Pith. sign in

REVIEW 29 cited by

Adaptive Personalized Federated Learning

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2003.13461 v3 pith:HDXWR2BA submitted 2020-03-30 cs.LG cs.DCstat.ML

Yuyang Deng , Mohammad Mahdi Kamani , Mehrdad Mahdavi This is my paper
classification cs.LGcs.DCstat.ML
keywords modelsfederatedgloballearninglocalpersonalizedadaptivegeneralization
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Investigation of the degree of personalization in federated learning algorithms has shown that only maximizing the performance of the global model will confine the capacity of the local models to personalize. In this paper, we advocate an adaptive personalized federated learning (APFL) algorithm, where each client will train their local models while contributing to the global model. We derive the generalization bound of mixture of local and global models, and find the optimal mixing parameter. We also propose a communication-efficient optimization method to collaboratively learn the personalized models and analyze its convergence in both smooth strongly convex and nonconvex settings. The extensive experiments demonstrate the effectiveness of our personalization schema, as well as the correctness of established generalization theories.

Discussion (0). Sign in to comment.

Forward citations

Cited by 29 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Clipping Makes Distributed and Federated Asynchronous SGD Robust to Stragglers

    cs.LG 2026-06 unverdicted novelty 7.0 of 10

    Gradient clipping eliminates the dependence on maximum delay in the oracle complexity of asynchronous SGD, yielding convergence in expectation and high probability under sub-Weibull gradient noise.

  2. Collaborative Yet Personalized Policy Training: Single-Timescale Federated Actor-Critic

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    A federated actor-critic framework lets agents share a linear subspace representation for policies while maintaining personalized local actors and critics, achieving critic error and policy gradient convergence rates ...

  3. FedOBP: Federated Optimal Brain Personalization through Cloud-Edge Element-wise Decoupling

    cs.LG 2026-04 unverdicted novelty 7.0 of 10

    FedOBP introduces a quantile-thresholded importance score based on a federated first-order Taylor approximation to select a small set of parameters for personalization, claiming better performance than prior PFL methods.

  4. Unlocking Multi-Site Clinical Data: A Federated Approach to Privacy-First Child Autism Behavior Analysis

    cs.CV 2026-04 unverdicted novelty 7.0 of 10

    A two-layer privacy system using skeletal abstraction and federated learning enables multi-site training for child autism behavior recognition and outperforms standard federated baselines on the MMASD benchmark.

  5. On the Convergence Rates of Federated Q-Learning across Heterogeneous Environments

    cs.LG 2024-09 unverdicted novelty 7.0 of 10

    Federated Q-learning in heterogeneous environments achieves linear speedup in K agents for sampling error but is limited to Θ(E/T) convergence when averaging every E steps, with a two-phase error decay-then-rise behav...

  6. FeDepth: Federated Learning for Depth Estimation under Robot Heterogeneity

    cs.RO 2026-08 conditional novelty 6.0 of 10

    FeDepth assigns each robot client to multiple clusters using frozen-encoder descriptors and Jeffreys divergence, improving federated depth estimation over hard-clustering baselines in the HPE scenario while performing...

  7. Tuning-Free Efficient Estimation for Multi-Source Data via Covariance-Aware Shrinkage

    stat.ME 2026-06 unverdicted novelty 6.0 of 10

    Proposes a covariance-aware tuning-free shrinkage framework and sequential algorithm for multi-source estimation that attains oracle risk asymptotically and improves on single-step methods.

  8. Range Penalization: Theoretical Insights with Applications in Federated Learning

    stat.ML 2026-06 unverdicted novelty 6.0 of 10

    Introduces range penalization for federated linear models that identifies shared weights and performs polar clustering on personalized features, supported by new nonasymptotic proofs and a fast optimization algorithm.

  9. Closing the Alignment-Maturity Gap in Federated Prototype Learning

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    FedSAP stabilizes federated prototype learning via a deterministic alignment curriculum and proxy separation loss, reporting up to 4 percentage point gains under high heterogeneity across three benchmarks.

  10. COSMOS: Model-Agnostic Personalized Federated Learning with Clustered Server Models and Pseudo-Label-Only Communication

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    COSMOS clusters clients via pseudo-label predictions on public data, trains cluster-specific server models, and distills them to clients, claiming exponential personalization risk contraction and outperforming model-a...

  11. COSMOS: Model-Agnostic Personalized Federated Learning with Clustered Server Models and Pseudo-Label-Only Communication

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    COSMOS performs model-agnostic personalized federated learning via server-side clustering on pseudo-label predictions and distillation of cluster models, claiming exponential personalization risk contraction.

  12. Personalized Digital Health Modeling with Adaptive Support Users

    cs.AI 2026-05 unverdicted novelty 6.0 of 10

    A framework for personalizing digital health models by jointly learning adaptive weights on support users, using similarity-weighted transfer from similar users and contrastive regularization from dissimilar users to ...

  13. Personalized Digital Health Modeling with Adaptive Support Users

    cs.AI 2026-05 unverdicted novelty 6.0 of 10

    A new framework trains personal digital health models using adaptive weights on support users including dissimilar ones, achieving up to 25% lower RMSE in low-data settings.

