Federated learning glossary
Clear definitions for federated learning, distributed AI, privacy-preserving machine learning, and the systems that make them practical.
Missing something?
Add a glossary entry and help the community build a shared vocabulary for federated AI.
Browse the glossary
19 entries
Aggregation
Combine model weights from sampled clients to update the global model. This process enables the global model to learn from each client's data.
Client
A client is any machine with local data that connects to a server, trains on received global model weights, and sends back updated weights. Clients may also evaluate global model weights.
Docker
Docker is a containerization tool that allows for consistent and reliable deployment of applications across different environments.
Edge Computing
Edge computing is a distributed computing concept of bringing compute and data storage as close as possible to the source of data generation and consumption by users.
Evaluation
Evaluation measures how well the trained model performs by testing it on each client's local data, providing insights into its generalizability across varied data sources.
Federated Learning
Federated Learning is a machine learning approach where model training occurs on decentralized devices, preserving data privacy and leveraging local computations.
Flower Datasets
Flower Datasets is a library for creating federated learning datasets by either partitioning centralized data to simulate heterogeneity or using naturally partitioned datasets.
gRPC
gRPC is an inter-process communication technology for building distributed apps. It allows developers to connect, invoke, operate, and debug apps as easily as making a local function call.
Inference
Inference is the phase in which a trained machine learning model applies its learned patterns to new, unseen data to make predictions or decisions.
IoT
The Internet of Things (IoT) refers to devices with sensors, software, and tech that connect and exchange data with other systems via the internet or communication networks.
Medical AI
Medical AI involves the application of artificial intelligence technologies to healthcare, enhancing diagnosis, treatment planning, and patient monitoring by analyzing complex medical data.
Model Training
Model training is the process of teaching an algorithm to learn from data to make predictions or decisions.
Platform Independence
The capability to run program across different hardware and operating systems.
Protocol Buffers
Protocol Buffers, often abbreviated as Protobuf, are a language-neutral, platform-neutral, extensible mechanism for serializing structured data, similar to XML but smaller, faster, and simpler.
Scalability
Scalability ensures systems grow with demand. In Federated Learning, it involves efficiently managing dynamic clients and diverse devices. Flower supports large-scale FL on various devices/ resources.
Secure Aggregation
Secure aggregation is an approach to ensure that individual model updates are encrypted and only aggregated results are revealed to the server.
Server
The central entity coordinating the aggregation of local model updates from multiple clients to build a comprehensive, privacy-preserving global model.
Vertical FL
Vertical Federated Learning (VFL) enables collaborative model training across multiple organizations or institutions that share a common set of samples but hold different feature sets.
XGBoost
XGBoost - or eXtreme Gradient Boosting - is an open-source library providing a regularizing gradient boosting decisiong tree framework for many programming languages including Python, C++, and Java.