Machine Learning for Causal Inference by 2023

Author:2023
Language: eng
Format: epub
ISBN: 9783031350511
Publisher: Springer International Publishing

Proximity: The counterfactual samples should be as similar as possible to the original instance. Otherwise, the counterfactual explanations may not be convincing enough.

Speed: In order to apply a counterfactual explainable model in real-world applications, the generation process of counterfactual explanations should be fast enough.

Diversity: The counterfactual explanations for different instances should be diverse.

In the following sections, we will provide examples of a few causal explainable models to demonstrate how to generate causal explanations. These examples cover typical AI tasks, including recommender system (RS), natural language processing (NLP), computer vision (CV), graph neural networks (GNN), and fairness.

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.