Seminar

TABCF: Counterfactual Explanations for Tabular Data Using a Transformer-Based VAE
TABCF: Counterfactual Explanations for Tabular Data Using a Transformer-Based VAE

Using transformer based variational autoencoder and Gumbrl-Softmax, TABCF produces counterdactuals the are not biased towards changing the continuous features more often than the categorical features.

Nov 6, 2024
Realistic Counterfactual Explanations with Learned Relations
Realistic Counterfactual Explanations with Learned Relations

This paper proposes a DAG-GNN based VAE to reflect the inter-feature relationships in the produced counterfactuals.

Oct 2, 2024
LLM-Guided Counterfactual Data Generation for Fairer AI
LLM-Guided Counterfactual Data Generation for Fairer AI

This paper introduces a technique to produce synthetic counterfactual images to train a model free of bias.

Aug 28, 2024
Counterfactual Explainable Recommendation
Counterfactual Explainable Recommendation

CountER tells us under what conditions a chosen item would not be recommended to a person anymore.

May 28, 2024
Adversarial Counterfactual Visual Explanations
Adversarial Counterfactual Visual Explanations

Adversarial Counterfactual Explanations propose to develop a filter that robustifies a model against adversarial attacks and helps to transform them into counterfactual explanations.

Apr 2, 2024
CounterNet: End-to-End Training of Prediction Aware Counterfactual Explanations
CounterNet: End-to-End Training of Prediction Aware Counterfactual Explanations

CounterNet proposes an end-to-end training of the predictor and explanation generator to solve some key issues associated with post-hoc/model agnostic explainers.

Feb 6, 2024
Generating Interpretable Counterfactual Explanations By Implicit Minimization of Epistemic and Aleatoric Uncertainties
Generating Interpretable Counterfactual Explanations By Implicit Minimization of Epistemic and Aleatoric Uncertainties

This article demonstrate a new approach to implement counterfactual explanations (CE) without necessarily employing any generative model. As generative models come with several drawbacks in CE generation, the approach in this paper is based on Epistemic and Aleatoric Uncertainty reduction.

Nov 15, 2023
Counterfactual Explanations for Multivariate Time Series
Counterfactual Explanations for Multivariate Time Series

This article focuses on defining what counterfactuals mean in the context of timeseries data and proposed an algorithm that generates plausible and minimally distant counterfactual explanations.

Oct 5, 2023
Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations
Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations

An introduction to counterfactual explanations using the novel approach developed by Microsoft Corporation, India.

Aug 31, 2023
Forecasting the future clinical events of a patient through contrastive learning
Forecasting the future clinical events of a patient through contrastive learning

This study implemented SimCLR on EHR data to detect rare dseases. In general, rare diseases are underrepresentative classes in any clinical dataset. Therefore, using SimCLR (contrastive learning) boosts their classification accuracy.

Jul 12, 2023