  14. A Taxonomy and Resolution Strategy for Client-Level Disagreements in Federated Learning

    cs.DC 2026-04 unverdicted novelty 6.0 of 10

    A taxonomy of client-level disagreements in federated learning is presented together with a multi-track resolution strategy that enforces strict exclusion via isolated update paths, shown to handle permanent, temporal...

  15. Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models

    cs.LG 2026-04 unverdicted novelty 6.0 of 10

    Bidirectional Manifold Consistency (BMC) is a geometric, training-free metric that quantifies stability of reasoning trajectories in diffusion LLMs to enable self-verification, rejection sampling, and alignment withou...

  16. Collaborative and Efficient Fine-tuning: Leveraging Task Similarity

    cs.LG 2026-02 conditional novelty 6.0 of 10

    CoLoRA shares a low-rank adapter pair across users plus a small personal matrix, improving fine-tuning for similar tasks and providing a recovery guarantee.

  17. Federated Multi-Task Clustering

    cs.LG 2025-12 unverdicted novelty 6.0 of 10

    FMTC learns personalized clustering models on clients and uses server-side tensor low-rank regularization to capture shared structure across heterogeneous clients in a privacy-preserving federated setting.

  18. Fed-REACT: Federated Representation Learning for Heterogeneous and Evolving Data

    cs.LG 2025-09 conditional novelty 6.0 of 10

    Fed-REACT first trains a shared encoder, then repeatedly clusters clients by smoothed task-model weights, improving federated learning accuracy on heterogeneous, non-stationary time series.

  19. A Model-agnostic Strategy to Mitigate Embedding Degradation in Personalized Federated Recommendation

    cs.IR 2025-08 conditional novelty 6.0 of 10

    PLGC combines NTK-weighted local-global item embedding mixing with a Barlow Twins-style redundancy reduction loss to lessen embedding degradation in personalized federated recommendation.

  20. Flexible Personalized Split Federated Learning for On-Device Fine-Tuning of Foundation Models

    cs.DC 2025-08 conditional novelty 6.0 of 10

    FlexP-SFL fine-tunes foundation models on resource-constrained devices through personalized split learning without parameter aggregation, improving accuracy and cutting wall-clock time and communication versus federat...

  21. COSMOS: Model-Agnostic Personalized Federated Learning with Clustered Server Models and Pseudo-Label-Only Communication

    cs.LG 2026-05 unverdicted novelty 5.5 of 10

    COSMOS personalizes federated learning across heterogeneous client models via server-side clustering and distillation using only pseudo-labels, with claimed exponential personalization risk contraction.

  22. Separate Aggregation of Split Network for Personalized Federated Learning

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    PGFedSplit improves client-specific performance and global generalization in heterogeneous federated learning via split architectures, adaptive aggregation, and local-plus-synthetic representation mixing.

  23. FIRMA: FIbonacci Ring Model Aggregation for Privacy-preserving Federated Learning

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    FIRMA introduces Fibonacci ring aggregation protocols for server-free federated learning that maintain private heads and achieve higher accuracy than FedAvg under label skew across multiple benchmarks and heterogeneit...

  24. Fed-BAC: Federated Bandit-Guided Additive Clustering in Hierarchical Federated Learning

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    Fed-BAC uses contextual bandits and Thompson Sampling with additive clustering to deliver up to 35.5 percentage point accuracy gains and 1.5-4.8x faster convergence in hierarchical federated learning on non-IID data.

  25. Fine-Tuning Impairs the Balancedness of Foundation Models in Long-tailed Personalized Federated Learning

    cs.CV 2026-05 unverdicted novelty 5.0 of 10

    Fine-tuning impairs the class balance of foundation models in long-tailed personalized federated learning, which FedPuReL addresses through gradient purification using zero-shot predictions and residual-based personal...

  26. Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models

    cs.LG 2026-04 unverdicted novelty 5.0 of 10

    Bidirectional Manifold Consistency measures geometric stability of dLLM trajectories and is claimed to indicate reasoning correctness for diagnosis, rejection sampling, and reward-based alignment.

  27. FedRio: Personalized Federated Social Bot Detection via Cooperative Reinforced Contrastive Adversarial Distillation

    cs.AI 2026-04 unverdicted novelty 5.0 of 10

    FedRio is a new federated framework that outperforms standard federated baselines in social bot detection accuracy and efficiency while staying competitive with centralized models under stronger privacy constraints.

  28. A Survey on Foundation Models for Personalized Federated Intelligence

    cs.AI 2025-05 unverdicted novelty 3.0 of 10

    The survey introduces personalized federated intelligence (PFI) as a framework integrating federated learning and foundation models to support privacy-aware personalization of AI models.

  29. Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions

    cs.LG 2024-06 unverdicted novelty 2.0 of 10

    A survey organizing knowledge distillation techniques for addressing privacy, heterogeneity, communication, and personalization challenges in federated learning.

Pith tools