204 citations · 381 across the 42 of their papers we have counts for
6 papers · 1 filter
Flatness is Necessary, Neural Collapse is Not: Rethinking Generalization via Grokking
Ting Han, Linara Adilova, Henning Petzka +2
Neural collapse, i.e., the emergence of highly symmetric, class-wise clustered representations, is frequently observed in deep networks and is often assumed to reflect or enable ge…
Whom to Trust? Adaptive Collaboration in Personalized Federated Learning
Amr Abourayya, Jens Kleesiek, Bharat Rao +1
Data heterogeneity poses a fundamental challenge in federated learning (FL), especially when clients differ not only in distribution but also in the reliability of their prediction…
Little is Enough: Boosting Privacy by Sharing Only Hard Labels in Federated Semi-Supervised Learning
Amr Abourayya, Jens Kleesiek, Kanishka Rao +4
In many critical applications, sensitive data is inherently distributed and cannot be centralized due to privacy concerns. A wide range of federated learning approaches have been p…
FAM: Relative Flatness Aware Minimization
Linara Adilova, Amr Abourayya, Jianning Li +5
Flatness of the loss curve around a model at hand has been shown to empirically correlate with its generalization ability. Optimizing for flatness has been proposed as early as 199…
Review of Disentanglement Approaches for Medical Applications -- Towards Solving the Gordian Knot of Generative Models in Healthcare
Jana Fragemann, Lynton Ardizzone, Jan Egger +1
Deep neural networks are commonly used for medical purposes such as image generation, segmentation, or classification. Besides this, they are often criticized as black boxes as the…
Certified Adversarial Defenses Meet Out-of-Distribution Corruptions: Benchmarking Robustness and Simple Baselines
Jiachen Sun, Akshay Mehra, Bhavya Kailkhura +4
Certified robustness guarantee gauges a model's robustness to test-time attacks and can assess the model's readiness for deployment in the real world. In this work, we critically e…