Knowledge-Injected Federated Learning
Not on the map. Why?
Abstract (arXiv)
Federated learning is an emerging technique for training models from decentralized data sets. In many applications, data owners participating in the federated learning system hold not only the data but also a set of domain knowledge. Such knowledge includes human know-how and craftsmanship that can be extremely helpful to the federated learning task. In this work, we propose a federated learning framework that allows the injection of participants' domain knowledge, where the key idea is to refine the global model with knowledge locally. The scenario we consider is motivated by a real industry-level application, and we demonstrate the effectiveness of our approach to this application.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 18 of its 35 references that are in the map. First posted on arXiv 16 Aug 2022.
Builds on
18 of 35 references.
References · 18
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
- 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
- 2020Personalized Federated Learning with Moreau Envelopescited by 612
- 2019Federated Learning with Personalization Layerscited by 533
- 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
- 2020Adaptive Personalized Federated Learningcited by 353
- 2020Three Approaches for Personalization with Applications to Federated Learningcited by 321
- 2020Personalized Federated Learning: A Meta-Learning Approachcited by 309
- 2020Personalized Cross-Silo Federated Learning on Non-IID Datacited by 282
- 2019Improving Federated Learning Personalization via Model Agnostic Meta Learningcited by 264
- 2019Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systemscited by 203
6 more
- 2018Federated Meta-Learning with Fast Convergence and Efficient Communicationcited by 154
- 2019Federated Evaluation of On-device Personalizationcited by 147
- 2016Harnessing Deep Neural Networks with Logic Rulescited by 135
- 2022ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!cited by 134
- 2020Improving Deep Learning Models via Constraint-Based Domain Knowledge: a Brief Surveycited by 16
- 2022Integration of knowledge and data in machine learningcited by 13
Built on by
Citing papers per year: 2024: 1.
1 paper.