paper-with-me

Papers

FedAli: Personalized Federated Learning with Aligned Prototypes through Optimal Transport

2024-11-15 · Sannara Ek, Kaile Wang, François Portet, Philippe Lalanda, Jiannong Cao

Federated Learning (FL) enables collaborative, personalized model training across multiple devices without sharing raw data, making it ideal for pervasive computing applications that optimize user-centric performances in diverse environments. However, data heterogeneity among clients poses a significant challenge, leading to inconsistencies among trained client models and reduced performance. To address this, we introduce the Alignment with Prototypes (ALP) layers, which align incoming embeddings closer to learnable prototypes through an optimal transport plan. During local training, the ALP layer updates local prototypes and aligns embeddings toward global prototypes aggregated from all clients using our novel FL framework, Federated Alignment (FedAli). For model inferences, embeddings are guided toward local prototypes to better reflect the client's local data distribution. We evaluate FedAli on heterogeneous sensor-based human activity recognition and vision benchmark datasets, demonstrating that it outperforms existing FL strategies. We publicly release our source code to facilitate reproducibility and furthered research.

📄 PDF Abstract BibTeX arXiv:2411.10595

Code (1)

getalp/FedAli 공식 구현 tf

Tasks

Activity RecognitionFederated LearningHuman Activity RecognitionPersonalized Federated Learning

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Aggregation Alignment for Federated Learning with Mixture-of-Experts under Data Heterogeneity

2026-03-22 · Zihan Fang, Qianru Wang, Haonan An, Zheng Lin 외 arxiv

Large language models (LLMs) increasingly adopt Mixture-of-Experts (MoE) architectures to scale model capacity while reducing computation. Fine-tuning these MoE-based LLMs often requires access to distributed and privacy…

Federated Learning

A State Alignment-Centric Approach to Federated System Identification: The FedAlign Framework

2025-03-15 · Ertuğrul Keçeci, Müjde Güzelkaya, Tufan Kumbasar

This paper presents FedAlign, a Federated Learning (FL) framework particularly designed for System Identification (SYSID) tasks by aligning state representations. Local workers can learn State-Space Models (SSMs) with eq…

Federated LearningState Space Models

FedAlign: Federated Domain Generalization with Cross-Client Feature Alignment

2025-01-26 · Sunny Gupta, Vinay Sutar, Varunav Singh, Amit Sethi

Federated Learning (FL) offers a decentralized paradigm for collaborative model training without direct data sharing, yet it poses unique challenges for Domain Generalization (DG), including strict privacy constraints, n…

DiversityDomain GeneralizationFederated LearningPrivacy Preserving

Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning

2021-11-28 · CVPR 2022 1 · Matias Mendieta, Taojiannan Yang, Pu Wang, Minwoo Lee 외

Federated learning (FL) is a promising strategy for performing privacy-preserving, distributed learning with a network of clients (i.e., edge devices). However, the data distribution among clients is often non-IID in nat…

Federated LearningPrivacy Preserving

FedHPro: Federated Hyper-Prototype Learning via Gradient Matching

2026-05-13 · Huan Wang, Jun Shen, Haoran Li, Zhenyu Yang 외 arxiv

Federated Learning (FL) enables collaborative training of distributed clients while protecting privacy. To enhance generalization capability in FL, prototype-based FL is in the spotlight, since shared global prototypes o…

Contrastive LearningFederated Learning