Federated Machine Learning: Concept and Applications

• My points of interest
  • federated learning
  • transfer learning
• our data is in the form of isolated islands & How to legally solve the problem
  • secure federated learning
  • federated transfer learning
• 当前人工智能的方向应该转变
  • shift the focus of AI development from improving model performance, which is what most of the AI field is currently doing, to investigating methods for data integration that is compliant with data privacy and security laws.
• In [ 34], block-chained federated learning (BlockFL) architecture
  Hyesung Kim, Jihong Park, Mehdi Bennis, and Seong-Lyun Kim. 2018. On-Device Federated Learning via Blockchain and its Latency Analysis. arXiv:cs.IT/1808.03949
• Deep Gradient Compression [39]
  Yujun Lin, Song Han, Huizi Mao, Yu Wang, and William J. Dally. 2017. Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training. CoRR abs/1712.01887 (2017). arXiv:1712.01887 http: //arxiv.org/abs/1712.01887
• Horizontal federated learning at first sight is somewhat similar to Distributed Machine Learning.
• Federated learning can be seen as an operating system for edge computing, as it provides the learning protocol for coordination and security
• 隐私壁垒和异构数据 需要联邦迁移学习