Federated Learning

Description

Federated learning enables collaborative model training across multiple distributed parties (devices, organisations, or data centres) without requiring centralised data sharing. Participants train models locally on their private datasets and only share model updates (gradients, weights, or aggregated statistics) with a central coordinator. This distributed approach serves multiple purposes: preserving data privacy and sovereignty, reducing communication costs, enabling learning from diverse data sources, improving model robustness through heterogeneous training, and facilitating compliance with data protection regulations whilst maintaining model performance comparable to centralised training.

Example Use Cases

Privacy

Developing a smartphone keyboard prediction model by learning from users' typing patterns without their text ever leaving their devices, enabling personalised predictions whilst maintaining complete data privacy.

Reliability

Training a medical diagnosis model across multiple hospitals without sharing patient records, ensuring model robustness by learning from diverse patient populations and clinical practices across different institutions.

Safety

Creating a cybersecurity threat detection model by federating learning across financial institutions without exposing sensitive transaction data, reducing systemic risk whilst maintaining competitive confidentiality.

Fairness

Building a fair credit scoring model by training across multiple regions and demographics without centralising sensitive financial data, ensuring representation from diverse populations whilst respecting local data sovereignty laws.

Limitations

Communication overhead can be substantial, especially with frequent model updates and large models, potentially limiting scalability and increasing training time compared to centralised approaches.
Statistical heterogeneity across participants (non-IID data distributions) can lead to training instability, slower convergence, and reduced model performance compared to centralised training on pooled data.
System heterogeneity in computational capabilities, network connectivity, and availability of participating devices can create bottlenecks and introduce bias towards more capable participants.
Privacy vulnerabilities remain through gradient leakage attacks, model inversion, and membership inference attacks that can potentially reconstruct sensitive information from shared model updates.
Coordination complexity increases with the number of participants, requiring sophisticated aggregation protocols, fault tolerance mechanisms, and secure communication infrastructure.

Resources

Open Federated Learning (OpenFL) Documentation

Documentation

Federated Learning - DeepLearning.AI

Tutorial

A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection

Documentation•Qinbin Li et al.•Jul 23, 2019

Federated learning with hybrid differential privacy for secure and reliable cross-IoT platform knowledge sharing

Research Paper•Algburi, S. et al.•Jan 1, 2024

Related Techniques

Name	Description	Assurance Goals
Influence Functions	Influence functions quantify how much each training example influenced a model's predictions by computing the change in prediction that would occur if that training example were removed and the model retrained. Using calculus and the implicit function theorem, they approximate this 'leave-one-out' effect without actually retraining the model by computing gradients and Hessian information. This mathematical approach reveals which specific training examples were most responsible for pushing the model toward or away from particular predictions, enabling practitioners to trace problematic outputs back to their root causes in the training data.	Explainability Fairness Privacy
Automated Documentation Generation	Automated documentation generation creates and maintains up-to-date documentation using various methods including programmatic scripts, large language models (LLMs), and extraction tools. These approaches can capture model architectures, data schemas, feature importance, performance metrics, API specifications, and lineage information without manual writing. Methods range from traditional code parsing and template-based generation to modern AI-assisted documentation that can understand context and generate human-readable explanations.	Transparency Reliability
Monotonicity Constraints	Monotonicity constraints enforce consistent directional relationships between input features and model predictions, ensuring that increasing a feature value either always increases, always decreases, or has no effect on the output. These constraints integrate domain knowledge into model training, preventing counterintuitive relationships that may arise from spurious correlations in data. By maintaining logical feature relationships (e.g., experience always positively influences salary), monotonicity constraints enhance model trustworthiness, interpretability, and alignment with business logic whilst often improving generalisation to new data.	Transparency Reliability
Datasheets for Datasets	Datasheets for datasets establish comprehensive documentation standards for datasets, systematically recording creation methodology, data composition, collection procedures, preprocessing transformations, intended applications, potential biases, privacy considerations, and maintenance protocols. These structured documents enhance dataset transparency by providing essential context for appropriate usage, enabling informed decisions about dataset suitability for specific tasks, supporting bias detection and mitigation efforts, ensuring compliance with data protection regulations, and promoting responsible data stewardship throughout the entire data lifecycle from collection to disposal.	Transparency Fairness Privacy
Deep Ensembles	Deep ensembles combine predictions from multiple neural networks trained independently with different random initializations to capture epistemic uncertainty (model uncertainty). By training several models on the same data with different starting points, the ensemble reveals how much the model's predictions depend on training randomness. The disagreement between ensemble members naturally indicates prediction uncertainty - when models agree, confidence is high; when they disagree, uncertainty is revealed. This approach provides more reliable uncertainty estimates, better out-of-distribution detection, and improved calibration compared to single models.	Reliability Transparency Safety
Out-of-DIstribution detector for Neural networks	ODIN (Out-of-Distribution Detector for Neural Networks) identifies when a neural network encounters inputs significantly different from its training distribution. It enhances detection by applying temperature scaling to soften the model's output distribution and adding small, carefully calibrated perturbations to the input that push in-distribution samples towards higher confidence predictions. By measuring the maximum softmax probability after these adjustments, ODIN can effectively distinguish between in-distribution and out-of-distribution inputs, flagging potentially unreliable predictions before they cause downstream errors.	Explainability Reliability Safety