Connectionists: CFP - Reminder - ESANN 2024 - SS - Machine learning in distributed, federated and non-stationary environments

[Frank-Michael Schleif]

CALL FOR PAPERS - ESANN 2024

Special Session on "Machine learning in
distributed, federated and non-stationary environments"

*DEADLINE*
Paper submission deadline: 2 May 2024
Notification of acceptance: 16 June 2024
The ESANN 2024 conference: 9-11 October 2024

*WEBSITE*
https://www.esann.org/

*DESCRIPTION*
Today machine learning is often done in a distributed setting to process
large data sets, compute high-complex models, but also to ensure data
privacy constraints in accessing the data.

Relevant data is often distributed among many individual users and cannot
be bundled directly for analysis. Also, the data is often dynamic,
generated as a data stream, or drifting over time.

Learning from this huge, heterogeneous and growing amount of data requires
flexible learning models that can adapt over time and deal with potentially
non-i.i.d., non-stationary input data. Another challenge could be costs for
energy consumption, transmission costs, and alike. The latter is
particularly crucial if machine learning is done using smart systems
(drones, unmanned vehicles ...), which should act independently over a
longer time.

This special session welcomes novel research about machine learning in a
non-stationary and distributed/federated setting.

*TOPICS AND THEMES*

We encourage the submission of papers on novel methods for topics like
streaming data processing, federated learning, distributed learning by
means of computational intelligence and machine learning approaches,
including but not limited to:

- Data analysis and pattern recognition approaches for non-stationary and
distributed environments

- Learning in heterogeneous systems

- Effective communication for updating distributed models

- Model compression and adaptive model aggregation

- Representation and modeling of distributed models

- Approximation techniques for non-stationary or distributed data

Algorithms for the processing and analysis of streaming data

- Federated learning algorithms and variants, e.g., Split learning, Gossip
Learning, and decentralized Federated Learning

- Security and privacy preservation in federated environments

- Differential privacy techniques

- Application of Deep Learning in the Federated Learning context

- Particular interesting applications in IoT, recommendation systems,

medicine, sensor networks, text processing...


*ORGANIZERS*
Mirko Polato, Universit? di Torino, Italy
Barbara Hammer, University of Bielefeld, Germany
Frank-Michael Schleif, Technical UAS Wuerzburg-Schweinfurt, Germany

-- 
-------------------------------------------------------
Prof. Dr. rer. nat. habil. Frank-Michael Schleif
School of Computer Science
Technical University of Applied Sciences Würzburg-Schweinfurt
Sanderheinrichsleitenweg 20
Raum I-3.35
Tel.: +49(0) 931 351 18127
97074 Würzburg

Honorable Research Fellow
The University of Birmingham
Edgbaston
Birmingham B15 2TT
United Kingdom
-
email: frank-michael.schleif at thws.de
http://promos-science.blogspot.de/
https://www.techfak.uni-bielefeld.de/~fschleif/
-------------------------------------------------------