Skip to contentScholarGate
LibraryBookshelfDeskReview StudioAssistant
Sign in
On this page
IntuitionHow it worksWhen to use itStrengths & limitationsCommon pitfallsApplicationsFrequently asked🔒 Read the full methodSourcesRelated methods
Cite this pageSpotted an issue on this page? Report or suggest a fix →
Home›Privacy›Federated Learning
Machine learningPrivacy-preserving analysis

Federated Learning

Also known as: Collaborative Learning, Decentralized Learning, FedAvg, Federe Öğrenme

Federated Learning is a distributed machine learning paradigm introduced by McMahan et al. in 2017 in which a global model is trained collaboratively across multiple decentralized clients — such as mobile devices or hospital systems — without ever transferring raw data to a central server. Each participant computes model updates locally using its private data; only those updates, not the underlying data, are communicated and aggregated by the server to improve the shared model.

ScholarGate
  1. Machine learning
  2. v1
  3. 1 Sources
  4. PUBLISHED
Cite this page →
Tools & resources
Download slides
Learn & explore

Read the full method

Members only

Sign in with a free account to read this section.

Sign in

Method map

The neighbourhood of related methods — select a node to explore.

Federated Learning
Differential PrivacyKnowledge DistillationStochastic Gradient Desc…Active Learning Federate…Bayesian Federated Learn…Ensemble Federated Learn…Homomorphic EncryptionOnline Federated LearningOnline LearningRegularized Federated Le…

+4 more

When to use it

Use Federated Learning when training data is distributed across many clients and cannot be centralized due to privacy regulations, data-ownership constraints, or communication costs — for example, mobile keyboards, medical imaging across hospitals, or IoT sensor networks. Key assumptions include sufficient local data per client and a shared task across all participants. It is less suitable when client data distributions are highly heterogeneous (non-IID), communication bandwidth is severely limited, or when strong formal privacy guarantees beyond data locality are required (consider combining with differential privacy in that case).

Strengths & limitations

Strengths
  • Preserves data privacy by design: raw data never leaves the client device or institution.
  • Scales to millions of heterogeneous edge devices without centralizing storage.
  • Reduces data-transfer costs because only model updates, not datasets, are communicated.
  • Enables learning from sensitive domains (healthcare, finance) where data sharing is legally restricted.
Limitations
  • Convergence can be slow and unstable when client data distributions are highly non-IID.
  • Communication overhead across many rounds can be significant on low-bandwidth networks.
  • Model updates can still leak information about local data through gradient inversion or membership inference attacks.
  • Stragglers and dropped clients complicate synchronous aggregation and can bias the global model.

Frequently asked

Does Federated Learning guarantee complete privacy?

Not by itself. While raw data never leaves client devices, model updates (gradients) can still leak information through gradient inversion or membership inference attacks. Combining federated learning with differential privacy noise addition and secure aggregation protocols substantially strengthens privacy guarantees, but each layer adds its own accuracy or communication trade-offs.

How does Federated Learning handle non-IID data across clients?

Standard FedAvg can diverge when client data distributions differ sharply from one another — a phenomenon called client drift. Remedies include increasing local batch sizes, reducing local epochs, applying personalized federated learning variants (such as FedProx or SCAFFOLD), or using server-side momentum. The severity depends on the degree of statistical heterogeneity across clients.

How many clients and rounds are typically needed for convergence?

McMahan et al. showed that even with a small fraction of clients sampled per round (e.g., 10 out of 100), FedAvg converges within tens to hundreds of rounds for standard tasks. In practice the number depends on dataset size per client, degree of non-IID-ness, learning rate, and the number of local gradient steps performed before each aggregation.

Sources

  1. McMahan, B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. (2017). Communication-efficient learning of deep networks from decentralized data. Artificial Intelligence and Statistics, 1273–1282. link ↗

How to cite this page

ScholarGate. (2026, June 2). Federated Learning. ScholarGate. https://scholargate.app/en/privacy/federated-learning

Related methods

Differential PrivacyKnowledge DistillationStochastic Gradient Descent

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

  • Differential PrivacyPrivacy↔ compare
  • Knowledge DistillationDeep learning↔ compare
  • Stochastic Gradient DescentMachine learning↔ compare
Compare side by side →

Referenced by

Active Learning Federated LearningBayesian Federated LearningDifferential PrivacyEnsemble Federated LearningHomomorphic EncryptionOnline Federated LearningOnline LearningRegularized Federated LearningRobust Federated LearningSecure Multi-Party ComputationSelf-supervised Federated learningSemi-supervised Federated learning

Similar methods

Online Federated LearningEnsemble Federated LearningRegularized Federated LearningBayesian Federated LearningSelf-supervised Federated learningRobust Federated LearningActive Learning Federated LearningSemi-supervised Federated learning

Related reference concepts

De-identification and Privacy-Preserving Data AnalysisStochastic OptimizationMachine LearningUnsupervised LearningDeep LearningReinforcement Learning

Spotted an issue on this page? Report or suggest a fix →

ScholarGate — Federated Learning (Federated Learning). Retrieved 2026-07-21 from https://scholargate.app/en/privacy/federated-learning · Dataset: https://doi.org/10.5281/zenodo.20539026
Quick facts
Originator
McMahan et al.
Year
2017
Type
Distributed privacy-preserving machine learning
Subfamily
Privacy-preserving analysis
Aggregation
Weighted averaging of local model updates
Communication
Iterative client-server rounds
Related methods
Differential PrivacyKnowledge DistillationStochastic Gradient Descent
ScholarGate

A content-first reference library for research methods — what each one is, how it works, and where it comes from.

Open data (CC-BY)

Explore

  • Library
  • Search the library…
  • Browse by field
  • Fields
  • Journey
  • Compare
  • Which method?

Reference

  • Subjects
  • Atlas
  • Glossary
  • Methodology
  • Philosophy

Your tools

  • Bookshelf
  • Desk
  • Chat

Company

  • About
  • Pricing
  • Contact
  • Suggest a method

Entries are compiled from published sources for reference. Verifying the accuracy and suitability of any information for your own use remains your responsibility.

© 2026 ScholarGate · A research-method reference library
  • Privacy
  • Cookies
  • Terms
  • Delete account