Thursday, March 10, 2022

[DMANET] Call for Papers: Special Issue on Federated, Distributed/Embedded Learning, and Learning at-the-Edge for Pervasive Systems

Special Issue on Federated, Distributed/Embedded Learning, and Learning
at-the-Edge for Pervasive Systems

Journal: Elsevier Pervasive and Mobile Computing
Submission link:

* Call for Papers
The explosion of data volumes generated at the edge of the internet by an
increasing number of devices combined with the growing attention and
sensitivity to privacy preservation of such data, is moving the whole AI
process from remote cloud facilities towards the edge of the network, i.e.,
data owners/holders are more and more unwilling to share their raw data
freely to build AI applications and services. However, the data and
computational landscape at the edge is so much different from the one in
the cloud, that it has stimulated the development of new learning
frameworks designed to cope with the several connected challenges at the
edge. This is the case for Federated Learning, to mention one, that is a
distributed learning framework specifically designed for being robust to
context where devices holding some local data collaborate to train a
globally shared AI model. The challenges to be addressed in learning at the
edge are many since the learning algorithm has to consider several aspects
like local data heterogeneity, device heterogeneity, technological
shortcomings like intermittent connectivity, devices with limited
computational resources, to mention a few.

Developing intelligent distributed and pervasive systems over federated
datasets overcoming the limitations imposed by the edge scenario faces new
exciting challenges in the design of new AI algorithms, federated and
distributed optimization methods, privacy and security mechanisms, and
system implementation. This special issue serves as a forum for researchers
and practitioners to present their latest research findings and engineering
experiences in the theoretical foundations, empirical studies, and novel
applications of federated learning, distributed and embedded learning for
next-generation pervasive systems. We welcome contributions proposing
advancements in theory, algorithms, systems, and applications of federated
learning, embedded learning in pervasive systems for various AI tasks to
establish the latest efforts of the research in this area.

* Topics of interest include but are not limited to:
- Federated/Distributed Machine Learning Algorithms for
Embedded/Mobile/Edge Systems
- Supervised/Semi-supervised/Unsupervised Federated/Distributed Learning
- Optimization Algorithms in Federated/Distributed Learning
- Incentive Mechanisms for Federated Learning
- Fairness in Federated Learning
- Communication-Efficient Distributed/Decentralised Machine Learning
- Efficient Privacy-Preserving & Secure Machine Learning
- Personalized Federated/Distributed Machine Learning
- Online/Continual Learning in Pervasive Systems
- Compression of machine learning models for real-time inference on
Embedded/Mobile/Edge Systems
- Efficient on-device learning

- Applications of Federated/Distributed/Embedded Learning for:
- Activity recognition
- Anomaly detection
- Urban computing
- Healthcare
- Industry 4.0
- COVID-19
- Smart Cities
- Smart Agriculture
- Audio and Video signals processing
- Emotion recognition
- Environmental applications
- Resilient Communication in Contested Environments

* Schedule:
- Expected first submission: May, 01 2022
- Submission deadline: June 01, 2022
- First review round completed: September, 15 2022
- Revised manuscripts due: December 01, 2022
- Completion of the review and revision process (final notification):
January 31, 2023

* Guest Editors
Dr. Lorenzo Valerio, IIT-CNR, Pisa, Italy (
Dr. Franco Maria Nardini, ISTI-CNR, Pisa, Italy (
Dr. Nirmalya Roy, University of Maryland, Baltimore County, USA (
Dr. Raghuveer Rao, U.S. DEVCOM Army Research Laboratory, USA (

* Contributions to be spread via DMANET are submitted to
* Replies to a message carried on DMANET should NOT be
* addressed to DMANET but to the original sender. The
* original sender, however, is invited to prepare an
* update of the replies received and to communicate it
* via DMANET.