PulseAugur
EN
LIVE 12:30:48

New methods advance personalized federated learning and unlearning

By PulseAugur Editorial · [7 sources] ·

Researchers have developed several new methods to enhance personalized federated learning (PFL), a technique that allows AI models to learn from distributed data while maintaining client-specific adaptations. CLoVE, for instance, uses client loss vector embeddings to identify and separate client clusters, optimizing cluster-specific models. pFedUL addresses federated unlearning within PFL by differentiating strategies for shared and personalized model layers to comply with privacy regulations like GDPR. Additionally, DC-CFL offers a single-round approach to clustered federated learning by analyzing data collaboration, and FedSPC introduces a shared parameter correction method to improve consistency in PFL models. AI

IMPACT These advancements in federated learning could enable more efficient and privacy-preserving AI model training on decentralized datasets.

RANK_REASON Multiple research papers published on arXiv detailing novel algorithms and methods for personalized and clustered federated learning.

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 7 sources. How we write summaries →

New methods advance personalized federated learning and unlearning

COVERAGE [7]

  1. arXiv cs.LG TIER_1 English(EN) · Seyed Salar Ghazi, Kaiwen Zhang, Mehdi feizi, Hans-Arno Jacobsen ·

    SCOPE-FL: A Strategy-proof Chain-based Optimal pareto efficient Federated Learning System

    arXiv:2606.18384v1 Announce Type: new Abstract: Hierarchical Federated Learning (HFL) enables scalable collaborative model training across distributed devices while preserving data privacy. However, existing HFL client selection mechanisms suffer from a fundamental strategic inef…

  2. arXiv cs.AI TIER_1 English(EN) · Davide Domini, Gianluca Aguzzi, Lorenzo Pellegrini, Mirko Viroli, Lukas Esterle ·

    C2FL: Clustered Continual Federated Learning under Spatial and Temporal Drift

    arXiv:2606.18003v1 Announce Type: cross Abstract: Collective Adaptive Systems (CAS) increasingly rely on machine learning to let each node learn from locally sensed data, aligning its behavior with the surrounding environment. Scaling this intelligence, however, raises fundamenta…

  3. arXiv cs.AI TIER_1 English(EN) · Lukas Esterle ·

    C2FL: Clustered Continual Federated Learning under Spatial and Temporal Drift

    Collective Adaptive Systems (CAS) increasingly rely on machine learning to let each node learn from locally sensed data, aligning its behavior with the surrounding environment. Scaling this intelligence, however, raises fundamental challenges: sensed data is often privacy-sensiti…

  4. arXiv cs.LG TIER_1 English(EN) · Sota Sugawara, Yuji Kawamata, Akihiro Toyoda, Tomoru Nakayama, Yukihiko Okada ·

    Single-Round Clustered Federated Learning via Data Collaboration Analysis for Non-IID Data

    arXiv:2601.09304v2 Announce Type: replace Abstract: Federated Learning (FL) enables distributed learning across multiple clients without sharing raw data. When statistical heterogeneity across clients is severe, Clustered Federated Learning (CFL) can im-prove performance by group…

  5. arXiv cs.AI TIER_1 English(EN) · Randeep Bhatia, Nikos Papadis, Murali Kodialam, TV Lakshman, Sayak Chakrabarty ·

    CLoVE: Personalized Federated Learning through Clustering of Loss Vector Embeddings

    arXiv:2506.22427v2 Announce Type: replace-cross Abstract: We propose CLoVE (Clustering of Loss Vector Embeddings), a novel algorithm for Clustered Federated Learning (CFL). In CFL, clients are naturally grouped into clusters based on their data distribution. However, identifying …

  6. arXiv cs.LG TIER_1 English(EN) · Zhuodong Liu, Xiangyu Li, Zhihao Zhang ·

    pFedUL: Layer-Aware Federated Unlearning for Personalized Federated Learning

    arXiv:2606.16304v1 Announce Type: new Abstract: Federated unlearning (FU) enables the removal of specific data contributions from federated learning (FL) models to comply with regulations such as the General Data Protection Regulation (GDPR). However, most existing FU methods are…

  7. arXiv cs.LG TIER_1 English(EN) · Kannanthodath Induchoodan Ajay Menon, Christian Prehofer, Yunfei Xu, Toru Hirano ·

    FedSPC: Shared Parameter Correction for Personalized Federated Learning

    arXiv:2606.13748v1 Announce Type: new Abstract: Personalized federated learning (PFL) is one of the important approaches in federated learning for addressing statistical heterogeneity while enabling client-specific adaptation. Many PFL methods split the model into shared and pers…

RELATED ENTITIES

RELATED TOPICS