approXimation for adaptable diStributed artificial intelligence (XS)
This research is funded by the Slovenian National Research Agency (ARRS) project number N2-0393 [SICRIS]
Project team:
- Dr. Veljko Pejović
- Dr. Alina Machidon
- Boris Radovič
- Aneta Kartali
Description
Conventional means of implementing artificial intelligence (AI) introduce serious impediments related to data centralisation, model bias, and exclusion of certain users. These hazards become particularly concerning as our reliance on AI grows and we start employing it in a range of life-critical tasks, from medical diagnostics to autonomous driving. With the goal of making AI more inclusive and more efficient, in this project we strive to set the ground for such AI to become feasible in years to come. XS is based on the insight that the key limiting factors for efficient AI the computational burden of model training can be selectively reduced to enable the incorporation of broader populations and attainment of more detailed learning goals.
To realise XL we will:
- Advance beyond backpropagation-based deep learning training methods and enable lightweight training particularly well suited for edge computing devices;
- Design and implement dynamically-tunable approximation of on-device neural network training, thus enabling heterogeneous devices to synchronously work towards joint AI models;
- Explore a range of novel paradigms for distributed learning that combine federated and split learning, and thus enable flexible distribution of computation (neural network training) over a set of heterogeneous computing devices.
Publications:
- I. Kirovska and V. Pejović
The Reports of My Capabilities Are Greatly Exaggerated - Small LLMs for Depression Inference from Mobile Sensing Data
Workshop on Mental Health and Well-being: From Research to Practice in Mental Health with ACM UbiComp, Espoo, Finland, 2025. - V. Pejović
Embracing Shifting Trends and Reviving Smartphone Sensing
IEEE Pervasive Computing (2025). - B. Radovič, M. Canini, S. Horvath, V. Pejović, and P. Vepakomma
Towards a Unified Framework for Split LearningEuroMLSys workshop with EuroSys, Rotterdam, Netherlands, March 2025. - M. Korelič, O. Machidon, and V. Pejović
SELLMA: Semantic Location through On-Device LLMs and WiFi Sensing
ACM EdgeSys workshop with EuroSys, Rotterdam, Netherlands, March 2025.