469 citations · 1.6k across the 93 of their papers we have counts for
20 papers · 1 filter
Explainable AI for Data-Driven Design of High-Dimensional Predictive Studies
Junyu Yan, Damian Machlanski, Kurt Butler +4
Predictive modelling is important for health data analysis and data-driven clinical decision-making. However, predictive studies are challenging to design optimally by hand when te…
A Causal Framework for Mitigating Data Shifts in Healthcare
Kurt Butler, Stephanie Riley, Damian Machlanski +13
Developing predictive models that perform reliably across diverse patient populations and heterogeneous environments is a core aim of medical research. However, generalization is o…
Causal Ordering for Structure Learning from Time Series
Pedro P. Sanchez, Damian Machlanski, Steven McDonagh +1
Predicting causal structure from time series data is crucial for understanding complex phenomena in physiology, brain connectivity, climate dynamics, and socio-economic behaviour.…
SWiFT: Soft-Mask Weight Fine-tuning for Bias Mitigation
Junyu Yan, Feng Chen, Yuyang Xue +4
Recent studies have shown that Machine Learning (ML) models can exhibit bias in real-world scenarios, posing significant challenges in ethically sensitive domains such as healthcar…
A Shift in Perspective on Causality in Domain Generalization
Damian Machlanski, Stephanie Riley, Edward Moroshko +7
The promise that causal modelling can lead to robust AI generalization has been challenged in recent work on domain generalization (DG) benchmarks. We revisit the claims of the cau…
BMFT: Achieving Fairness via Bias-based Weight Masking Fine-tuning
Yuyang Xue, Junyu Yan, Raman Dutt +4
Developing models with robust group fairness properties is paramount, particularly in ethically sensitive domains such as medical diagnosis. Recent approaches to achieving fairness…
The MRI Scanner as a Diagnostic: Image-less Active Sampling
Yuning Du, Rohan Dharmakumar, Sotirios A. Tsaftaris
Despite the high diagnostic accuracy of Magnetic Resonance Imaging (MRI), using MRI as a Point-of-Care (POC) disease identification tool poses significant accessibility challenges…
A Causal Ordering Prior for Unsupervised Representation Learning
Avinash Kori, Pedro Sanchez, Konstantinos Vilouras +2
Unsupervised representation learning with variational inference relies heavily on independence assumptions over latent variables. Causal representation learning (CRL), however, arg…
Privacy Distillation: Reducing Re-identification Risk of Multimodal Diffusion Models
Virginia Fernandez, Pedro Sanchez, Walter Hugo Lopez Pinaya +3
Knowledge distillation in neural networks refers to compressing a large model or dataset into a smaller version of itself. We introduce Privacy Distillation, a framework that allow…
Diffusion Models for Causal Discovery via Topological Ordering
Pedro Sanchez, Xiao Liu, Alison Q O'Neil +1
Discovering causal relations from observational data becomes possible with additional assumptions such as considering the functional relations to be constrained as nonlinear with a…
Why patient data cannot be easily forgotten?
Ruolin Su, Xiao Liu, Sotirios A. Tsaftaris
Rights provisioned within data protection regulations, permit patients to request that knowledge about their information be eliminated by data holders. With the advent of AI learne…
Causal Machine Learning for Healthcare and Precision Medicine
Pedro Sanchez, Jeremy P. Voisey, Tian Xia +3
Causal machine learning (CML) has experienced increasing popularity in healthcare. Beyond the inherent capabilities of adding domain knowledge into learning systems, CML provides a…
Unintended memorisation of unique features in neural networks
John Hartley, Sotirios A. Tsaftaris
Neural networks pose a privacy risk due to their propensity to memorise and leak training data. We show that unique features occurring only once in training data are memorised by d…
Diffusion Causal Models for Counterfactual Estimation
Pedro Sanchez, Sotirios A. Tsaftaris
We consider the task of counterfactual estimation from observational imaging data given a known causal structure. In particular, quantifying the causal effect of interventions for…
Measuring Unintended Memorisation of Unique Private Features in Neural Networks
John Hartley, Sotirios A. Tsaftaris
Neural networks pose a privacy risk to training data due to their propensity to memorise and leak information. Focusing on image classification, we show that neural networks also u…
FROB: Few-shot ROBust Model for Classification and Out-of-Distribution Detection
Nikolaos Dionelis, Mehrdad Yaghoobi, Sotirios A. Tsaftaris
Nowadays, classification and Out-of-Distribution (OoD) detection in the few-shot setting remain challenging aims due to rarity and the limited samples in the few-shot setting, and…
OMASGAN: Out-of-Distribution Minimum Anomaly Score GAN for Sample Generation on the Boundary
Nikolaos Dionelis, Mehrdad Yaghoobi, Sotirios A. Tsaftaris
Generative models trained in an unsupervised manner may set high likelihood and low reconstruction loss to Out-of-Distribution (OoD) samples. This increases Type II errors and lead…
Tail of Distribution GAN (TailGAN): Generative-Adversarial-Network-Based Boundary Formation
Nikolaos Dionelis, Mehrdad Yaghoobi, Sotirios A. Tsaftaris
Generative Adversarial Networks (GAN) are a powerful methodology and can be used for unsupervised anomaly detection, where current techniques have limitations such as the accurate…
Boundary of Distribution Support Generator (BDSG): Sample Generation on the Boundary
Nikolaos Dionelis, Mehrdad Yaghoobi, Sotirios A. Tsaftaris
Generative models, such as Generative Adversarial Networks (GANs), have been used for unsupervised anomaly detection. While performance keeps improving, several limitations exist p…
Survey: Leakage and Privacy at Inference Time
Marija Jegorova, Chaitanya Kaul, Charlie Mayor +4
Leakage of data from publicly available Machine Learning (ML) models is an area of growing significance as commercial and government applications of ML can draw on multiple sources…