ML researchers assess spurious correlations via four pragmatic frames (relevance, generalizability, human-likeness, harmfulness) rather than a fixed statistical definition.
On Causal and Anticausal Learning
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
We consider the problem of function estimation in the case where an underlying causal model can be inferred. This has implications for popular scenarios such as covariate shift, concept drift, transfer learning and semi-supervised learning. We argue that causal knowledge may facilitate some approaches for a given problem, and rule out others. In particular, we formulate a hypothesis for when semi-supervised learning can help, and corroborate it with empirical results.
representative citing papers
A self-supervised approach uses consistent spatial relationships of anatomical structures across patients to improve 3D multi-modal medical image representations, yielding modest gains on segmentation and classification tasks.
CausalDisenSeg uses causality-guided disentanglement via CVAE with HSIC, a Region Causality Module, and counterfactual reasoning to achieve robust brain tumor segmentation under missing MRI modalities, reporting 84.49 macro-average DSC on BraTS 2023.
citing papers explorer
-
The Pragmatic Frames of Spurious Correlations in Machine Learning: Interpreting How and Why They Matter
ML researchers assess spurious correlations via four pragmatic frames (relevance, generalizability, human-likeness, harmfulness) rather than a fixed statistical definition.
-
Beyond Instance-Level Self-Supervision in 3D Multi-Modal Medical Imaging
A self-supervised approach uses consistent spatial relationships of anatomical structures across patients to improve 3D multi-modal medical image representations, yielding modest gains on segmentation and classification tasks.
-
CausalDisenSeg: A Causality-Guided Disentanglement Framework with Counterfactual Reasoning for Robust Brain Tumor Segmentation Under Missing Modalities
CausalDisenSeg uses causality-guided disentanglement via CVAE with HSIC, a Region Causality Module, and counterfactual reasoning to achieve robust brain tumor segmentation under missing MRI modalities, reporting 84.49 macro-average DSC on BraTS 2023.
- Optimal Causal Annotations: An Application to Casenotes in Social Services