Federated Learning and Cooperative Neural Networks (CoNN) Special Session - International Joint Conference on Neural Network 2022
IJCNN 2022 - FEDERATED LEARNING S.S. 2022
- URL: https://sites.google.com/view/federatedlearning-ss-ijcnn2022/home-page
- Event Date: 2022-07-18 ~ 2022-07-23
- Submission Date: 2022-01-31
Special Session Abstract:
Federated Learning (FL) comes to rescue from standard centralized training of machine learning models, that is unfeasible in many interesting use-cases, where the associated data transfer and maintenance costs (e.g., video analytics), privacy concerns (e.g., in healthcare and justice domains settings), or sensitivity of the proprietary data (e.g., in drug discovery) represent a heavy bottleneck. And yet, different parties that own even a small amount of data would benefit from access to accurate models. So, Federated learning allows multiple clients owning data to train shared models collaboratively, under the orchestration of a central server without having to share raw data. Typically, FL proceeds in multiple rounds of communication between the server and the clients: the clients compute model updates on their local data and send them to the server which aggregates and applies these updates to the shared model. While gaining popularity very quickly, FL is a relatively new subfield with many open questions and unresolved challenges, as the Statistical Unbalancing of Data, Distributed Optimization Problems, Communication Latency as far as Security and Resilience to attacks issues, that has attracted increasing interest from the international research communities.
Main Goals of this Special Session:
The main objective of the 2022 Special Session on Federated Learning and Distribute Cooperative Learning, hosted in the IEEE International Joint Conference on Neural Networks (IJCNN), among the world most influential international conferences on Neural Networks, is to recall the international research community's attention to the emerging perspective and practical algorithms in Federated Learning and Cooperative Neural Networks A goal that this session aims to reach consists in collecting several novel contributions and research experiences from the Federated Learning studies and applications, from different research communities and concerning different but complementary solutions and proposals to mitigate issues and optimize Federated Learning algorithms. Attention paid to Federated Learning and Cooperative NN has grown significantly in the last few times, thus witnessing a remarkable increase in the research contributions published in the last months of the 2021 year. The expected outcomes are very high quality and novel contributions, to help take a step forward in this interesting but complex area.
The main outcomes of the first edition of this special session, held in 2021, were represented by a reinforced interest in the challenges and solutions to the main issue related to distributed learning paradigms as the Federated Learning and the Cooperative Neural Networks and the creation of research collaboration for sharing findings and building something better than the existent.
So, we were encouraged to propose once again this special session in order to provide the opportunity to share findings, advances with the past participants and new researchers.
Topics of the Special Session include (but are 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
Here is more detailed information about deadlines and submission instructions:
- Deadlines: https://wcci2022.org/dates/
- Authors'Instructions: https://wcci2022.org/submission/
Federated Learning (FL) comes to rescue from standard centralized training of machine learning models, that is unfeasible in many interesting use-cases, where the associated data transfer and maintenance costs (e.g., video analytics), privacy concerns (e.g., in healthcare and justice domains settings), or sensitivity of the proprietary data (e.g., in drug discovery) represent a heavy bottleneck. And yet, different parties that own even a small amount of data would benefit from access to accurate models. So, Federated learning allows multiple clients owning data to train shared models collaboratively, under the orchestration of a central server without having to share raw data. Typically, FL proceeds in multiple rounds of communication between the server and the clients: the clients compute model updates on their local data and send them to the server which aggregates and applies these updates to the shared model. While gaining popularity very quickly, FL is a relatively new subfield with many open questions and unresolved challenges, as the Statistical Unbalancing of Data, Distributed Optimization Problems, Communication Latency as far as Security and Resilience to attacks issues, that has attracted increasing interest from the international research communities.
Main Goals of this Special Session:
The main objective of the 2022 Special Session on Federated Learning and Distribute Cooperative Learning, hosted in the IEEE International Joint Conference on Neural Networks (IJCNN), among the world most influential international conferences on Neural Networks, is to recall the international research community's attention to the emerging perspective and practical algorithms in Federated Learning and Cooperative Neural Networks A goal that this session aims to reach consists in collecting several novel contributions and research experiences from the Federated Learning studies and applications, from different research communities and concerning different but complementary solutions and proposals to mitigate issues and optimize Federated Learning algorithms. Attention paid to Federated Learning and Cooperative NN has grown significantly in the last few times, thus witnessing a remarkable increase in the research contributions published in the last months of the 2021 year. The expected outcomes are very high quality and novel contributions, to help take a step forward in this interesting but complex area.
The main outcomes of the first edition of this special session, held in 2021, were represented by a reinforced interest in the challenges and solutions to the main issue related to distributed learning paradigms as the Federated Learning and the Cooperative Neural Networks and the creation of research collaboration for sharing findings and building something better than the existent.
So, we were encouraged to propose once again this special session in order to provide the opportunity to share findings, advances with the past participants and new researchers.
Topics of the Special Session include (but are 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
Here is more detailed information about deadlines and submission instructions:
- Deadlines: https://wcci2022.org/dates/
- Authors'Instructions: https://wcci2022.org/submission/
Journal Promotion
|
| Acta Koreana (Acta Koreana) |
|
| Acta Via Serica (AVS) |
|
| Computers and Concrete (CAC) |
|
| Journal of Information Processing Systems (JIPS) |
|
| Journal of Internet Computing and Services (KSII - JICS) |
|
| Journal of Smart Tourism (Smart Tourism) |
|
| Membrane and Water Treatment (MWT) |
|
| Wind and Structures, An International Journal (Wind and Structures) |
MANUSCRIPTLINK © 2015 -
