Generalized Inverse Classification
By Michael T. Lash, Qihang Lin, W. Street, Jennifer G. Robinson, Jeffrey W. Ohlmann. 2016
68 citations recorded by the source corpus.
Inverse classification is the process of perturbing an instance in a meaningful way such that it is more likely to conform to a specific class. Historical methods that address such a problem are often framed to leverage only a single classifier, or specific set of classifiers. These works are often accompanied by naive assumptions. In this work we propose generalized inverse classification (GIC), which avoids restricting the classification model that can be used. We incorporate this formulation into a refined framework in which GIC takes place. Under this framework, GIC operates on features that are immediately actionable. Each change incurs an individual cost, either linear or non-linear. Such changes are subjected to occur within a specified level of cumulative change (budget). Furthermore, our framework incorporates the estimation of features that change as a consequence of direct actions taken (indirectly changeable features). To solve such a problem, we propose three real-valued heuristic-based methods and two sensitivity analysis-based comparison methods, each of which is evaluated on two freely available real-world datasets. Our results demonstrate the validity and benefits of our formulation, framework, and methods.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Amir-Hossein Karimi
- Isabel Valera
- Bernhard Schölkopf
- Sahil Verma
- John P. Dickerson
- Keegan E. Hines
- Gilles Barthe
- Martin Pereira-Fariña
In Computer Vision and Pattern Recognition
- Martin Pereira-Fariña
- Isabel Valera
- Gilles Barthe
- Amir-Hossein Karimi
- Ilia Stepin
- Bernhard Schölkopf
- John P. Dickerson
- Sahil Verma
Citations in the corpus
- A survey of algorithmic recourse: definitions, formulations, solutions, and prospects (2020, background): “For instance, cost-minimizing inverse classification problem [4, 101–103, 105, 118], aim to identify the “minimum required change to a case in order to reclassify it as a member of a different preferred class?””
- A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence (2021, methodology): “perturbation as determined by a contrastive explanation [142].”
- Counterfactual Explanations for Machine Learning: A Review (2020, methodology): “• Inverse classification - Inverse classification aims to perturb an input in a meaningful way in order to classify it into its desired class [12, 72].”
- Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review (2020, unknown): “[189] Black-box Agnostic No No Iteratively No No Yes -”