trainable Global Prototypes (TGP) on the server.
  arXiv  Detail & Related papers  (2024-01-06T14:43:47Z)
• Inclusive Data Representation in Federated Learning: A Novel Approach Integrating Textual and Visual Prompt [12.869146009608816]
  We present Twin Prompt Federated learning (TPFL), a pioneering solution that integrates both visual and textual modalities. In order to tackle the data heterogeneity issues, we introduce the Augmented TPFL (ATPFL), which not only enhances the global knowledge acquisition of client models but also fosters the development of robust, compact models. The effectiveness of TPFL and ATPFL is substantiated by our extensive evaluations, consistently showing superior performance compared to all baselines.
  arXiv  Detail & Related papers  (2023-10-04T11:20:28Z)
• Personalized Federated Learning with Local Attention [5.018560254008613]
  Federated Learning (FL) aims to learn a single global model that enables the central server to help the model training in local clients without accessing their local data. Key challenge of FL is the heterogeneous label distribution and feature shift, which could lead to significant performance degradation of the learned models. We propose a simple yet effective algorithm, namely textbfpersonalized textbfFederated learning with textbfLocal textbfAttention (pFedLA) Two modules are proposed in pFedLA, i.e., the personalized
  arXiv  Detail & Related papers  (2023-04-02T20:10:32Z)
• Visual Prompt Based Personalized Federated Learning [83.04104655903846]
  We propose a novel PFL framework for image classification tasks, dubbed pFedPT, that leverages personalized visual prompts to implicitly represent local data distribution information of clients. Experiments on the CIFAR10 and CIFAR100 datasets show that pFedPT outperforms several state-of-the-art (SOTA) PFL algorithms by a large margin in various settings.
  arXiv  Detail & Related papers  (2023-03-15T15:02:15Z)
• Vertical Semi-Federated Learning for Efficient Online Advertising [50.18284051956359]
  Semi-VFL (Vertical Semi-Federated Learning) is proposed to achieve a practical industry application fashion for VFL. We build an inference-efficient single-party student model applicable to the whole sample space. New representation distillation methods are designed to extract cross-party feature correlations for both the overlapped and non-overlapped data.
  arXiv  Detail & Related papers  (2022-09-30T17:59:27Z)
• Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferring [104.19414150171472]
  Attributes skews the current federated learning (FL) frameworks from consistent optimization directions among the clients. We propose disentangled federated learning (DFL) to disentangle the domain-specific and cross-invariant attributes into two complementary branches. Experiments verify that DFL facilitates FL with higher performance, better interpretability, and faster convergence rate, compared with SOTA FL methods.
  arXiv  Detail & Related papers  (2022-06-14T13:12:12Z)
• Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning [86.59588262014456]
  Federated Learning (FL) is an emerging distributed learning paradigm under privacy constraint. We propose a data-free knowledge distillation method to fine-tune the global model in the server (FedFTG) Our FedFTG significantly outperforms the state-of-the-art (SOTA) FL algorithms and can serve as a strong plugin for enhancing FedAvg, FedProx, FedDyn, and SCAFFOLD.
  arXiv  Detail & Related papers  (2022-03-17T11:18:17Z)
• Heterogeneous Federated Learning via Grouped Sequential-to-Parallel Training [60.892342868936865]
  Federated learning (FL) is a rapidly growing privacy-preserving collaborative machine learning paradigm. We propose a data heterogeneous-robust FL approach, FedGSP, to address this challenge. We show that FedGSP improves the accuracy by 3.7% on average compared with seven state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-01-31T03:15:28Z)

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.