3 papers
cs.LG2026
PhysAttNet: Enhancing Predictive Performance in Industrial and Astrophysical Time Series via Physics-Informed Attention
Amal Saadallah, Julia Tjus, Petra Wiederkeher +1
Accurate and robust time series forecasting is essential in many applications involving physical processes, such as manufacturing monitoring and astrophysical event detection. In t…
cs.LG2025
Adaptive Fine-Tuning via Pattern Specialization for Deep Time Series Forecasting
Amal Saadallah, Abdulaziz Al-Ademi
Time series forecasting poses significant challenges in non-stationary environments where underlying patterns evolve over time. In this work, we propose a novel framework that enha…
cs.LG2025
SHAP-Guided Regularization in Machine Learning Models
Amal Saadallah
Feature attribution methods such as SHapley Additive exPlanations (SHAP) have become instrumental in understanding machine learning models, but their role in guiding model optimiza…