Federated Learning: Opportunities and Challenges
arXiv:2101.05428
Abstract
Federated Learning (FL) is a concept first introduced by Google in 2016, in which multiple devices collaboratively learn a machine learning model without sharing their private data under the supervision of a central server. This offers ample opportunities in critical domains such as healthcare, finance etc, where it is risky to share private user information to other organisations or devices. While FL appears to be a promising Machine Learning (ML) technique to keep the local data private, it is also vulnerable to attacks like other ML models. Given the growing interest in the FL domain, this report discusses the opportunities and challenges in federated learning.
References in corpus (13)
- Communication-Efficient Learning of Deep Networks from Decentralized Data
- Federated Learning: Strategies for Improving Communication Efficiency
- Towards Federated Learning at Scale: System Design
- Differentially Private Federated Learning: A Client Level Perspective
- Asynchronous Federated Optimization
- Can You Really Backdoor Federated Learning?
- One-Shot Federated Learning
- Distilled One-Shot Federated Learning
- Blockchain-Federated-Learning and Deep Learning Models for COVID-19 detection using CT Imaging
- BAFFLE : Blockchain Based Aggregator Free Federated Learning
- Asynchronous Federated Learning with Reduced Number of Rounds and with Differential Privacy from Less Aggregated Gaussian Noise
- Data Poisoning Attacks on Federated Machine Learning
- BlockFLA: Accountable Federated Learning via Hybrid Blockchain Architecture
Cited by in corpus (7)
- Federated Learning for Big Data: A Survey on Opportunities, Applications, and Future Directions
- Personalized and privacy-preserving federated heterogeneous medical image analysis with PPPML-HMI
- Federated Split Vision Transformer for COVID-19 CXR Diagnosis using Task-Agnostic Training
- Securing Federated Sensitive Topic Classification against Poisoning Attacks
- Computing: Looking Back and Moving Forward
- OCTOPUS: Overcoming Performance andPrivatization Bottlenecks in Distributed Learning
- A Federated Random Forest Solution for Secure Distributed Machine Learning