Exploring Machine Learning in Dynamic and Decentralized Environments: ESANN 2024 Special Session

Machine learning is increasingly being applied to distributed and heterogeneous data, which poses unique challenges. With the rise of data privacy concerns and the need to process vast amounts of data in real-time, machine learning models must be flexible and adaptive. This special session at ESANN 2024 invites researchers to submit papers on innovative methods for machine learning in non-stationary and distributed/federated settings. Topics of interest include data analysis techniques, model compression, communication optimization, representation learning, and federated learning algorithms. Applications span various domains such as IoT, healthcare, sensor networks, and text processing. Join us in exploring novel solutions to address the challenges of machine learning in dynamic and decentralized environments.