Advances and Open Problems in Federated Learning
Explore this paper's citation graph
Summary
Motivated by the explosive growth in FL research, this paper discusses recent advances and presents an extensive collection of open problems and challenges.
- Type
- article
- Published
- 2019-12-10
- Cited by
- 9,413
- References
- 516
- Access
- Open access
- OpenAlex
- https://openalex.org/W2995022099
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:209202606
Keywords
Orchestration, Computer science, Data collection, Federated learning, Open research
References
- SEPIA: Privacy-Preserving Aggregation of Multi-Domain Network Events and Statistics
- Differential Privacy Under Fire
- ON DATA BANKS AND PRIVACY HOMOMORPHISMS
- Information Theory: 1948-1998 - Guest Editorial
- Privacy for the Protected (Only)
- On the Computational Practicality of Private Information Retrieval
- Data Matching
- Geppetto: Versatile Verifiable Computation
- Domain Adaptation: Learning Bounds and Algorithms
- Intriguing properties of neural networks
- Scalable Bayesian Optimization Using Deep Neural Networks
- The Composition Theorem for Differential Privacy
- BinaryConnect: Training Deep Neural Networks with binary weights during propagations
- The Knowledge Complexity of Interactive Proof Systems
- Computationally Sound Proofs
- Privacy-Preserving Ridge Regression on Hundreds of Millions of Records
- Domain adaptation and sample bias correction theory and algorithm for regression
- RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response
- STATLOG: COMPARISON OF CLASSIFICATION ALGORITHMS ON LARGE REAL-WORLD PROBLEMS
- Local, Private, Efficient Protocols for Succinct Histograms
Cited by
- Particle swarm optimizer with crossover operation
- SecureBoost: A Lossless Federated Learning Framework
- Who started this rumor? Quantifying the natural differential privacy guarantees of gossip protocols
- Fully Decentralized Joint Learning of Personalized Models and Collaboration Graphs
- SoK: Differential privacies
- Boosting Privately: Privacy-Preserving Federated Extreme Boosting for Mobile Crowdsensing
- Learning to Demodulate From Few Pilots via Offline and Online Meta-Learning
- Private Aggregation from Fewer Anonymous Messages
- Model Pruning Enables Efficient Federated Learning on Edge Devices
- The Non-IID Data Quagmire of Decentralized Machine Learning
- SAFA: A Semi-Asynchronous Protocol for Fast Federated Learning With Low Overhead
- Model Fusion via Optimal Transport
- Q-GADMM: Quantized Group ADMM for Communication Efficient Decentralized Machine Learning
- Improved Differentially Private Decentralized Source Separation for fMRI Data
- Asynchronous Online Federated Learning for Edge Devices
- Soft-Label Dataset Distillation and Text Dataset Distillation
- Federated Learning for Healthcare Informatics
- Adaptive Catalyst for Smooth Convex Optimization
- A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection
- Don't Use Large Mini-Batches, Use Local SGD
Related papers
- Learning Multiple Layers of Features from Tiny Images
- Federated Optimization in Heterogeneous Networks
- Towards Federated Learning at Scale: System Design
- Federated Machine Learning
- LEAF: A Benchmark for Federated Settings
- Federated Learning for Mobile Keyboard Prediction
- Federated Learning with Non-IID Data