Probabilistic Federated Prompt-Tuning with Non-IID and Imbalanced Data

• URL: http://arxiv.org/abs/2502.19752v1
• Date: Thu, 27 Feb 2025 04:31:34 GMT
• Title: Probabilistic Federated Prompt-Tuning with Non-IID and Imbalanced Data
• Authors: Pei-Yau Weng, Minh Hoang, Lam M. Nguyen, My T. Thai, Tsui-Wei Weng, Trong Nghia Hoang,
• Abstract summary: Fine-tuning pre-trained models is a popular approach in machine learning for solving complex tasks with moderate data.<n>Fine-tuning the entire pre-trained model is ineffective in federated data scenarios where local data distributions are diversely skewed.<n>Our approach transforms federated learning into a distributed set modeling task, aggregating diverse sets of prompts to globally fine-tune the pre-trained model.
• Score: 35.47385526394076
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Fine-tuning pre-trained models is a popular approach in machine learning for solving complex tasks with moderate data. However, fine-tuning the entire pre-trained model is ineffective in federated data scenarios where local data distributions are diversely skewed. To address this, we explore integrating federated learning with a more effective prompt-tuning method, optimizing for a small set of input prefixes to reprogram the pre-trained model's behavior. Our approach transforms federated learning into a distributed set modeling task, aggregating diverse sets of prompts to globally fine-tune the pre-trained model. We benchmark various baselines based on direct adaptations of existing federated model aggregation techniques and introduce a new probabilistic prompt aggregation method that substantially outperforms these baselines. Our reported results on a variety of computer vision datasets confirm that the proposed method is most effective to combat extreme data heterogeneity in federated learning.

Related papers

• Federated Learning for Diffusion Models [12.46092849473786]
  Diffusion models are powerful generative models that can produce highly realistic samples for various tasks. We propose FedDDPM-Federated Learning with Denoising Diffusion Probabilistic Models. We provide a rigorous convergence analysis of FedDDPM and propose an enhanced algorithm, FedDDPM+, to reduce training overheads.
  arXiv  Detail & Related papers  (2025-03-09T03:41:10Z)
• Multiply Robust Estimation for Local Distribution Shifts with Multiple Domains [9.429772474335122]
  We focus on scenarios where data distributions vary across multiple segments of the entire population. We propose a two-stage multiply robust estimation method to improve model performance on each individual segment. Our method is designed to be implemented with commonly used off-the-shelf machine learning models.
  arXiv  Detail & Related papers  (2024-02-21T22:01:10Z)
• Federated Learning with Projected Trajectory Regularization [65.6266768678291]
  Federated learning enables joint training of machine learning models from distributed clients without sharing their local data. One key challenge in federated learning is to handle non-identically distributed data across the clients. We propose a novel federated learning framework with projected trajectory regularization (FedPTR) for tackling the data issue.
  arXiv  Detail & Related papers  (2023-12-22T02:12:08Z)
• Consistency Regularization for Generalizable Source-free Domain Adaptation [62.654883736925456]
  Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset. Existing SFDA methods ONLY assess their adapted models on the target training set, neglecting the data from unseen but identically distributed testing sets. We propose a consistency regularization framework to develop a more generalizable SFDA method.
  arXiv  Detail & Related papers  (2023-08-03T07:45:53Z)
• Tackling Computational Heterogeneity in FL: A Few Theoretical Insights [68.8204255655161]
  We introduce and analyse a novel aggregation framework that allows for formalizing and tackling computational heterogeneous data. Proposed aggregation algorithms are extensively analyzed from a theoretical, and an experimental prospective.
  arXiv  Detail & Related papers  (2023-07-12T16:28:21Z)
• Deep Unfolding-based Weighted Averaging for Federated Learning in Heterogeneous Environments [11.023081396326507]
  Federated learning is a collaborative model training method that iterates model updates by multiple clients and aggregation of the updates by a central server. To adjust the aggregation weights, this paper employs deep unfolding, which is known as the parameter tuning method. The proposed method can handle large-scale learning models with the aid of pretrained models such as it can perform practical real-world tasks.
  arXiv  Detail & Related papers  (2022-12-23T08:20:37Z)
• Dataless Knowledge Fusion by Merging Weights of Language Models [51.8162883997512]
  Fine-tuning pre-trained language models has become the prevalent paradigm for building downstream NLP models. This creates a barrier to fusing knowledge across individual models to yield a better single model. We propose a dataless knowledge fusion method that merges models in their parameter space.
  arXiv  Detail & Related papers  (2022-12-19T20:46:43Z)
• DRFLM: Distributionally Robust Federated Learning with Inter-client Noise via Local Mixup [58.894901088797376]
  federated learning has emerged as a promising approach for training a global model using data from multiple organizations without leaking their raw data. We propose a general framework to solve the above two challenges simultaneously. We provide comprehensive theoretical analysis including robustness analysis, convergence analysis, and generalization ability.
  arXiv  Detail & Related papers  (2022-04-16T08:08:29Z)
• Deep Ensembles for Low-Data Transfer Learning [21.578470914935938]
  We study different ways of creating ensembles from pre-trained models. We show that the nature of pre-training itself is a performant source of diversity. We propose a practical algorithm that efficiently identifies a subset of pre-trained models for any downstream dataset.
  arXiv  Detail & Related papers  (2020-10-14T07:59:00Z)
• Learning Diverse Representations for Fast Adaptation to Distribution Shift [78.83747601814669]
  We present a method for learning multiple models, incorporating an objective that pressures each to learn a distinct way to solve the task. We demonstrate our framework's ability to facilitate rapid adaptation to distribution shift.
  arXiv  Detail & Related papers  (2020-06-12T12:23:50Z)

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.