paper-with-me

홈 › Papers

FedConv: Enhancing Convolutional Neural Networks for Handling Data Heterogeneity in Federated Learning

2023-10-06 · Peiran Xu, Zeyu Wang, Jieru Mei, Liangqiong Qu, Alan Yuille, Cihang Xie, Yuyin Zhou

Federated learning (FL) is an emerging paradigm in machine learning, where a shared model is collaboratively learned using data from multiple devices to mitigate the risk of data leakage. While recent studies posit that Vision Transformer (ViT) outperforms Convolutional Neural Networks (CNNs) in addressing data heterogeneity in FL, the specific architectural components that underpin this advantage have yet to be elucidated. In this paper, we systematically investigate the impact of different architectural elements, such as activation functions and normalization layers, on the performance within heterogeneous FL. Through rigorous empirical analyses, we are able to offer the first-of-its-kind general guidance on micro-architecture design principles for heterogeneous FL. Intriguingly, our findings indicate that with strategic architectural modifications, pure CNNs can achieve a level of robustness that either matches or even exceeds that of ViTs when handling heterogeneous data clients in FL. Additionally, our approach is compatible with existing FL techniques and delivers state-of-the-art solutions across a broad spectrum of FL benchmarks. The code is publicly available at https://github.com/UCSC-VLAA/FedConv

📄 PDF Abstract BibTeX arXiv:2310.04412

Code (1)

ucsc-vlaa/fedconv 공식 구현 pytorch

Tasks

Federated Learning

Methods 이 논문이 사용한 방법론

Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Adam 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

FedConv: A Learning-on-Model Paradigm for Heterogeneous Federated Clients

2025-02-28 · Leming Shen, Qiang Yang, Kaiyan Cui, Yuanqing Zheng 외

Federated Learning (FL) facilitates collaborative training of a shared global model without exposing clients' private data. In practical FL systems, clients (e.g., edge servers, smartphones, and wearables) typically have…

Federated Learning

A Federated Learning Framework for Handling Subtype Confounding and Heterogeneity in Large-Scale Neuroimaging Diagnosis

2025-08-08 · Xinglin Zhao, Yanwen Wang, Xiaobo Liu, Yanrong Hao 외 arxiv

Computer-aided diagnosis (CAD) systems play a crucial role in analyzing neuroimaging data for neurological and psychiatric disorders. However, small-sample studies suffer from low reproducibility, while large-scale datas…

Federated Learning

Decentralized Personalized Federated Learning

2024-06-10 · Salma Kharrat, Marco Canini, Samuel Horvath

This work tackles the challenges of data heterogeneity and communication limitations in decentralized federated learning. We focus on creating a collaboration graph that guides each client in selecting suitable collabora…

Federated LearningPersonalized Federated Learning

Handling Spatial-Temporal Data Heterogeneity for Federated Continual Learning via Tail Anchor

2025-01-01 · CVPR 2025 1 · Hao Yu, Xin Yang, Le Zhang, Hanlin Gu 외

Federated Continual Learning (FCL) allows each client to continually update its knowledge from task streams, enhancing the applicability of federated learning in real-world scenarios. However, FCL needs to address no…

Continual LearningFederated LearningPrototype Selection

H-GCN: A Graph Convolutional Network Accelerator on Versal ACAP Architecture

2022-06-28 · Chengming Zhang, Tong Geng, Anqi Guo, Jiannan Tian 외

Graph Neural Networks (GNNs) have drawn tremendous attention due to their unique capability to extend Machine Learning (ML) approaches to applications broadly-defined as having unstructured data, especially graphs. Compa…

BIG-bench Machine Learning