FedScale: Benchmarking Model and System Performance of Federated Learning at Scale

Abstract

We present FedScale, a federated learning (FL) benchmarking suite with realistic datasets and a scalable runtime to enable reproducible FL research. FedScale datasets encompass a wide range of critical FL tasks, ranging from image classification and object detection to language modeling and speech recognition. Each dataset comes with a unified evaluation protocol using real-world data splits and evaluation metrics. To reproduce realistic FL behavior, FedScale contains a scalable and extensible runtime. It provides high-level APIs to implement FL algorithms, deploy them at scale across diverse hardware and software backends, and evaluate them at scale, all with minimal developer efforts. We combine the two to perform systematic benchmarking experiments and highlight potential opportunities for heterogeneity-aware co-optimizations in FL. FedScale is open-source and actively maintained by contributors from different institutions at http://fedscale.ai. We welcome feedback and contributions from the community.

References in corpus (19)

• Communication-Efficient Learning of Deep Networks from Decentralized Data
• MobileNetV2: Inverted Residuals and Linear Bottlenecks
• Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
• Differentially Private Federated Learning: A Client Level Perspective
• EMNIST: an extension of MNIST to handwritten letters
• Applied Federated Learning: Improving Google Keyboard Query Suggestions
• Can You Really Backdoor Federated Learning?
• FedML: A Research Library and Benchmark for Federated Machine Learning
• LEAF: A Benchmark for Federated Settings
• Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding
• Error Feedback Fixes SignSGD and other Gradient Compression Schemes
• Adaptive Federated Optimization
• IBM Federated Learning: an Enterprise Framework White Paper V0.1
• Federated Learning Of Out-Of-Vocabulary Words
• The OARF Benchmark Suite: Characterization and Implications for Federated Learning Systems
• Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval
• Practical and Private (Deep) Learning without Sampling or Shuffling
• FedEval: A Holistic Evaluation Framework for Federated Learning
• Semi-Cyclic Stochastic Gradient Descent

Cited by in corpus (9)

• Federated Few-Shot Learning for Mobile NLP
• Federated Fine-Tuning of LLMs on the Very Edge: The Good, the Bad, the Ugly
• Decentralized Learning Made Easy with DecentralizePy
• FLEdge: Benchmarking Federated Machine Learning Applications in Edge Computing Systems
• Auxo: Efficient Federated Learning via Scalable Client Clustering
• Federated learning with differential privacy and an untrusted aggregator
• Boosting Asynchronous Decentralized Learning with Model Fragmentation
• Practical Federated Learning without a Server
• Accelerating MoE Model Inference with Expert Sharding