Pith. sign in

REVIEW 7 cited by

Improving Federated Learning Personalization via Model Agnostic Meta Learning

Not yet reviewed by Pith; the record is open.

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 1909.12488 v2 pith:BF5B3QX4 submitted 2019-09-27 cs.LG stat.ML

classification cs.LGstat.ML
keywords modellearningdatafederatedglobalmamlmetanatural
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Federated Learning (FL) refers to learning a high quality global model based on decentralized data storage, without ever copying the raw data. A natural scenario arises with data created on mobile phones by the activity of their users. Given the typical data heterogeneity in such situations, it is natural to ask how can the global model be personalized for every such device, individually. In this work, we point out that the setting of Model Agnostic Meta Learning (MAML), where one optimizes for a fast, gradient-based, few-shot adaptation to a heterogeneous distribution of tasks, has a number of similarities with the objective of personalization for FL. We present FL as a natural source of practical applications for MAML algorithms, and make the following observations. 1) The popular FL algorithm, Federated Averaging, can be interpreted as a meta learning algorithm. 2) Careful fine-tuning can yield a global model with higher accuracy, which is at the same time easier to personalize. However, solely optimizing for the global model accuracy yields a weaker personalization result. 3) A model trained using a standard datacenter optimization method is much harder to personalize, compared to one trained using Federated Averaging, supporting the first claim. These results raise new questions for FL, MAML, and broader ML research.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

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

  1. FedMeNF: Privacy-Preserving Federated Meta-Learning for Neural Fields

    cs.LG 2025-08 conditional novelty 7.0 of 10

    MDIR detects LLM weight homology from embedding matrices alone using polar decomposition and permutation matching, achieving perfect AUC and accuracy on LeaFBench and reconstructing layer-level transformations.

  2. Federated Learning with Heterogeneous and Private Label Sets

    cs.LG 2025-08 conditional novelty 6.0 of 10

    By averaging classifier weights per label across clients and tuning the central model on unlabeled data, federated learning can handle private, heterogeneous client label sets at accuracy close to the public-label setting.

  3. Addressing the Collaboration Dilemma in Low-Data Federated Learning via Transient Sparsity

    cs.LG 2025-06 conditional novelty 6.0 of 10

    LIPS, a method that periodically prunes low-sensitivity middle-layer weights after aggregation, mitigates layer-wise inertia and improves low-data federated learning accuracy.

  4. Collate: Collaborative Neural Network Learning for Latency-Critical Edge Systems

    cs.LG 2026-07 conditional novelty 5.5 of 10

    Collate jointly trains heterogeneous models under per-device latency constraints via dynamic zeroizing-recovering and proto-corrected aggregation, gaining ~2–3% accuracy over prior heterogeneous FL.

  5. SuperSFL: Resource-Heterogeneous Federated Split Learning with Weight-Sharing Super-Networks

    cs.DC 2026-01 conditional novelty 5.0 of 10

    A weight-sharing super-network plus locally supervised gradient fusion makes split-federated learning converge in fewer communication rounds than fixed-split baselines.

  6. The OCR Quest for Generalization: Learning to recognize low-resource alphabets with model editing

    cs.LG 2025-06 conditional novelty 5.0 of 10

    Merging task vectors from separately fine-tuned OCR experts improves out-of-domain generalization and transfer to low-resource alphabets compared to centralized fine-tuning on the same data.

  7. Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions

    cs.LG 2025-05 conditional novelty 5.0 of 10

    FLowDUP generates personalized federated models for unlabeled clients via a hypernetwork operating in a low-dimensional random subspace, with a transductive multi-task PAC-Bayes bound motivating the objective.

Pith tools