arXiv subjects

Thomas Melistas

Publications and source records attributed to Thomas Melistas.

5 recordsLinked to original sources

arXiv2026

A Causal Framework for Mitigating Data Shifts in Healthcare

Developing predictive models that perform reliably across diverse patient populations and heterogeneous environments is a core aim of medical research. However, generalization is only possible if the learned model is robust to statistical differences between data used for training and data seen at the time and place of deployment. Domain generalization methods provide strategies to address data shifts, but each method comes with its own set of assumptions and trade-offs. To apply these methods in healthcare, we must understand how domain shifts arise, what assumptions we prefer to make, and what our design constraints are. This article proposes a causal framework for the design of predictive models to improve generalization. Causality provides a powerful language to characterize and understand diverse domain shifts, regardless of data modality. This allows us to pinpoint why models fail to generalize, leading to more principled strategies to prepare for and adapt to shifts. We recommend general mitigation strategies, discussing trade-offs and highlighting existing work. Our causality-based perspective offers a critical foundation for developing robust, interpretable, and clinically relevant AI solutions in healthcare, paving the way for reliable real-world deployment.

cs.LG↗

arXiv2025

A Shift in Perspective on Causality in Domain Generalization

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 causality and DG literature, reconciling apparent contradictions and advocating for a more nuanced theory of the role of causality in generalization. We also provide an interactive demo at https://chai-uk.github.io/ukairs25-causal-predictors/.

cs.LG↗

arXiv2025

Causally Steered Diffusion for Automated Video Counterfactual Generation

Adapting text-to-image (T2I) latent diffusion models (LDMs) to video editing has shown strong visual fidelity and controllability, but challenges remain in maintaining causal relationships inherent to the video data generating process. Edits affecting causally dependent attributes often generate unrealistic or misleading outcomes if these relationships are ignored. In this work, we introduce a causally faithful framework for counterfactual video generation, formulated as an Out-of-Distribution (OOD) prediction problem. We embed prior causal knowledge by encoding the relationships specified in a causal graph into text prompts and guide the generation process by optimizing these prompts using a vision-language model (VLM)-based textual loss. This loss encourages the latent space of the LDMs to capture OOD variations in the form of counterfactuals, effectively steering generation toward causally meaningful alternatives. The proposed framework, dubbed CSVC, is agnostic to the underlying video editing system and does not require access to its internal mechanisms or fine-tuning. We evaluate our approach using standard video quality metrics and counterfactual-specific criteria, such as causal effectiveness and minimality. Experimental results show that CSVC generates causally faithful video counterfactuals within the LDM distribution via prompt-based causal steering, achieving state-of-the-art causal effectiveness without compromising temporal consistency or visual quality on real-world facial videos. Due to its compatibility with any black-box video editing system, our framework has significant potential to generate realistic 'what if' hypothetical video scenarios in diverse areas such as digital media and healthcare.

cs.CV↗

arXiv2025

Benchmarking Counterfactual Image Generation

Generative AI has revolutionised visual content editing, empowering users to effortlessly modify images and videos. However, not all edits are equal. To perform realistic edits in domains such as natural image or medical imaging, modifications must respect causal relationships inherent to the data generation process. Such image editing falls into the counterfactual image generation regime. Evaluating counterfactual image generation is substantially complex: not only it lacks observable ground truths, but also requires adherence to causal constraints. Although several counterfactual image generation methods and evaluation metrics exist, a comprehensive comparison within a unified setting is lacking. We present a comparison framework to thoroughly benchmark counterfactual image generation methods. We integrate all models that have been used for the task at hand and expand them to novel datasets and causal graphs, demonstrating the superiority of Hierarchical VAEs across most datasets and metrics. Our framework is implemented in a user-friendly Python package that can be extended to incorporate additional SCMs, causal methods, generative models, and datasets for the community to build on. Code: https://github.com/gulnazaki/counterfactual-benchmark.

cs.CV↗

arXiv2020

The contact Banach-Mazur distance and large scale geometry of overtwisted contact forms

In the symplectic realm, a distance between open starshaped domains in Liouville manifolds was recently defined. This is the symplectic Banach-Mazur distance. It was proposed by Ostrover and Polterovich and developed by Ostrover, Polterovich, Usher, Gutt, Zhang and Stojisavljević. The natural question is, can an analogous distance in the contact realm be defined? One idea is to define the distance on contact hypersurfaces of Liouville manifolds and another one on contact forms supporting isomorphic contact structures. Rosen and Zhang recently defined such a distance working with manifolds that are prequantizations of Liouville manifolds. They also considered a distance on contact forms supporting the same contact structure on a contact manifold $Y$. This allowed them to view the space of contact forms supporting isomorphic contact structures on a manifold $Y$ as a pseudometric space, study its properties, and derive interesting results. In this work, we do something similar, yet the distance we define is less restrictive. Moreover, viewing contact homology algebra as a persistence module, focusing purely on the overtwisted case and exploiting the fact that the contact homology of overtwisted contact structures vanishes, allows us to bi-Lipschitz embed part of the 2-dimensional Euclidean space into the space of overtwisted contact forms supporting a given contact structure on a smooth closed manifold $Y$.

math.SG↗