Federated Machine Learning
By Qiang Yang, Yang Liu, Tianjian Chen, Yongxin Tong. 2019
3,214 citations recorded by the source corpus.
Today’s artificial intelligence still faces two major challenges. One is that, in most industries, data exists in the form of isolated islands. The other is the strengthening of data privacy and security. We propose a possible solution to these challenges: secure federated learning. Beyond the federated-learning framework first proposed by Google in 2016, we introduce a comprehensive secure federated-learning framework, which includes horizontal federated learning, vertical federated learning, and federated transfer learning. We provide definitions, architectures, and applications for the federated-learning framework, and provide a comprehensive survey of existing works on this subject. In addition, we propose building data networks among organizations based on federated mechanisms as an effective solution to allowing knowledge to be shared without compromising user privacy.
Subfields: Artificial Intelligence, Federated & Distributed Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Percy Liang
- Qiang Yang
- Yang Liu
- Peter Richtárik
- Martin Jaggi
- Jakub Konecný
- Virginia Smith
- Mohit Bansal
In Federated & Distributed Learning
- Virginia Smith
- Tian Li
- Bingsheng He
- Qinbin Li
- Qiang Yang
- Jakub Konecný
- Peter Richtárik
- Ameet Talwalkar
Citations in the corpus
- Attack of the Tails: Yes, You Really Can Backdoor Federated Learning (2020, background): “Related Work Due to its emphasis on preserving privacy, FL has gained significant attention in the community [12, 39, 40, 41, 42].”
- Backdoor attacks and defenses in feature-partitioned collaborative learning (2020, methodology): “…collaborative learning frameworks have been developed for models including trees (Cheng et al., 2019), linear and logistic regression (Yang et al., 2019b; Hardy et al., 2017; Gratton et al., 2018; Kikuchi et al., 2017; Hu et al., 2019a), and neural networks (Liu et al., 2018; Hu et…”
- On the Outsized Importance of Learning Rates in Local Update Methods (2020, background): “A different categorization, vertical and horizontal, was proposed by Yang et al. (2019), which is based on modelling constraints, rather than on system constraints.”
- Three Approaches for Personalization with Applications to Federated Learning (2020, background): “In FL, typically a centralized global model is trained based on data from a large number of clients, which may be mobile phones, other mobile devices, or sensors (Konečnỳ et al., 2016b,a; McMahan et al., 2017; Yang et al., 2019) using a variant of”
- Gradient Descent with Compressed Iterates (2019, background): “1 Introduction Federated learning is a machine learning setting where the goal is to learn a centralized model given access only to local optimization procedures distributed over many devices [18, 22, 36].”
- Wireless Network Intelligence at the Edge (2018, background): “For more details on state dimensionality reduction and advanced FL and FD frameworks in both supervised learning and RL, the readers are encouraged to check [186], [195], and [196].”
- LEAF: A Benchmark for Federated Settings (2018, background): “With data increasingly being generated on federated networks of remote devices, there is growing interest in empowering on-device applications with models that make use of such data [22, 23, 30, 19, 37].”
- Federated Learning: Challenges, Methods, and Future Directions (2019, methodology): “Federated learning methods have been deployed by major service providers [11, 124], and play a critical role in supporting privacy-sensitive applications where the training data are distributed at the edge [e.g., 5, 46, 51, 89, 105, 127, 139].”
- Mobile Edge Computing, Blockchain and Reputation-based Crowdsourcing IoT Federated Learning: A Secure, Decentralized and Privacy-preserving System (2019, background): “On the other hand, FL has attracted substantial attention recently [17]–[21], and one of the most important issues in FL is privacy protection, which is explored in [22]–[26].”
- Federated Learning for Healthcare: Systematic Review and Architecture Proposal (2022, background): “Recent work proposes the concept of federated learning (FL) [10] to tackle these issues.”
- Digital Twins: State of the Art Theory and Practice, Challenges, and Open Research Questions (2020, methodology): “New methods like continual learning [43] and federated learning [85] seem promising for the use of DT but require further research.”
- How Machine Learning will Transform Biomedicine (2020, positive): “When data are distributed across multiple sites and cannot be moved to create a single dataset for machine learning, federated learning approaches are used to learn incrementally across all the data (Konecny et al., 2016; Yang et al., 2019).”
- The future of digital health with federated learning (2020, background): “d FL approaches are still under development. 3 Technical Considerations FL is perhaps best-known from the work of Konecnˇ y` et al. [36], but various other definitions have been proposed in literature [14, 11, 15, 9]. These approaches can be realised via different communication architectures (see Fig”
- Personalized Federated Learning for Intelligent IoT Applications: A Cloud-Edge Based Framework (2020, positive): “A sophisticated solution to deal with distributed data training is federated learning which enables to collaboratively train a high-quality shared model by aggregating and averaging locally-computed updates uploaded by IoT devices [4].”