Skip to main content

Menu

LEVEL 0
0/5 XP
HomeAboutTopicsPricingMy VaultStatsPractice TestsCertifications

Categories

🎓 Certifications
🤖 Artificial Intelligence
☁️ Cloud and Infrastructure
💾 Data and Databases
💼 Professional Skills
🎯 Programming and Development
🔒 Security and Networking
📚 Specialized Topics
CheatGrid
HomeAboutTopicsPricingMy VaultStatsPractice TestsCertifications
LVLEVEL 0
0/5 XP
GitHub
© 2026 CheatGrid™. All rights reserved.
Privacy PolicyTerms of UseAboutContact

Federated Learning Cheat Sheet

Federated Learning Cheat Sheet

Back to AI and Machine Learning
Updated 2026-05-02
Next Topic: Google Vertex AI Cheat Sheet

Federated Learning (FL) is a distributed machine learning paradigm that enables collaborative model training across decentralized devices or servers without centralizing raw data. Originally introduced by Google in 2016 for improving Gboard's next-word prediction, FL has become foundational for privacy-preserving AI in healthcare, finance, IoT, and edge computing. Unlike traditional centralized learning where all data is uploaded to a central server, FL keeps data local while sharing only model updates—a critical distinction that preserves user privacy, complies with regulations like GDPR and HIPAA, and reduces communication overhead. The key challenge: achieving global model convergence despite heterogeneous data distributions, unreliable network connections, and resource-constrained devices requires sophisticated aggregation algorithms, communication-efficient protocols, and robust defenses against adversarial attacks.

What This Cheat Sheet Covers

This topic spans 24 focused tables and 148 indexed concepts. Below is a complete table-by-table outline of this topic, spanning foundational concepts through advanced details.

Table 1: Core Aggregation AlgorithmsTable 2: Federated Learning ParadigmsTable 3: Privacy-Preserving MechanismsTable 4: Communication Efficiency TechniquesTable 5: Handling Data Heterogeneity (Non-IID Data)Table 6: Personalized Federated LearningTable 7: Client Selection and Sampling StrategiesTable 8: Convergence and OptimizationTable 9: Security Threats and AttacksTable 10: Frameworks and LibrariesTable 11: Real-World ApplicationsTable 12: Advanced Communication TechniquesTable 13: Fairness and Bias MitigationTable 14: Knowledge Distillation and Model CompressionTable 15: System Heterogeneity and StragglersTable 16: Normalization and Architecture ConsiderationsTable 17: Meta-Learning and Few-Shot AdaptationTable 18: Federated Reinforcement LearningTable 19: Convergence Theory and GuaranteesTable 20: Advanced Attack Defense MechanismsTable 21: Vertical Federated Learning and Split LearningTable 22: Blockchain and Incentive MechanismsTable 23: Concept Drift and Continual LearningTable 24: Federated Neural Architecture Search

Table 1: Core Aggregation Algorithms

The aggregation algorithm is the heart of federated learning—it's the rule the server uses to fuse hundreds of local model updates into one global model. FedAvg is the simple weighted-average baseline everything else builds on; the rest are direct answers to its weaknesses, adding proximal terms, control variates, or server-side adaptive optimizers to keep training stable when clients hold wildly different data.

AlgorithmExampleDescription
FedAvg (Federated Averaging)
w_{t+1} = \sum_{k=1}^{K} \frac{n_k}{n} w_k^t
• Weighted average of local model updates where weights are proportional to client dataset sizes
• forms the baseline for most FL algorithms
FedProx
\min_w F(w) + \frac{\mu}{2} \<code>w - w_t\</code>^2
• Adds proximal term \mu to limit client drift in heterogeneous environments
• mitigates impact of clients with radically different local optima due to non-IID data
FedAdam
m_t = \beta_1 m_{t-1} + (1-\beta_1) \Delta w_t
v_t = \beta_2 v_{t-1} + (1-\beta_2) \Delta w_t^2
• Applies adaptive momentum at the server using first and second moment estimates
• achieves faster convergence than FedAvg on non-convex objectives
Scaffold
w_{k,t+1} = w_k^t - \eta (g_k - c_k + c)
• Maintains control variates c_k and global correction c to reduce client drift
• achieves linear speedup with respect to number of clients

More in AI and Machine Learning

  • Feature Store Architecture and Design Cheat Sheet
  • Google Vertex AI Cheat Sheet
  • AI Bias & Fairness Cheat Sheet
  • Edge AI and TinyML Cheat Sheet
  • MLflow Cheat Sheet
  • PyTorch Cheat Sheet
View all 83 topics in AI and Machine Learning