Pith. sign in

REVIEW 14 cited by

Three Approaches for Personalization with Applications to 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 2002.10619 v2 pith:7IT2UGWG submitted 2020-02-25 cs.LG stat.ML

Yishay Mansour , Mehryar Mohri , Jae Ro , Ananda Theertha Suresh This is my paper
classification cs.LGstat.ML
keywords learningapproachesmodelthreealgorithmsfederatedinterpolationlearning-theoretic
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The standard objective in machine learning is to train a single model for all users. However, in many learning scenarios, such as cloud computing and federated learning, it is possible to learn a personalized model per user. In this work, we present a systematic learning-theoretic study of personalization. We propose and analyze three approaches: user clustering, data interpolation, and model interpolation. For all three approaches, we provide learning-theoretic guarantees and efficient algorithms for which we also demonstrate the performance empirically. All of our algorithms are model-agnostic and work for any hypothesis class.

Discussion (0). Sign in to comment.

Forward citations

Cited by 14 Pith papers

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

  1. Clustered Federated Learning via Embedding Distributions

    cs.LG 2025-06 conditional novelty 7.0 of 10

    EMD-CFL clusters federated learning clients in one shot by comparing Earth Mover's distances between randomly projected embedding distributions, matching oracle clustering on several benchmarks.

  2. 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.

  3. 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.

  4. One-Shot Clustering for Federated Learning Under Clustering-Agnostic Assumption

    cs.LG 2025-09 conditional novelty 6.0 of 10

    OCFL automatically picks the clustering round by detecting a rise in the p-norm of the pairwise cosine-distance matrix of client gradients, and with density-based clustering it recovers client cohorts earlier and more...

  5. Federated Majorize-Minimization: Beyond Parameter Aggregation

    cs.LG 2025-07 conditional novelty 6.0 of 10

    By averaging surrogate-function parameters across clients and then minimizing the aggregated surrogate on the server, federated learning can converge under heterogeneity where parameter averaging diverges.

  6. DICE: Data Influence Cascade in Decentralized Learning

    cs.LG 2025-07 conditional novelty 6.0 of 10

    DICE defines and approximates multi-hop data influence in decentralized learning, showing that influence is shaped by data, topology, and loss curvature.

  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. 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.

  10. MedFedPure: A Medical Federated Framework with MAE-based Detection and Diffusion Purification for Inference-Time Attacks

    cs.LG 2025-11 conditional novelty 5.0 of 10

    A client-side test-time defense combining MAE detection with diffusion purification raises federated MRI tumor-classifier adversarial accuracy from 49.5% to 87.3% under bounded PGD attacks.

  11. DFCA: Decentralized Federated Clustering Algorithm

    cs.LG 2025-10 conditional novelty 5.0 of 10

    DFCA decentralizes IFCA-style clustered federated learning: clients keep one model per cluster, train their assigned model locally, and exchange only that model with neighbors via a running average, matching centraliz...

  12. Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data

    cs.LG 2025-07 conditional novelty 5.0 of 10

    Proto-EVFL selects useful unaligned data in vertical federated learning with a dual optimal transport cost and class priors, then aggregates party features with learned gates, improving accuracy on rare and unseen classes.

  13. 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.

  14. Generalizable Federated Learning using Client Adaptive Focal Modulation

    cs.CV 2025-08 reject novelty 4.0 of 10

    The abstract describes AdaptFED, a claimed federated learning method, but the full text is an unrelated graph theory paper, so the claimed results are absent from the submission.

Pith tools