Najah Ghalyan

According to our database, Najah Ghalyan authored at least 5 papers between 2023 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Efficient and Explainable Anomaly Detection in Financial System Logs Using Statistical Modeling.

Mohammed Ayub, Mauro Annarumma, Gaston Liberman, David Algorry, Kostis Gourgoulias, Najah Ghalyan, Sean J. Moran

Proceedings of the 2nd IEEE/ACM Workshop on Software Engineering Challenges in Financial Firms, 2025

2024

Estimating class separability of text embeddings with persistent homology.

Kostis Gourgoulias, Najah Ghalyan, Maxime Labonne, Yash Satsangi, Sean J. Moran, Joseph Sabelja

Trans. Mach. Learn. Res., 2024

DeepClean: Machine Unlearning on the Cheap by Resetting Privacy Sensitive Weights Using the Fisher Diagonal.

Jialei Shi, Kostis Gourgoulias, John F. Buford, Sean J. Moran, Najah Ghalyan

Proceedings of the Computer Vision - ECCV 2024 Workshops, 2024

2023

DeepClean: Machine Unlearning on the Cheap by Resetting Privacy Sensitive Weights using the Fisher Diagonal.

Jiaeli Shi, Najah Ghalyan, Kostis Gourgoulias, John F. Buford, Sean J. Moran

CoRR, 2023

An Unsupervised Method for Estimating Class Separability of Datasets with Application to LLMs Fine-Tuning.

Najah Ghalyan, Kostis Gourgoulias, Yash Satsangi, Sean J. Moran, Maxime Labonne, Joseph Sabelja

CoRR, 2023