Skip to content
Open access

Consensus Memory Alignment for Effective Knowledge Transfer in Personalized Federated Learning

2026 · IEEE Transactions on Cognitive Communications and Networking · Vol 12, pp. 12302-12315 · 0 citations · 42 references

TL;DR

Extensive experiments show that FedAvg+FDA outperforms leading PFL methods in terms of effectiveness, stability, and fairness, and theoretical analysis provides generalization guarantees supporting the effectiveness of FDA in facilitating server-to-client knowledge transfer.

Abstract

Personalized Federated Learning (PFL) addresses performance degradation in non-IID settings by preserving personalized local models. However, the inherent reinitialization of local models in each communication round weakens cross-client knowledge transfer, which disrupts the balance between global and local knowledge. This imbalance restricts the utilization of shared representations, resulting in biased feature extraction that ultimately limits the model’s personalization performance. To solve this problem, we propose Feature Distribution Alignment (FDA), a general FL framework that enhances collaborative knowledge transfer. It consists of two components, namely Consensus Knowledge Guidance (CKG) and Local Knowledge Memory (LKM). CKG employs a domain adversarial approach adapted to FL settings, guiding local feature extractors toward globally consistent representations. LKM retains historical local features via attention-based fusion and mutual information maximization, enhancing feature alignment while reducing redundancy. This combined mechanism ensures the persistent retention of prior knowledge in local models despite continuous global model updates. By integrating these components, the FDA enables local feature extractors to better align with global knowledge while maintaining personalization. This design effectively balances global and local knowledge while improving local model performance. Theoretical analysis provides generalization guarantees supporting the effectiveness of FDA in facilitating server-to-client knowledge transfer. Extensive experiments on four datasets under three statistically heterogeneous settings show that FedAvg+FDA outperforms leading PFL methods in terms of effectiveness, stability, and fairness. Our code is available at https://github.com/NiantaoZ/FedFDA.

Read PDF

Similar papers

Open access 2026

Toward Communication-Efficient Adversarial Federated Learning for Robust Edge Intelligence

Federated learning (FL) enables decentralized model training without sharing raw data but remains vulnerable to adversarial attacks and often suffers from performance degradation under non-IID data distributions. By analyzing vanilla knowledge distillation (VKD) and adversarial knowledge distillation (AKD), we observe...

Yu Qiao, Apurba Adhikary, Huy Q. Le et al. · 0 citations
#federated learning Book Open access Nov 2026

Release the Potential of Relative Feature Consistency for Data Heterogeneous Federated Learning

Federated Learning is a promising paradigm to achieve privacy-preserving collaborative training. However, its performance degrades severely under data heterogeneity. A main obstacle is the divergent local representations induced by data heterogeneity, which will degrade the quality of the aggregated global representati...

Yi-Bin Wang, Yu-Can Zhou, Xiao-Yan Gu et al. · 0 citations
#machine learning Preprint Oct 2026

Is High Local Accuracy Enough? Geometric Consensus with Support-Adaptive Statistical Personalization for Federated Learning

Real-world deployment of personalized federated learning (PFL) requires adapting to heterogeneous clients while preserving recognition performance beyond local distributions. However, high local accuracy can conceal failures on locally rare or absent classes. Effective personalization should therefore strengthen global...

Jun-Yu Lin, Bo-Song Qi, Pengcheng Shi et al. · 0 citations
#machine learning Preprint Sep 2026

Personalized Federated Learning through Global Knowledge Distillation and Local Head Adaptation

Component-wise diagnostics and convergence results support the role of persistent heads and distillation-guided local optimization under label-skewed data and suggest that pFedKDH obtains the best accuracy in most settings.

Polycarpo Souza, José Mairton Barros da Silva, C. Cavalcante · 0 citations

EMD-guided adaptive decoupled knowledge distillation for federated meta-learning under data heterogeneity

FedML-DKD is proposed, a robust framework that integrates adaptive Decoupled Knowledge Distillation with federated meta-learning and introduces a heterogeneity-aware weighting mechanism based on Earth Mover’s Distance that helps prevent overfitting to biased local data while improving the reliability of knowledge trans...

De-Bao Wang, Shao-Peng Guan · 0 citations
Conference Open access 2026

KT-pFL: A Personalized Federated Learning Model Based on Knowledge Transfer

. To address the issues of data privacy protection and the difficulty of federated learning meeting personalized needs in heterogeneous (non-IID) scenarios, this paper proposes a personalized federated learning model based on knowledge transfer, KT-pFL, and completes its experimental reproduction and verification. This...

Chen-Rui Li · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.