Nov 7, 2023 · We introduce a model-agnostic data augmentation method that imputes the counterfactual outcomes for a selected subset of individuals.
Nov 3, 2023 · A data augmentation technique to improve accuracy of causal effect estimation. A method is proposed to augment units with their estimated potential outcomes.
Oct 28, 2024 · In this paper, we propose a method in which we use token-based and sentence-based augmentation methods to generate counterfactual sentence pairs ...
People also ask
What is counterfactual data augmentation?
How and why data augmentation is done related to transfer learning?
How to do data augmentation in deep learning?
How data augmentation can help the model generalize better while training?
Nov 7, 2023 · A model-agnostic data augmentation method that imputes the counterfactual outcomes for a selected subset of individuals by utilizing ...
In this paper, we propose a novel LDA-based counterfactual contrastive learning framework and three data augmentation methods, to capture the causal information ...
Oct 31, 2024 · In this paper, we propose a method in which we use token-based and sentence-based augmentation methods to generate counterfactual sentence pairs ...
C3DA (Wang et al., 2022): A cross-channel data augmentation method aiming to generation negative samples for contrastive learning. • Senti-SPM (Hsu et al.
Relation-based Counterfactual Data Augmentation and Contrastive Learning for Robustifying Natural Language Inference Models ... Learning Representations ...
Oct 25, 2024 · Contrastive pretraining is well-known to improve downstream task performance and model generalisation, especially in limited label settings.
Sep 17, 2024 · Counterfactual contrastive learning is a novel approach that leverages causal image synthesis to generate diverse counterfactual examples.