Saved in:
Bibliographic Details
Main Authors: Liu, Renpu, Shen, Cong, Yang, Jing
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.04596
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914875217805312
author Liu, Renpu
Shen, Cong
Yang, Jing
author_facet Liu, Renpu
Shen, Cong
Yang, Jing
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_04596
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Federated Representation Learning in the Under-Parameterized Regime
Liu, Renpu
Shen, Cong
Yang, Jing
Machine Learning
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.
title Federated Representation Learning in the Under-Parameterized Regime
topic Machine Learning
url https://arxiv.org/abs/2406.04596