# A Randomized Zeroth-Order Hierarchical Framework for Heterogeneous Federated Learning

Source: [A Randomized Zeroth-Order Hierarchical Framework for Heterogeneous Federated Learning](<https://www.sota2.com/research/paper/68fa5e351e209131ce9e058a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T18:39:59.265Z

Authors: Yuyang Qiu, Kibaek Kim, Farzad Yousefian

Published: 2025-04-02T15:44:59.000Z

## Abstract

Heterogeneity in federated learning (FL) is a critical and challenging aspect that significantly impacts model performance and convergence. In this paper, we propose a novel framework by formulating heterogeneous FL as a hierarchical optimization problem. This new framework captures both local and global training processes through a bilevel formulation and is capable of the following: (i) addressing client heterogeneity through a personalized learning framework; (ii) capturing the pre-training process on the server side; (iii) updating the global model through nonstandard aggregation; (iv) allowing for nonidentical local steps; and (v) capturing clients' local constraints. We design and analyze an implicit zeroth-order FL method (ZO-HFL), equipped with nonasymptotic convergence guarantees for both the server-agent and the individual client-agents, and asymptotic guarantees for both the server-agent and client-agents in an almost sure sense. Notably, our method does not rely on standard assumptions in heterogeneous FL, such as the bounded gradient dissimilarity condition. We implement our method on image classification tasks and compare with other methods under different heterogeneous settings.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2504.01839>)

[PDF](<https://arxiv.org/pdf/2504.01839.pdf>)
