Federated Learning: Privacy and Incentive

(An Edited Book)

Full Chapter Submission Due: July 31, 2020 (23:59:59 UTC-12)
Camera Ready Chapter Submission Due: August 31, 2020 (23:59:59 UTC-12)

Book Publication Date: December 25, 2020


Yang, Q., Fan, L. & Yu, H. (Eds.). (2020). Federated Learning: Privacy and Incentive. Springer International Publishing, Switzerland, p. 282.

Invitation for Book Chapter Contribution

Federated Learning (FL) attracts much recent attention from both academia and industry, as it provides a technological framework to address wide-spreading public concerns of the protection of data privacy and information security. The training of FL models is distributed across a multitude of devices and remote parties, and the raw data do not leave the sites of data owners. This promise adheres to regulatory requirements of data privacy protection such as European Union’s General Data Protection Regulation (GDPR), and is particularly interested to data providers from e.g. banks or health institutes. Despite the rapid development of the technological landscape, there is a consensus that open issues such as improving learning efficiency, trust mechanism, protection against adversarial attacks, limited communication bandwidth and cross-silo Federated Learning remain to be addressed with care.

This edited book aims at lining up both academic researchers and industrial engineers to share original works in FL theory, algorithms, and applications. Novel methods to address challenging issues are particularly welcome. Topics of interest include but not limited to:


  1. Adversarial learning, data poisoning, adversarial examples, adversarial robustness, black box attacks and defense etc. for Federated Learning.
  2. Federated learning and distributed privacy-preserving techniques including secure multi-party computation, homomorphic encryption, secret sharing techniques, and differential privacy.
  3. Incentive mechanism and game theory in Federated Learning.


  1. Data value and economics of data federation.
  2. Safety and security assessment of federated learning applications.
  3. Solutions to privacy-preserving and small-data challenges in industries.
  4. Federated learning applications in finance, e-Commerce, urban computing, smart devices, public services etc.

Submission Guidelines

  1. Authors are invited to submit original work that has neither appeared elsewhere for publication, nor is presently under review for another refereed publication. Extensions of previously published works are welcome as long as the contributions made in the extended version are significant to warrant publication (a rule of thumb is to ensure at least 30% novel contributions).
  2. Authors are expected to prepare the full chapter draft, which must be at least 12 pages and at most 15 pages long, including tables, references, figures and appendices, if any. Full chapter MUST be prepared in Latex using following Author Guidelines and it should be submitted at: https://easychair.org/conferences/?conf=flpi2020
  3. We expect to have 15 to 20 chapters in this book.
  4. What to submit? You must submit a PDF file at our submission site by the specified deadline of July 31, 2020.
  5. Important Note: Authors are expected to submit a ZIP file containing the source code of latex files (i.e. .tex, .bib, and/or supporting PDF and Graphics). Instructions will be given during camera ready submission.

Editorial Team

Qiang Yang
Chief Artificial Intelligence Officer (CAIO), WeBank
Chair Professor, Hong Kong University of Science and Technology (HKUST)
Email: qiangyang@webank.com, qyang@cse.ust.hk

Lixin Fan
Principal Scientist, WeBank
Email: lixinfan@webank.com

Han Yu
Nanyang Assistant Professor, Nanyang Technological University (NTU)
Email: han.yu@ntu.edu.sg