activity
20242026
most citedCounterfactual Explanations for Medical Image Classification and Regression using Diffusion Autoencoder

14 citations · 31 across the 73 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2025

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…

cs.LG2025

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…

cs.LG2025

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…

cs.LG2025

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…

cs.LG2025

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…

cs.LG2025

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…