paper-with-me

홈 › Papers

Closing the Alignment-Maturity Gap in Federated Prototype Learning

2026-06-01 · Mario Casado-Diez, Alejandro Dopico-Castro, Verónica Bolón-Canedo, Bertha Guijarro-Berdiñas arxiv

Learning discriminative visual representations from distributed, heterogeneous data is a fundamental challenge in Federated Learning (FL). Prototype-based methods address statistical heterogeneity by sharing class-level representations across clients but create a distance-dependent gradient pressure that is particularly severe during early training rounds: alignment pressure applied to immature global prototypes, aggregated from noisy local representations, generates large gradients that suppress the emergence of local discriminative structure. The result is a poorly organized embedding space and degraded recognition performance, particularly under severe non-IID conditions. We propose FedSAP, a framework that stabilises federated representation learning through two complementary mechanisms: a deterministic alignment curriculum that delays global alignment until local representations become stable and a geometry-driven proxy separation loss that enforces inter-class structure on the unit hypersphere using the existing prototype bank without introducing additional parameters or communication overhead. Together, these mechanisms produce compact, well-separated class clusters without altering the underlying communication protocol between federation's participants. Experiments across three benchmarks and varying degrees of heterogeneity show gains of up to 4 percentage points over the prototype-based baselines evaluated, with improvements most pronounced under high heterogeneity. The representational nature of our framework further enables a straightforward extension to semi-supervised settings, where unlabelled data is incorporated with minimal modification, underscoring the generality of scheduled alignment as a design principle.

📄 PDF Abstract BibTeX arXiv:2606.02172

Code (0)

등록된 구현이 없습니다.

Tasks

Representation LearningFederated Learning

Similar Papers 제목 키워드 기반

FedAli: Personalized Federated Learning with Aligned Prototypes through Optimal Transport

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

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…

Activity RecognitionFederated LearningHuman Activity RecognitionPersonalized Federated Learning

RefProtoFL: Communication-Efficient Federated Learning via External-Referenced Prototype Alignment

2026-01-21 · Hongyue Wu, Hangyu Li, Guodong Fan, Haoran Zhu 외 arxiv

Federated learning (FL) enables collaborative model training without sharing raw data in edge environments, but is constrained by limited communication bandwidth and heterogeneous client data distributions. Prototype-bas…

Federated Learning

Mitigating Domain Shift in Federated Learning via Intra- and Inter-Domain Prototypes

2025-01-15 · Huy Q. Le, Ye Lin Tun, Yu Qiao, Minh N. H. Nguyen 외

Federated Learning (FL) has emerged as a decentralized machine learning technique, allowing clients to train a global model collaboratively without sharing private data. However, most FL studies ignore the crucial challe…

Federated Learning

From Coordinate Matching to Structural Alignment: Rethinking Prototype Alignment in Heterogeneous Federated Learning

2026-05-07 · Xinghao Wu, Jianwei Niu, Guogang Zhu, Xuefeng Liu 외 arxiv

Heterogeneous federated learning (HtFL) aims to enable collaboration among clients that differ in both data distributions and model architectures. Prototype-based methods, which communicate class-level feature centers (p…

Federated Learning

FedDAP: Domain-Aware Prototype Learning for Federated Learning under Domain Shift

2026-04-08 · Huy Q. Le, Loc X. Nguyen, Yu Qiao, Seong Tae Kim 외 arxiv

Federated Learning (FL) enables decentralized model training across multiple clients without exposing private data, making it ideal for privacy-sensitive applications. However, in real-world FL scenarios, clients often h…

Federated Learning