Ömer Faruk Akgül
I am a 3rd year Ph.D. student in Computer Science at University of Southern California, advised by Prof. Viktor Prasanna. I receieved B.Sc. in Computer Science at Bilkent University. Previously, I conducted research with Prof. Tudor Dumitras at the University of Maryland Institute for Advanced Computer Studies (UMIACS), investigating the impact of malware variability on machine learning models. My research centers on machine learning for graph-structured data and the integration of large language models (LLMs) with graph-based approaches. Key areas of interest include:
- Uncertainty modeling in graph neural networks (GNNs)
- Scaling GNNs for large-scale applications
- Temporal knowledge graphs and their applications
- Enhancing the reasoning capabilities of LLMs
news
| Aug 15, 2024 | Conformal Prediction for Federated Graph Neural Networks with Missing Neighbor Information is on arxiv! |
|---|---|
| May 15, 2023 | An Efficient Distributed Graph Engine for Deep Learning on Graphs accepted to the SC’23 workshop. |
| Aug 22, 2022 | Started the PhD program in Computer Science at USC, joining Prof. Viktor Prasanna’s research group. |
| Jun 15, 2021 | I’m excited to join UMD MC2 as a summer intern! |
selected publications
- GNN
An Efficient Distributed Graph Engine for Deep Learning on GraphsIn Proceedings of the SC’23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis, 2023 - GNN
Conformal Prediction for Federated Graph Neural Networks with Missing Neighbor Information2024Under submission to ICLR 2025
