Personalized Federated Instruction Tuning via Neural Architecture Search
- URL: http://arxiv.org/abs/2402.16919v1
- Date: Mon, 26 Feb 2024 06:29:05 GMT
- Title: Personalized Federated Instruction Tuning via Neural Architecture Search
- Authors: Pengyu Zhang, Yingbo Zhou, Ming Hu, Junxian Feng, Jiawen Weng, and
Mingsong Chen
- Abstract summary: Federated Instruction Tuning (FIT) has shown the ability to achieve collaborative model instruction tuning among massive data owners without sharing private data.
Due to the varying data distribution and preferences among data owners, FIT cannot adapt to the personalized data of individual owners.
We propose a novel Personalized Federated Instruction Tuning (PerFIT) framework based on architecture search.
- Score: 25.19100691411643
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Federated Instruction Tuning (FIT) has shown the ability to achieve
collaborative model instruction tuning among massive data owners without
sharing private data. However, it still faces two key challenges, i.e., data
and resource heterogeneity. Due to the varying data distribution and
preferences among data owners, FIT cannot adapt to the personalized data of
individual owners. Moreover, clients with superior computational abilities are
constrained since they need to maintain the same fine-tuning architecture as
the weaker clients. To address these issues, we propose a novel Personalized
Federated Instruction Tuning (PerFIT) framework based on architecture search.
Specifically, PerFIT allows each client to search for a personalized
architecture by expanding the trainable parameter space of the global model
followed by pruning the parameters to the original state. This procedure allows
personalized instruction fine-tuning within expanded parameter spaces,
concurrently preserving the same number of trainable parameters. Furthermore,
to release the abilities of heterogeneous computational resources and enhance
the performance of personalization on local data, we exploit personalized
parameter-wise aggregation. The evaluation with multiple LLMs non-IID scenarios
demonstrates that compared to the state-of-the-art FIT methods, our approach
can achieve up to a 23% decrease in perplexity.
Related papers
- MAP: Model Aggregation and Personalization in Federated Learning with Incomplete Classes [49.22075916259368]
In some real-world applications, data samples are usually distributed on local devices.
In this paper, we focus on a special kind of Non-I.I.D. scene where clients own incomplete classes.
Our proposed algorithm named MAP could simultaneously achieve the aggregation and personalization goals in FL.
arXiv Detail & Related papers (2024-04-14T12:22:42Z) - FewFedPIT: Towards Privacy-preserving and Few-shot Federated Instruction Tuning [54.26614091429253]
Federated instruction tuning (FedIT) is a promising solution, by consolidating collaborative training across multiple data owners.
FedIT encounters limitations such as scarcity of instructional data and risk of exposure to training data extraction attacks.
We propose FewFedPIT, designed to simultaneously enhance privacy protection and model performance of federated few-shot learning.
arXiv Detail & Related papers (2024-03-10T08:41:22Z) - Profit: Benchmarking Personalization and Robustness Trade-off in
Federated Prompt Tuning [40.16581292336117]
In many applications of federated learning (FL), clients desire models that are personalized using their local data, yet are also robust in the sense that they retain general global knowledge.
It is critical to understand how to navigate this personalization vs robustness trade-off when designing federated systems.
arXiv Detail & Related papers (2023-10-06T23:46:33Z) - Efficient Model Personalization in Federated Learning via
Client-Specific Prompt Generation [38.42808389088285]
Federated learning (FL) emerges as a decentralized learning framework which trains models from multiple distributed clients without sharing their data to preserve privacy.
We propose a novel personalized FL framework of client-specific Prompt Generation (pFedPG)
pFedPG learns to deploy a personalized prompt generator at the server for producing client-specific visual prompts that efficiently adapts frozen backbones to local data distributions.
arXiv Detail & Related papers (2023-08-29T15:03:05Z) - Towards Personalized Federated Learning via Heterogeneous Model
Reassembly [84.44268421053043]
pFedHR is a framework that leverages heterogeneous model reassembly to achieve personalized federated learning.
pFedHR dynamically generates diverse personalized models in an automated manner.
arXiv Detail & Related papers (2023-08-16T19:36:01Z) - FedJETs: Efficient Just-In-Time Personalization with Federated Mixture
of Experts [48.78037006856208]
FedJETs is a novel solution by using a Mixture-of-Experts (MoE) framework within a Federated Learning (FL) setup.
Our method leverages the diversity of the clients to train specialized experts on different subsets of classes, and a gating function to route the input to the most relevant expert(s)
Our approach can improve accuracy up to 18% in state of the art FL settings, while maintaining competitive zero-shot performance.
arXiv Detail & Related papers (2023-06-14T15:47:52Z) - Partially Personalized Federated Learning: Breaking the Curse of Data
Heterogeneity [8.08257664697228]
We present a partially personalized formulation of Federated Learning (FL) that strikes a balance between the flexibility of personalization and cooperativeness of global training.
In our framework, we split the variables into global parameters, which are shared across all clients, and individual local parameters, which are kept private.
We prove that under the right split of parameters, it is possible to find global parameters that allow each client to fit their data perfectly, and refer to the obtained problem as overpersonalized.
arXiv Detail & Related papers (2023-05-29T17:54:50Z) - 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) - Personalizing or Not: Dynamically Personalized Federated Learning with
Incentives [37.42347737911428]
We propose personalized federated learning (FL) for learning personalized models without sharing private data.
We introduce the personalization rate, measured as the fraction of clients willing to train personalized models, into federated settings and propose DyPFL.
This technique incentivizes clients to participate in personalizing local models while allowing the adoption of the global model when it performs better.
arXiv Detail & Related papers (2022-08-12T09:51:20Z) - Personalized Federated Learning with First Order Model Optimization [76.81546598985159]
We propose an alternative to federated learning, where each client federates with other relevant clients to obtain a stronger model per client-specific objectives.
We do not assume knowledge of underlying data distributions or client similarities, and allow each client to optimize for arbitrary target distributions of interest.
Our method outperforms existing alternatives, while also enabling new features for personalized FL such as transfer outside of local data distributions.
arXiv Detail & Related papers (2020-12-15T19:30:29Z)
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.