paper-with-me

Papers

Federated Representation Learning in the Under-Parameterized Regime

2024-06-07 · Renpu Liu, Cong Shen, Jing Yang

Federated representation learning (FRL) is a popular personalized federated learning (FL) framework where clients work together to train a common representation while retaining their personalized heads. Existing studies, however, largely focus on the over-parameterized regime. In this paper, we make the initial efforts to investigate FRL in the under-parameterized regime, where the FL model is insufficient to express the variations in all ground-truth models. We propose a novel FRL algorithm FLUTE, and theoretically characterize its sample complexity and convergence rate for linear models in the under-parameterized regime. To the best of our knowledge, this is the first FRL algorithm with provable performance guarantees in this regime. FLUTE features a data-independent random initialization and a carefully designed objective function that aids the distillation of subspace spanned by the global optimal representation from the misaligned local representations. On the technical side, we bridge low-rank matrix approximation techniques with the FL analysis, which may be of broad interest. We also extend FLUTE beyond linear representations. Experimental results demonstrate that FLUTE outperforms state-of-the-art FRL solutions in both synthetic and real-world tasks.

📄 PDF Abstract BibTeX arXiv:2406.04596

Code (2)

RenpuLiu/flute 공식 구현 pytorch
KarhouTam/FL-bench pytorch

Tasks

Federated LearningPersonalized Federated LearningRepresentation Learning

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

The Effect of Label Noise on the Information Content of Neural Representations

2025-10-07 · Ali Hussaini Umar, Franky Kevin Nando Tezoh, Jean Barbier, Santiago Acevedo 외 arxiv

In supervised classification tasks, models are trained to predict a label for each data point. In real-world datasets, these labels are often noisy due to annotation errors. While the impact of label noise on the perform…

FedExP: Speeding Up Federated Averaging via Extrapolation

2023-01-23 · Divyansh Jhunjhunwala, Shiqiang Wang, Gauri Joshi

Federated Averaging (FedAvg) remains the most popular algorithm for Federated Learning (FL) optimization due to its simple implementation, stateless nature, and privacy guarantees combined with secure aggregation. Recent…

Federated Learning

Least Squares Regression Can Exhibit Under-Parameterized Double Descent

2023-05-24 · Xinyue Li, Rishi Sonthalia

The relationship between the number of training data points, the number of parameters, and the generalization capabilities of models has been widely studied. Previous work has shown that double descent can occur in the o…

Denoisingregression

Personalized Federated Learning with Gaussian Processes

2021-06-29 · NeurIPS 2021 12 · Idan Achituve, Aviv Shamsian, Aviv Navon, Gal Chechik 외

Federated learning aims to learn a global model that performs well on client devices with limited cross-client communication. Personalized federated learning (PFL) further extends this setup to handle data heterogeneity …

Federated LearningGaussian ProcessesPersonalized Federated Learning

Implicit Bias of MSE Gradient Optimization in Underparameterized Neural Networks

2022-01-12 · ICLR 2022 4 · Benjamin Bowman, Guido Montufar

We study the dynamics of a neural network in function space when optimizing the mean squared error via gradient flow. We show that in the underparameterized regime the network learns eigenfunctions of an integral operato…