Search Results for author:
Found 20 papers, 12 papers with code
Bias Discovery within Human Raters: A Case Study of the Jigsaw Dataset
Understanding and quantifying the bias introduced by human annotation of data is a crucial problem for trustworthy supervised learning.
Causal Perception
In this work, we formalize perception under causal reasoning to capture the act of interpretation by an individual.
Deep Neural Network Benchmarks for Selective Classification
The selective classification framework aims to design a mechanism that balances the fraction of rejected predictions (i. e., the proportion of examples for which the model does not make a prediction) versus the improvement in predictive performance on the selected predictions.
Correlation and Unintended Biases on Univariate and Multivariate Decision Trees
Decision Trees are accessible, interpretable, and well-performing classification models.
Causal Fairness-Guided Dataset Reweighting using Neural Networks
The two neural networks can approximate the causal model of the data, and the causal model of interventions.
Declarative Reasoning on Explanations Using Constraint Logic Programming
Explaining opaque Machine Learning (ML) models is an increasingly relevant problem.
Ensemble of Counterfactual Explainers
In eXplainable Artificial Intelligence (XAI), several counterfactual explainers have been proposed, each focusing on some desirable properties of counterfactual instances: minimality, actionability, stability, diversity, plausibility, discriminative power.
The Initial Screening Order Problem
To study the impact of ISO, we introduce a human-like screener and compare to its algorithmic counterpart.
Reason to explain: Interactive contrastive explanations (REASONX)
REASONX provides interactive contrastive explanations that can be augmented by background knowledge, and allows to operate under a setting of under-specified information, leading to increased flexibility in the provided explanations.
Beyond Demographic Parity: Redefining Equal Treatment
Liberalism-oriented political philosophy reasons that all individuals should be treated equally independently of their protected characteristics.
Domain Adaptive Decision Trees: Implications for Accuracy and Fairness
In uses of pre-trained machine learning models, it is a known issue that the target population in which the model is being deployed may not have been reflected in the source population with which the model was trained.
Counterfactual Situation Testing: Uncovering Discrimination under Fairness given the Difference
For any complainant, we find and compare similar protected and non-protected instances in the dataset used by the classifier to construct a control and test group, where a difference between the decision outcomes of the two groups implies potential individual discrimination.
AUC-based Selective Classification
We propose a model-agnostic approach to associate a selection function to a given probabilistic binary classifier.
Fairness Implications of Encoding Protected Categorical Attributes
We investigate the interaction between categorical encodings and target encoding regularization methods that reduce unfairness.
Estimating the Total Volume of Queries to a Search Engine
The observed volumes of sample queries are collected from Google Trends (continuous data) and SearchVolume (binned data).
On The Stability of Interpretable Models
Interpretable classification models are built with the purpose of providing a comprehensible description of the decision logic to an external oversight agent.
Open the Black Box Data-Driven Explanation of Black Box Decision Systems
We introduce the local-to-global framework for black box explanation, a novel approach with promising early results, which paves the road for a wide spectrum of future developments along three dimensions: (i) the language for expressing explanations in terms of highly expressive logic-based rules, with a statistical and causal interpretation; (ii) the inference of local explanations aimed at revealing the logic of the decision adopted for a specific instance by querying and auditing the black box in the vicinity of the target instance; (iii), the bottom-up generalization of the many local explanations into simple global ones, with algorithms that optimize the quality and comprehensibility of explanations.
Local Rule-Based Explanations of Black Box Decision Systems
Then it derives from the logic of the local interpretable predictor a meaningful explanation consisting of: a decision rule, which explains the reasons of the decision; and a set of counterfactual rules, suggesting the changes in the instance's features that lead to a different outcome.
A Survey Of Methods For Explaining Black Box Models
The applications in which black box decision systems can be used are various, and each approach is typically developed to provide a solution for a specific problem and, as a consequence, delineating explicitly or implicitly its own definition of interpretability and explanation.
Enumerating Distinct Decision Trees
The search space for the feature selection problem in decision tree learning is the lattice of subsets of the available features.
