14 citations · 31 across the 73 of their papers we have counts for
6 papers · 1 filter
Knowledge Graph Sparsification for GNN-based Rare Disease Diagnosis
Premt Cara, Kamilia Zaripova, David Bani-Harouni +2
Rare genetic disease diagnosis faces critical challenges: insufficient patient data, inaccessible full genome sequencing, and the immense number of possible causative genes. These…
Stress-Aware Resilient Neural Training
Ashkan Shakarami, Yousef Yeganeh, Azade Farshad +3
This paper introduces Stress-Aware Learning, a resilient neural training paradigm in which deep neural networks dynamically adjust their optimization behavior - whether under stabl…
Stability, Complexity and Data-Dependent Worst-Case Generalization Bounds
Mario Tuci, Lennart Bastian, Benjamin Dupuis +3
Providing generalization guarantees for stochastic optimization algorithms remains a key challenge in learning theory. Recently, numerous works demonstrated the impact of the geome…
PhenoKG: Knowledge Graph-Driven Gene Discovery and Patient Insights from Phenotypes Alone
Kamilia Zaripova, Ege Özsoy, Nassir Navab +1
Identifying causative genes from patient phenotypes remains a significant challenge in precision medicine, with important implications for the diagnosis and treatment of genetic di…
Does Machine Unlearning Truly Remove Knowledge?
Haokun Chen, Yueqi Zhang, Yuan Bi +9
In recent years, Large Language Models (LLMs) have achieved remarkable advancements, drawing significant attention from the research community. Their capabilities are largely attri…
VeLU: Variance-enhanced Learning Unit for Deep Neural Networks
Ashkan Shakarami, Yousef Yeganeh, Azade Farshad +3
Activation functions play a critical role in deep neural networks by shaping gradient flow, optimization stability, and generalization. While ReLU remains widely used due to its si…