Distributed and Continual Inference and Learning
Scope and Topics of Interest
Recent advances in Deep Learning and high-performance computing led to remarkable solutions for visual, audio, sensor, and multi-modal data analysis problems. Deep Learning-empowered systems can nowadays achieve performance levels in various data analysis tasks which are comparable to, or even exceeding, those of humans. Even though these advancements have the potential to open new high-impact applications in a variety of domains, including smart living spaces and critical infrastructures such as energy systems, challenges in many real-life applications go beyond the unrestricted analysis of visual, audio, and sensor data provided by Deep Learning models when run on high-end Graphics Processing Units (GPUs). While Edge Computing has had a significant impact on the development of IT system architectures, data-driven Artificial Intelligence has provided breakthrough developments on the algorithmic side of such systems. With the emergence of the Internet of Things (IoT) and computing (cloud-edge) continuum technologies (e.g., edge networks and storage) the paradigm of Artificial Intelligence of Things (AIoT) gives the potential to employ decentralized computing in efficient ways for enhancing AI capabilities.
Recent advances in Deep Learning and high-performance computing led to remarkable solutions for visual, audio, sensor, and multi-modal data analysis problems. Deep Learning-empowered systems can nowadays achieve performance levels in various data analysis tasks which are comparable to, or even exceeding, those of humans. Even though these advancements have the potential to open new high-impact applications in a variety of domains, including smart living spaces and critical infrastructures such as energy systems, challenges in many real-life applications go beyond the unrestricted analysis of visual, audio, and sensor data provided by Deep Learning models when run on high-end Graphics Processing Units (GPUs). While Edge Computing has had a significant impact on the development of IT system architectures, data-driven Artificial Intelligence has provided breakthrough developments on the algorithmic side of such systems. With the emergence of the Internet of Things (IoT) and computing (cloud-edge) continuum technologies (e.g., edge networks and storage) the paradigm of Artificial Intelligence of Things (AIoT) gives the potential to employ decentralized computing in efficient ways for enhancing AI capabilities.
For fully exploiting Deep Learning solutions in AIoT environments setting restrictions in processing power, memory consumption, hard real-timeness, handling uncertainties in the processing outcomes, and requiring a level of interpretability, a number of challenges need to be addressed through theoretical and methodological contributions, including but not limited to:
Efficient Deep Learning methodologies for Internet of Things
Deep Learning methodologies for distributed inference and learning
Continual Learning methods training lightweight Deep Learning models
Continual Inference of Deep Learning models
Lightweight Deep Learning models for visual, audio, sensor data analysis
Deep Learning models for efficient multimodal data analysis and fusion
Sensor time-series analysis based on Deep Learning
Deep Learning methodologies for smart cities, including Federated Learning, Transfer Learning, Domain Adaptation, and Split Computing
Privacy-preserving distributed learning and inference
Resource-efficient distributed learning
The aim of this special session is to bring together and disseminate state-of-the-art research contributions that address Distributed and Continual Inference and Learning approaches, including the analysis and design of novel algorithms and methodologies, innovative applications and enabling technologies, etc. Please consider to submit your latest research in the topic.
Paper preparation and submission guidelines
Submitted papers need to follow the guidelines of regular papers for IEEE MLSP 2024. Papers need to be submitted following the submission guidelines of IEEE MLSP 2024 and select the title of the Special Session during the submission process. Accepted papers will be included in the IEEE MLSP 2024 proceedings.
Important Dates (same as the main venue)
Paper submission: April 30, 2024
Notification of acceptance: June 31, 2024
Camera ready paper submission: July 31, 2024
Paper submission: April 30, 2024
Notification of acceptance: June 31, 2024
Camera ready paper submission: July 31, 2024
The Special Session is supported by the NordForsk Nordic University Cooperation on Edge Intelligence (NUEI) with project number 168043, and the HEU project PANDORA (GA number 101135775) .
For inquiries concerning this Special Session please feel free to contact us at ai [at] ece.au.dk