Prof Blesson Varghese

Professor

Researcher profile

Phone

+44 (0)1334 46 3262

Email

blesson@st-andrews.ac.uk

 

Biography

Blesson Varghese is Reader in the School of Computer Science at the University of St Andrews. He directs the Edge Computing Hub funded by Rakuten, Japan.

He was the recipient of the 2021 IEEE Rising Star Award and a Royal Society industry fellowship to British Telecoms plc, UK. His research interests are in developing large-scale distributed systems spanning the cloud and the edge of the network and has academic, industry and consulting experience in multiple continents.

He has featured in 'Clouded', a documentary on the cloud produced by Hewlett Packard and VMWare, and has interviewed on broadcast media.

Find more information on his personal homepage or Google Scholar profile. 

Teaching

I teach CS5052: Data-Intensive Systems that focuses on the design of large-scale distributed systems encompassing the cloud and the edge. 

I also supervise undergraduate and postgraduate projects. 

Research areas

My research focuses on addressing systems-related challenges for developing large-scale distributed systems, specifically those encompassing the cloud and the edge of the network. My current interests are in unlocking the scientific and societal potential in 'Edge computing', referred to as the next Internet frontier. 

PhD supervision

• Jiawei Luo
• Dhananjay Saikumar
• Zihan Zhang

Selected publications

• EMO: Edge Model Overlays to scale model size in federated learning

  Wu, D., He, W., Feng, W., Wen, Z., Qian, B. & Varghese, B., 21 Jul 2025, p. 1-6. 6 p.

  Research output: Contribution to conference › Poster › peer-review

• FedFreeze: a dual-phase layer freezing framework for federated learning

  Wu, D., Wong, L. & Varghese, B., 26 Nov 2025, (E-pub ahead of print) In: Future Generation Computer Systems. 177, 108250.

  Research output: Contribution to journal › Article › peer-review

• Open access

  Mosaic: composite projection pruning for resource-efficient LLMs

  Eccles, B. J., Wong, L. & Varghese, B., Feb 2026, In: Future Generation Computer Systems. 175, p. 1-15 15 p., 108056.

  Research output: Contribution to journal › Article › peer-review

• Open access

  DNNShifter: an efficient DNN pruning system for edge computing

  Eccles, B. J., Rodgers, P., Kilpatrick, P., Spence, I. & Varghese, B., Mar 2024, In: Future Generation Computer Systems. 152, p. 43-54

  Research output: Contribution to journal › Article › peer-review

• Open access

  EcoFed: efficient communication for DNN partitioning-based federated learning

  Wu, D., Ullah, R., Rodgers, P., Kilpatrick, P., Spence, I. & Varghese, B., 4 Jan 2024, In: IEEE Transactions on Parallel and Distributed Systems. Early Access, 13 p., 10380682.

  Research output: Contribution to journal › Article › peer-review

• Open access

  Enabling privacy-aware interoperable and quality IoT data sharing with context

  Chhetri, T. R., Dehury, C. K., Varghese, B., Fensel, A., Srirama, S. N. & DeLong, R. J., Aug 2024, In: Future Generation Computer Systems. 157, p. 164-179

  Research output: Contribution to journal › Article › peer-review

• Open access

  NeuroFlux: memory-efficient CNN training using adaptive local learning

  Saikumar, D. & Varghese, B., Apr 2024, EuroSys '24: Proceedings of the Nineteenth European Conference on Computer Systems. ACM, p. 999-1015 17 p.

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

• Open access

  PiPar: Pipeline parallelism for collaborative machine Learning

  Zhang, Z., Rodgers, P., Kilpatrick, P., Spence, I. & Varghese, B., Nov 2024, In: Journal of Parallel and Distributed Computing. 193, 17 p., 104947.

  Research output: Contribution to journal › Article › peer-review

• Open access

  Rapid deployment of DNNs for edge computing via structured pruning at initialization

  Eccles, B. J., Wong, L. & Varghese, B., 8 Oct 2024, 2024 IEEE/ACM 24th International symposium on cluster, cloud and internet computing (CCGrid). Los Alamitos: IEEE, p. 317 - 326 10 p. 10701394. (IEEE International symposium on cluster, cloud and internet computing (CCGrid)).

  Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

• Open access

  ScissionLite: accelerating distributed deep learning with lightweight data compression for IIoT

  Ahn, H., Lee, M., Seong, S., Na, G.-J., Chun, I.-G., Varghese, B. & Hong, C.-H., 24 Jun 2024, (E-pub ahead of print) In: IEEE Transactions on Industrial Informatics. Early Access, 11 p.

  Research output: Contribution to journal › Article › peer-review

 

See more publications