Mehdi Bennis

Full Professor, University of Oulu

Joined

April 2022

Names

Mehdi Bennis (Preferred)

Emails

****@oulu.fi (Confirmed)

Personal Links

Homepage

Career & Education History

Full Professor

University of Oulu (oulu.fi)

2021 – Present

Advisors, Relations & Conflicts

No relations added

Expertise

Semantic communication

2020 – Present

edge AI

2017 – Present

Publications

Server-side local gradient averaging and learning rate acceleration for scalable split learning
Shraman Pal, Mansi Uniyal, Jihong Park, Praneeth Vepakomma, Ramesh Raskar, Mehdi Bennis, Moongu Jeon, Jinho Choi
- FL-AAAI-22
- Readers: Everyone
Tutorial on Joint Embedding Predictive Architectures (JEPA): Foundations, Applications, and Future Directions
Mehdi Monemi, Maryam Chinipardaz, Mehdi Rasti, Mehdi Bennis, Matti Latva-aho
- OpenReview Archive Direct Upload
- Readers: Everyone
Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach
Chaouki Ben Issaid, Praneeth Vepakomma, Mehdi Bennis
- Accepted by TMLR
- Readers: Everyone
Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach
Chaouki Ben Issaid, Praneeth Vepakomma, Mehdi Bennis
- Submitted to ICLR 2025
- Readers: Everyone
Privacy-Preserving Split Learning with Vision Transformers using Patch-Wise Random and Noisy CutMix
Seungeun Oh, Sihun Baek, Jihong Park, Hyelin Nam, Praneeth Vepakomma, Ramesh Raskar, Mehdi Bennis, Seong-Lyun Kim
- Accepted by TMLR
- Readers: Everyone
Differentially Private CutMix for Split Learning with Vision Transformer
Seungeun Oh, Jihong Park, Sihun Baek, Hyelin Nam, Praneeth Vepakomma, Ramesh Raskar, Mehdi Bennis, Seong-Lyun Kim
- 06 Oct 2022 (modified: 05 May 2023)
- INTERPOLATE at NeurIPS 2022
- Readers: Everyone
DR-DSGD: A Distributionally Robust Decentralized Learning Algorithm over Graphs
Chaouki Ben Issaid, Anis Elgabli, Mehdi Bennis
- Accepted by TMLR
- Readers: Everyone

Mehdi Bennis

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

Server-side local gradient averaging and learning rate acceleration for scalable split learning

Tutorial on Joint Embedding Predictive Architectures (JEPA): Foundations, Applications, and Future Directions

Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach

Tackling Feature and Sample Heterogeneity in Decentralized Multi-Task Learning: A Sheaf-Theoretic Approach

Privacy-Preserving Split Learning with Vision Transformers using Patch-Wise Random and Noisy CutMix

Differentially Private CutMix for Split Learning with Vision Transformer

DR-DSGD: A Distributionally Robust Decentralized Learning Algorithm over Graphs

Co-Authors