4th IEEE Workshop on Pervasive and Resource-constrained Artificial Intelligence (PeRConAI)
co-located with IEEE PerCom 2025, March 17-21, 2025, Washington DC, USA

Website: http://perconai.iit.cnr.it
Email contact for info: perconai@iit.cnr.it

Call for Papers
---------------

PeRConAI will focus on solutions that contribute to advancing truly pervasive and liquid AI, enabling edge devices, regardless of their available resources, to accomplish training and inference under full, weak, or no supervision.

The increasing pervasiveness of edge devices and the high availability, velocity, and volatility of data generated and collected at the edge of the internet are pushing towards a paradigm shift in the design of AI-based systems. AI systems are moving the execution of both training and inference tasks from powerful and remote data centers where all data is available in a centralized fashion to more pervasive and distributed/decentralized systems at the edge of the internet, working in proximity to where data is physically generated and/or collected.
The design of edge AI systems must leverage the collaboration of several heterogeneous devices working in a highly dynamic context both in terms of processing capabilities and connectivity. Beyond resource limitations, data locally collected or generated by devices might statistically differ from one device to another, even if collected by the same application or belonging to the same phenomenon. Finally, human intervention in the AI process is still predominant, especially in its initial phases, e.g., data preparation, labeling, and pre-processing, thus limiting the necessary speed up to make AI truly pervasive.

Topics of interest
------------------
The PeRConAI workshop aims to foster the development and circulation of new ideas and research directions on pervasive and resource-constrained AI/ML, bringing together practitioners and researchers working on the intersection between pervasive computing and machine learning.
The PeRConAI workshop solicits contributions on, but not limited to, the following topics:

** Foundations of Advanced Machine learning algorithms and methods for pervasive systems subject to resource limitations addressing the following open challenges:

- Distributed/decentralized Machine Learning for resource-constrained devices (e.g., resource-efficient federated learning);
- Lightweight ML models for on-device training/inference in pervasive computing (e.g., GRU, ELM, MHN, etc.);
- Sustainable AI through new, brain- and bio-inspired ML algorithms exploiting energy-efficient hardware, e.g., FPGA, Neuromorphic HW;
- Compression of deep learning models for real-time inference
- Privacy-preserving distributed/decentralized learning in pervasive and resource-constrained scenarios;
- Trustworthiness of distributed/decentralized learning systems in pervasive and resource-constrained scenarios;
- Semi-supervised and self-supervised learning systems in pervasive and resource-constrained scenarios;
- Learning with imbalanced data in pervasive and resource-constrained scenarios;
- Continual learning in pervasive and resource-constrained scenarios;
Over-the-air computing for distributed/decentralized learning systems in pervasive and resource-constrained scenarios.

** Applications of Advanced Machine learning algorithms, methods, and approaches for pervasive computing under resource limitations applied to the following application domains:

- Health and well-being applications (e.g., activity recognition, health monitoring).
- Anomaly/Novelty detection (e.g., Industry 4.0, intrusion detection, privacy, and security).
- Audio signal processing (e.g., sound event detection, speech recognition/processing).
- Video stream processing on resource-constrained devices.
- Natural Language Processing and Information Retrieval (e.g., conversational applications running on resource-constrained, mobile, or
edge devices).
- Intersection between mobile computing with ML/DL on resource-constrained devices.
- Any other real-world applications and case studies where the pervasiveness of resource-constrained devices is central for knowledge extraction.

Submissions Guidelines
----------------------
All papers must be at most 6 pages of technical content, typeset in double-column IEEE format using 10pt fonts on US letter paper, with all fonts embedded. In PeRConAI, the peer-review process will be double-blind.
Submissions must be made via EasyChair. The IEEE LaTeX and Microsoft Word templates and related information can be found on the IEEE Computer Society website.

PeRConAI will be held in conjunction with IEEE PerCom 2025 (https://www.percom.org). All accepted papers will be included in the Percom workshop proceedings and indexed in the IEEEXplore digital library. At least one author must fully register for the conference and present the paper during the workshop. We also strongly suggest that authors of submitted papers be prepared to apply for their US visa as soon as they are accepted.

Submission Steps:
1- Follow the submission link: https://easychair.org/my/conference?conf=percom2025
2- Select PeRConAI (4th Workshop on Pervasive and Resource-Constrained AI)
3- Fill in the form and upload the paper in PDF format.

Organizing Committee
--------------------
Prof. Plamen Angelov, Lancaster University, UK
Prof. Mario Luca Bernardi, University of Sannio, IT
Dr. Paolo Dini, CTTC, ES
Dr. Franco Maria Nardini, ISTI-CNR, IT
Prof. Riccardo Pecori, eCampus University, IT and IMEM-CNR, IT
Dr. Lorenzo Valerio, IIT-CNR, IT