Related papers: A Causal Framework for Mitigating Data Shifts in H…
Domain generalization (DG) is about learning models that generalize well to new domains that are related to, but different from, the training domain(s). It is a fundamental problem in machine learning and has attracted much attention in…
Clinical machine learning models experience significantly degraded performance in datasets not seen during training, e.g., new hospitals or populations. Recent developments in domain generalization offer a promising solution to this problem…
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…
Machine learning models rely on various assumptions to attain high accuracy. One of the preliminary assumptions of these models is the independent and identical distribution, which suggests that the train and test data are sampled from the…
Medical imaging models frequently fail when deployed across hospitals, scanners, populations, or imaging protocols due to domain shift, limiting their clinical reliability. While transfer learning and domain adaptation address such shifts…
Deep learning models usually suffer from domain shift issues, where models trained on one source domain do not generalize well to other unseen domains. In this work, we investigate the single-source domain generalization problem: training a…
Ensuring robust model performance in diverse real-world scenarios requires addressing generalizability across domains with covariate shifts. However, no formal procedure exists for statistically evaluating generalizability in machine…
The hypothesis that computational models can be reliable enough to be adopted in prognosis and patient care is revolutionizing healthcare. Deep learning, in particular, has been a game changer in building predictive models, thus leading to…
Domain generalization aims to learn knowledge invariant across different distributions while semantically meaningful for downstream tasks from multiple source domains, to improve the model's generalization ability on unseen target domains.…
Causality has been combined with machine learning to produce robust representations for domain generalization. Most existing methods of this type require massive data from multiple domains to identify causal features by cross-domain…
Domain shift, the mismatch between training and testing data characteristics, causes significant degradation in the predictive performance in multi-source imaging scenarios. In medical imaging, the heterogeneity of population, scanners and…
We study how well machine learning models trained on causal features generalize across domains. We consider 16 prediction tasks on tabular datasets covering applications in health, employment, education, social benefits, and politics. Each…
Objective: Causality mining is an active research area, which requires the application of state-of-the-art natural language processing techniques. In the healthcare domain, medical experts create clinical text to overcome the limitation of…
Methods of transfer learning try to combine knowledge from several related tasks (or domains) to improve performance on a test task. Inspired by causal methodology, we relax the usual covariate shift assumption and assume that it holds true…
Single domain generalization aims to learn a model from a single training domain (source domain) and apply it to multiple unseen test domains (target domains). Existing methods focus on expanding the distribution of the training domain to…
In the domain generalization literature, a common objective is to learn representations independent of the domain after conditioning on the class label. We show that this objective is not sufficient: there exist counter-examples where a…
Classical supervised learning produces unreliable models when training and target distributions differ, with most existing solutions requiring samples from the target domain. We propose a proactive approach which learns a relationship in…
We consider robustness to distribution shifts in the context of diagnostic models in healthcare, where the prediction target $Y$, e.g., the presence of a disease, is causally upstream of the observations $X$, e.g., a biomarker. Distribution…
The problem of domain generalization concerns learning predictive models that are robust to distribution shifts when deployed in new, previously unseen environments. Existing methods typically require labeled data from multiple training…
The performance of machine learning models relies heavily on the quality of input data, yet real-world applications often face significant data-related challenges. A common issue arises when curating training data or deploying models: two…