Semantic Scholar Open Access 2019 5752 sitasi

Federated Learning: Challenges, Methods, and Future Directions

Tian Li Anit Kumar Sahu Ameet Talwalkar Virginia Smith

Lihat Sumber DOI

Abstrak

Federated learning involves training statistical models over remote devices or siloed data centers, such as mobile phones or hospitals, while keeping data localized. Training in heterogeneous and potentially massive networks introduces novel challenges that require a fundamental departure from standard approaches for large-scale machine learning, distributed optimization, and privacy-preserving data analysis. In this article, we discuss the unique characteristics and challenges of federated learning, provide a broad overview of current approaches, and outline several directions of future work that are relevant to a wide range of research communities.

Topik & Kata Kunci

Computer Science Mathematics

Penulis (4)

Tian Li

Anit Kumar Sahu

Ameet Talwalkar

Virginia Smith

Format Sitasi

APA MLA BibTeX

Li, T., Sahu, A.K., Talwalkar, A., Smith, V. (2019). Federated Learning: Challenges, Methods, and Future Directions. https://doi.org/10.1109/MSP.2020.2975749

Akses Cepat

Lihat di Sumber doi.org/10.1109/MSP.2020.2975749

Informasi Jurnal

Tahun Terbit: 2019
Bahasa: en
Total Sitasi: 5752×
Sumber Database: Semantic Scholar
DOI: 10.1109/MSP.2020.2975749
Akses: Open Access ✓