Pith. sign in

REVIEW 13 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 · ORCID
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). Continue with ORCID to comment.

Forward citations

Cited by 13 Pith papers

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

  1. 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...

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

  3. 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.

  4. 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.

  5. 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.

  6. 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...

  7. Adaptive collaboration for online personalized distributed learning with heterogeneous clients

    stat.ML 2025-07 conditional novelty 6.0 of 10

    An adaptive gradient-similarity criterion dynamically selects collaboration partners in personalized federated learning, provably recovering the oracle-optimal sample complexity of All-for-one without knowing client h...

  8. SPIRE: Conditional Personalization for Federated Diffusion Generative Models

    cs.LG 2025-06 reject novelty 6.0 of 10

    SPIRE adds per-client embeddings to a shared diffusion backbone, enabling parameter-efficient personalization in federated learning, with new-client KID improvements on MNIST, CIFAR-10, and CelebA.

  9. Beyond Personalization: Federated Recommendation with Calibration via Low-rank Decomposition

    cs.CR 2025-06 conditional novelty 6.0 of 10

    A low-rank buffer matrix that calibrates user embeddings and personalizes item embeddings reduces the distortion caused by federated aggregation and improves recommendation accuracy.

  10. Hypernetworks for Model-Heterogeneous Personalized Federated Learning

    cs.LG 2025-07 conditional novelty 5.0 of 10

    A server-side multi-head hypernetwork generates personalized parameters for clients with heterogeneous model architectures, plus an optional global-model distillation variant, and beats several pFL baselines on four b...

  11. Federated Learning for Commercial Image Sources

    cs.CV 2025-07 conditional novelty 5.0 of 10

    The authors present a new 31-class, 8-source image classification dataset for federated learning and show that Fed-Cyclic and Fed-Star beat FedAvg and RingFed on it.

  12. Learning to Collaborate Over Graphs: A Selective Federated Multi-Task Learning Approach

    cs.LG 2025-06 conditional novelty 5.0 of 10

    SFMTL-Graph builds a dynamic client similarity graph, partitions it with Louvain community detection, and restricts federated model aggregation to within communities to personalize learning while cutting communication.

  13. Pessimism Principle Can Be Effective: Towards a Framework for Zero-Shot Transfer Reinforcement Learning

    cs.LG 2025-05 conditional novelty 5.0 of 10

    A pessimism-based framework for zero-shot transfer RL builds conservative proxies from robust MDPs, yielding lower-bound performance guarantees and distributed algorithms that mitigate negative transfer.

Pith tools