6 citations · 12 across the 24 of their papers we have counts for
16 papers · 1 filter
Memorisation bias in medical AI
Moritz A. Knolle, Martin J. Menten, Laurin Lux +5
Medical AI models hold immense potential to improve patient outcomes, but they are also known to unintentionally memorise individual records from their training datasets. While suc…
It depends: Incorporating correlations for joint aleatoric and epistemic uncertainties of high-dimensional output spaces
Leonhard F. Feiner, Manuel Nickel, Martin Menten +6
Uncertainty Quantification (UQ) plays a vital role in enhancing the reliability of deep learning model predictions, especially in scenarios with high-dimensional output spaces. Thi…
Depth-adaptive Inference of Looped Language Models via Continuous Depth Batching
Kristian Schwethelm, Daniel Rueckert, Georgios Kaissis
A main promise of looped language models is depth-adaptive inference. By looping a block of shared layers a variable number of times, the model can use less compute for "easy" toke…
How Much Is One Recurrence Worth? Iso-Depth Scaling Laws for Looped Language Models
Kristian Schwethelm, Daniel Rueckert, Georgios Kaissis
We measure how much one recurrence is worth to a looped (depth-recurrent) transformer, in equivalent unique parameters. From an iso-depth pretraining sweep across recurrence counts…
Survival In-Context: Amortized Bayesian Survival Analysis via Prior-Fitted Networks
Dmitrii Seletkov, Paul Hager, Georgios Kaissis +3
Survival analysis is crucial for many medical applications, but remains challenging for modern machine learning due to limited data, censoring, and the heterogeneity of tabular cov…
Unintended Memorization of Sensitive Information in Fine-Tuned Language Models
Marton Szep, Jorge Marin Ruiz, Georgios Kaissis +4
Fine-tuning Large Language Models (LLMs) on sensitive datasets carries a substantial risk of unintended memorization and leakage of Personally Identifiable Information (PII), which…
Gradient-Weight Alignment as a Train-Time Proxy for Generalization in Classification Tasks
Florian A. Hölzl, Daniel Rueckert, Georgios Kaissis
Robust validation metrics remain essential in contemporary deep learning, not only to detect overfitting and poor generalization, but also to monitor training dynamics. In the supe…
Efficient numeracy in language models through single-token number embeddings
Linus Kreitner, Paul Hager, Jonathan Mengedoht +3
To drive progress in science and engineering, large language models (LLMs) must be able to process large amounts of numerical data and solve long calculations efficiently. This is…
Addressing Benchmarking Gaps in Large Language Models for Health and Medicine with Dynamic Red-Teaming
Jiazhen Pan, Bailiang Jian, Paul Hager +19
Large language models (LLMs) are increasingly used to answer health-related questions and support healthcare workflows, yet evidence for their safety still relies heavily on static…
On Arbitrary Predictions from Equally Valid Models
Sarah Lockfisch, Kristian Schwethelm, Martin Menten +4
Model multiplicity refers to the existence of multiple machine learning models that describe the data equally well but may produce different predictions on individual samples. In m…
Laplace Sample Information: Data Informativeness Through a Bayesian Lens
Johannes Kaiser, Kristian Schwethelm, Daniel Rueckert +1
Accurately estimating the informativeness of individual samples in a dataset is an important objective in deep learning, as it can guide sample selection, which can improve model e…
Improved Localized Machine Unlearning Through the Lens of Memorization
Reihaneh Torkzadehmahani, Reza Nasirigerdeh, Georgios Kaissis +3
Machine unlearning refers to removing the influence of a specified subset of training data from a machine learning model, efficiently, after it has already been trained. This is im…
Differentially Private Active Learning: Balancing Effective Data Selection and Privacy
Kristian Schwethelm, Johannes Kaiser, Jonas Kuntzer +3
Active learning (AL) is a widely used technique for optimizing data labeling in machine learning by iteratively selecting, labeling, and training on the most informative data. Howe…
Machine Unlearning for Medical Imaging
Reza Nasirigerdeh, Nader Razmi, Julia A. Schnabel +2
Machine unlearning is the process of removing the impact of a particular set of training samples from a pretrained model. It aims to fulfill the "right to be forgotten", which gran…
SoK: Memorisation in machine learning
Dmitrii Usynin, Moritz Knolle, Georgios Kaissis
Quantifying the impact of individual data samples on machine learning models is an open research problem. This is particularly relevant when complex and high-dimensional relationsh…
Incentivising the federation: gradient-based metrics for data selection and valuation in private decentralised training
Dmitrii Usynin, Daniel Rueckert, Georgios Kaissis
Obtaining high-quality data for collaborative training of machine learning models can be a challenging task due to A) regulatory concerns and B) a lack of data owner incentives to…