=====================================================================================
KES-2022-IS18: Federated Learning: Advances and Open Challenges in Distributed and Cooperative Learning Models
http://kes2022.kesinternational.org/cmsISdisplay.php
=====================================================================================


MISSION:
------------------------------------------------------------------------------
Federated Learning and Cooperative NN are growing in importance and number of applications, enabling the computational capabilities of the modern distributed networks, that generating a wealth of data each day. Federated and Cooperative Learning is promising in mitigating the issues concerning privacy protection and private information sharing. It is increasingly attractive to store data locally and push network computation to the edge devices. Federated learning has emerged as a training paradigm in such settings but it raises new questions at the intersection of machine learning and systems and requires fundamental advances in privacy, large-scale machine learning, and distributed optimization areas. Federated learning and classical distributed learning share a similar goal of minimizing the empirical risk over distributed entities. However, solving this objective in the federated settings poses some fundamental challenges as Privacy Concerns, Systems Heterogeneity, Statistical Heterogeneity, Expensive Communication, Trust in Federation Membership. According to both the recent experiences and the trends addressed by the most authoritative players in the AI field (Facebook AI, Google AI), supported also by the availability of specific frameworks (cfr. TensorFlow Federated, e.g.), Federated and Cooperative Learning are among the most recent and challenging paradigm related to machine learning and to its implementations by Deep Neural Networks, also considering that such great open issues are related to security aspects, like vulnerabilities to both data and model poisoning attacks, to the trustworthiness and robustness of the models as well as the quality evaluation of federated learning models against real-world data when that data is not available in a data center.


TOPICS:
------------------------------------------------------------------------------
We are interested in receiving submissions related to innovative research, technical use cases, and project demonstrators covering one or more of the following main topics (not limited to):
• Advances, novel issues, and open challenges in Federated Learning
• Optimization of Distributed Consensus Strategies
• Federated Learning Trust Policy and Strategies
• Resilient and Trustworthy Federated Learning
• Security Concerns with Federated Learning
• Poisoning Attacks and Countermeasures in Reliable Federated Learning
• Resilience Issues in Federated Learning
• Resilience, Robustness, Reliability and Trustworthiness Measures in Federated Learning Models
• Performance Evaluation Methods, Metrics and Tools of Federated Learning Systems
• Performance Optimization of Federated Learning Models
• Privacy Concerns and Federated Learning
• Case Studies and Applications of Federated Learning
• Federated Learning frameworks and tools employment and comparisons.
• Federated Learning and Blockchain
• Federated Learning For IoT
• Federated Learning For Smart Grids
• Federated Learning For Energy Efficiency In IoT
• Federated Learning For Industrial Applications
• Federated Learning and Graph-based Approaches for Fraud Detection
• Federated Learning For Intrusion Detection In IoT
• Federated Learning With Edge Computing For Cybersecurity In IoT
• Federated Learning For Privacy Preservation Of The Users In Social Media Apps


PAPER SUBMISSION:
------------------------------------------------------------------------------
Papers are invited for KES2022 on topics lying within the scope of the conference. All contributions must be of high quality, original, and must not have been previously published elsewhere or intended for publication elsewhere. All papers will be reviewed by members of the International Programme Committee and depending on their level and attributes, may be selected for oral or poster presentation, and publication in the conference proceedings.
Full papers will be reviewed by the IPC and if accepted and presented, they will be published in Elsevier's Procedia Computer Science open access journal, available in ScienceDirect and submitted to be indexed/abstracted in CPCI (ISI conferences and part of Web of Science), Engineering Index, and Scopus.
Authors of selected papers may be invited to submit extended versions of their papers for publication as full journal papers, for example in the KES Journal or other journals.
To submit a paper please follow the procedure described at the KES-2022 website http://kes2022.kesinternational.org/submission.php.


IMPORTANT DATES:
------------------------------------------------------------------------------
Submission of Papers: 18 May 2022
Notification of Acceptance: 21 May 2022
Upload Final Publication Files: 03 June 2022


FOR ANY OTHER INFORMATION, PLEASE VISIT
http://kes2022.kesinternational.org/cmsISdisplay.php