Explaining Text Classifiers with Counterfactual Representations

2024-02-01 · Pirmin Lemberger, Antoine Saillenfest

One well motivated explanation method for classifiers leverages counterfactuals which are hypothetical events identical to real observations in all aspects except for one feature. Constructing such counterfactual poses specific challenges for texts, however, as some attribute values may not necessarily align with plausible real-world events. In this paper we propose a simple method for generating counterfactuals by intervening in the space of text representations which bypasses this limitation. We argue that our interventions are minimally disruptive and that they are theoretically sound as they align with counterfactuals as defined in Pearl's causal inference framework. To validate our method, we conducted experiments first on a synthetic dataset and then on a realistic dataset of counterfactuals. This allows for a direct comparison between classifier predictions based on ground truth counterfactuals - obtained through explicit text interventions - and our counterfactuals, derived through interventions in the representation space. Eventually, we study a real world scenario where our counterfactuals can be leveraged both for explaining a classifier and for bias mitigation.

📄 PDF Abstract BibTeX arXiv:2402.00711

Code (1)

toinesayan/counterfactual-representations-for-explanation 공식 구현 pytorch

Tasks

AttributeCausal Inferencecounterfactual

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Counterfactuals 설명 없음

Causal inference Causal inference is the process of drawing a conclusion about a causal connection based on the conditions of the occurrence of an effect. The main difference between causal…

Explaining Reject Options of Learning Vector Quantization Classifiers

2022-02-15 · André Artelt, Johannes Brinkrolf, Roel Visser, Barbara Hammer

While machine learning models are usually assumed to always output a prediction, there also exist extensions in the form of reject options which allow the model to reject inputs where only a prediction with an unacceptab…

counterfactual Quantization

Explaining 3D Computed Tomography Classifiers with Counterfactuals

2025-02-11 · Joseph Paul Cohen, Louis Blankemeier, Akshay Chaudhari

Counterfactual explanations in medical imaging are critical for understanding the predictions made by deep learning models. We extend the Latent Shift counterfactual generation method from 2D applications to 3D computed …

Computed Tomography (CT)counterfactual

Explaining Image Classifiers Using Contrastive Counterfactuals in Generative Latent Spaces

2022-06-10 · Kamran Alipour, Aditya Lahiri, Ehsan Adeli, Babak Salimi 외

Despite their high accuracies, modern complex image classifiers cannot be trusted for sensitive tasks due to their unknown decision-making process and potential biases. Counterfactual explanations are very effective in p…

Attribute counterfactual Decision Making

GANterfactual - Counterfactual Explanations for Medical Non-Experts using Generative Adversarial Learning

2020-12-22 · Silvan Mertes, Tobias Huber, Katharina Weitz, Alexander Heimerl 외

With the ongoing rise of machine learning, the need for methods for explaining decisions made by artificial intelligence systems is becoming a more and more important topic. Especially for image classification tasks, man…

counterfactual Counterfactual Explanation Counterfactual Reasoning Feature Importance+3

Instance-based Counterfactual Explanations for Time Series Classification

2020-09-28 · Eoin Delaney, Derek Greene, Mark T. Keane

In recent years, there has been a rapidly expanding focus on explaining the predictions made by black-box AI systems that handle image and tabular data. However, considerably less attention has been paid to explaining th…

Classification counterfactual Counterfactual Explanation Dynamic Time Warping+4