Ömer Faruk Akgül

I am a 4th year Ph.D. student in Computer Science at University of Southern California, advised by Prof. Viktor Prasanna. I received B.Sc. in Computer Science at Bilkent University. Previously, I conducted research with Prof. Tudor Dumitras at the University of Maryland, investigating the impact of malware variability on machine learning models.

My current research include:

Efficient & Robust LLM Reasoning
Graph Neural Networks
Temporal knowledge graphs and their applications

news

Jun 09, 2025	I started working as an Applied Science Intern at Amazon. I will be working on Text-to-SQL systems.
Aug 15, 2024	Conformal Prediction for Federated Graph Neural Networks with Missing Neighbor Information is accepted to UAI’25!
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!

publications

LLM

RECIPE-TKG: From Sparse History to Structured Reasoning for LLM-based Temporal Knowledge Graph Completion

Ömer Faruk Akgül^*, Feiyu Zhu^*, Yuxin Yang, and 2 more authors

arXiv preprint arXiv:2505.17794, 2025

Submitted to ACL ’26

Bib

@article{akgul2025recipe,
  title = {RECIPE-TKG: From Sparse History to Structured Reasoning for LLM-based Temporal Knowledge Graph Completion},
  author = {Akgül, Ömer Faruk and Zhu, Feiyu and Yang, Yuxin and Kannan, Rajgopal and Prasanna, Viktor},
  journal = {arXiv preprint arXiv:2505.17794},
  year = {2025},
  note = {Submitted to ACL '26},
}

LLM

Tina: Tiny Reasoning Models via LoRA

Shangshang Wang, Julian Asilis, Ömer Faruk Akgül, and 3 more authors

arXiv preprint arXiv:2504.15777, 2025

Submitted to ICLR ’26

Bib

@article{wang2025tina,
  title = {Tina: Tiny Reasoning Models via LoRA},
  author = {Wang, Shangshang and Asilis, Julian and Akgül, Ömer Faruk and Bilgin, Enes Burak and Liu, Ollie and Neiswanger, Willie},
  journal = {arXiv preprint arXiv:2504.15777},
  year = {2025},
  note = {Submitted to ICLR '26},
}

GNN

Training Diverse Graph Experts for Ensembles: A Systematic Empirical Study

Gangda Deng^*, Yuxin Yang^*, Ömer Faruk Akgül^*, and 4 more authors

arXiv preprint arXiv:2510.18370, 2025

Submitted to KDD ’26

Bib

@article{deng2025training,
  title = {Training Diverse Graph Experts for Ensembles: A Systematic Empirical Study},
  author = {Deng, Gangda and Yang, Yuxin and Akgül, Ömer Faruk and Zeng, Hanqing and Xia, Yinglong and Kannan, Rajgopal and Prasanna, Viktor},
  journal = {arXiv preprint arXiv:2510.18370},
  year = {2025},
  note = {Submitted to KDD '26},
}

LLM

Resa: Transparent Reasoning Models via SAEs

Shangshang Wang, Julian Asilis, Ömer Faruk Akgül, and 4 more authors

arXiv preprint arXiv:2506.09967, 2025

NeurIPS 2025 Workshop on Efficient Reasoning

Bib

@article{wang2025resa,
  title = {Resa: Transparent Reasoning Models via SAEs},
  author = {Wang, Shangshang and Asilis, Julian and Akgül, Ömer Faruk and Bilgin, Enes Burak and Liu, Ollie and Fu, Deqing and Neiswanger, Willie},
  journal = {arXiv preprint arXiv:2506.09967},
  year = {2025},
  note = {NeurIPS 2025 Workshop on Efficient Reasoning},
}

GNN

Conformal Prediction for Federated Graph Neural Networks with Missing Neighbor Information

Ömer Faruk Akgül, Rajgopal Kannan, and Viktor Prasanna

In Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI), 2025

Bib

@inproceedings{akgul2025conformal,
  title = {Conformal Prediction for Federated Graph Neural Networks with Missing Neighbor Information},
  author = {Akgül, Ömer Faruk and Kannan, Rajgopal and Prasanna, Viktor},
  booktitle = {Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI)},
  year = {2025},
}

GNN

An Efficient Distributed Graph Engine for Deep Learning on Graphs

Gangda Deng^*, Ömer Faruk Akgül^*, Hongkuan Zhou, and 4 more authors

In Proceedings of the SC’23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis, 2023

Bib

@inproceedings{deng2023efficient,
  title = {An Efficient Distributed Graph Engine for Deep Learning on Graphs},
  author = {Deng, Gangda and Akgül, Ömer Faruk and Zhou, Hongkuan and Zeng, Hanqing and Xia, Yinglong and Li, Jianbo and Prasanna, Viktor},
  booktitle = {Proceedings of the SC'23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis},
  pages = {922--931},
  year = {2023}
}