Counterfactual Shapley Additive Explanations

Albini, Emanuele; Long, Jason; Dervovic, Danial; Magazzeni, Daniele

doi:10.1145/3531146.3533168

Cited by 28 publications

(12 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• An Algorithm for Robust Counterfactual Explanations (RobX): We propose RobX that generates robust counterfactuals for tree-based ensembles leveraging our metric of counterfactual stability. Our proposed strategy is a post-processing one, i.e., it can be applied after generating counterfactuals using any of the existing methods for tree-based ensembles (that we also refer to as the base method), e.g., Feature Tweaking (FT) [7], FOCUS [8], Nearest Neighbor (NN) [9], FACE [10], etc. Our strategy iteratively refines the counterfactual generated by the base method and moves it towards the conservative counterfactual, until a "stable" counterfactual is found (i.e., one that passes our counterfactual stability test R Φ (x, M ) ≥ τ ).…”

Section: Methodsmentioning

confidence: 99%

“…• Nearest Neighbor (NN) [9] attempts to find counterfactuals that are essentially the nearest neighbors (L 1 or L 2 cost) to the original data points with respect to the dataset S that lie on the other side of the decision boundary (recall Definition 2).…”

Section: Methodsmentioning

confidence: 99%

“…Closest counterfactuals have often been criticized in existing literature [6,10,18] as being too far from the data manifold, and thus being too unrealistic, and anomalous. This has led to several approaches for generating "data-support" counterfactuals that are lie on the data manifold, e.g., [9,10,18]. Here, we choose one such definition of data-support counterfactual which is essentially the nearest neighbor with respect to the dataset S, that also gets accepted by the model [9].…”

Section: Background On Counterfactualsmentioning

confidence: 99%

“…This has led to several approaches for generating "data-support" counterfactuals that are lie on the data manifold, e.g., [9,10,18]. Here, we choose one such definition of data-support counterfactual which is essentially the nearest neighbor with respect to the dataset S, that also gets accepted by the model [9]. Definition 2 (Closest Data-Support Counterfactual C p,S (x, M )).…”

Section: Background On Counterfactualsmentioning

confidence: 99%

See 3 more Smart Citations

Robust Counterfactual Explanations for Tree-Based Ensembles

Dutta¹,

Long²,

Mishra³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Counterfactual explanations inform ways to achieve a desired outcome from a machine learning model. However, such explanations are not robust to certain real-world changes in the underlying model (e.g., retraining the model, changing hyperparameters, etc.), questioning their reliability in several applications, e.g., credit lending. In this work, we propose a novel strategy -that we call RobX -to generate robust counterfactuals for tree-based ensembles, e.g., XGBoost. Tree-based ensembles pose additional challenges in robust counterfactual generation, e.g., they have a non-smooth and non-differentiable objective function, and they can change a lot in the parameter space under retraining on very similar data. We first introduce a novel metric -that we call Counterfactual Stability -that attempts to quantify how robust a counterfactual is going to be to model changes under retraining, and comes with desirable theoretical properties. Our proposed strategy RobX works with any counterfactual generation method (base method) and searches for robust counterfactuals by iteratively refining the counterfactual generated by the base method using our metric Counterfactual Stability. We compare the performance of RobX with popular counterfactual generation methods (for tree-based ensembles) across benchmark datasets. The results demonstrate that our strategy generates counterfactuals that are significantly more robust (nearly 100% validity after actual model changes) and also realistic (in terms of local outlier factor) over existing state-of-the-art methods.How do we generate counterfactuals for tree-based ensembles that are not only close but also robust to changes in the model?

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Background On Counterfactualsmentioning

confidence: 99%

Section: Background On Counterfactualsmentioning

confidence: 99%

See 2 more Smart Citations

Robust Counterfactual Explanations for Tree-Based Ensembles

Dutta¹,

Long²,

Mishra³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…lending company might need to provide reasons for why certain customer had a mortgage request denied by its AI model (Bracke et al [2019]). This type of metric is very present in the recent literature of individual and counterfactual fairness, which builds and is built upon local XAI methods (Ge et al [2022], Albini et al [2022]).…”

Section: Local Vs Globalmentioning

confidence: 99%

Local and Global Explainability Metrics for Machine Learning Predictions

Muñoz¹,

Costa²,

Modenesi³

et al. 2023

Preprint

View full text Add to dashboard Cite

Rapid advancements in artificial intelligence (AI) technology have brought about a plethora of new challenges in terms of governance and regulation. AI systems are being integrated into various industries and sectors, creating a demand from decision-makers to possess a comprehensive and nuanced understanding of the capabilities and limitations of these systems. One critical aspect of this demand is the ability to explain the results of machine learning models, which is crucial to promoting transparency and trust in AI systems, as well as fundamental in helping machine learning models to be trained ethically. In this paper, we present novel quantitative metrics frameworks for interpreting the predictions of classifier and regressor models. The proposed metrics are model agnostic and are defined in order to be able to quantify: (i) the interpretability factors based on global and local feature importance distributions; (ii) the variability of feature impact on the model output; and (iii) the complexity of feature interactions within model decisions. We employ publicly available datasets to apply our proposed metrics to various machine learning models focused on predicting customers' credit risk (classification task) and real estate price valuation (regression task). The results expose how these metrics can provide a more comprehensive understanding of model predictions and facilitate better communication between decision-makers and stakeholders, thereby increasing the overall transparency and accountability of AI systems.

show abstract

YOLOv7‐XAI: Multi‐Class Skin Lesion Diagnosis Using Explainable AI With Fair Decision Making

Veeramani,

Jayaraman

2024

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Skin cancer, a prevalent and potentially life‐threatening condition, demands accurate and timely detection for effective intervention. It is an uncontrolled growth of abnormal cells in the human body. Studies are underway to determine if a skin lesion is benign (non‐cancerous) or malignant (cancerous), but the biggest challenge for a doctor is determining the type of skin cancer. As a result, determining the type of tumour is crucial for the right course of treatment. In this study, we introduce a groundbreaking approach to multi‐class skin cancer detection by harnessing the power of Explainable Artificial Intelligence (XAI) in conjunction with a customised You Only Look Once (YOLOv7) architecture. Our research focuses on enhancing the YOLOv7 framework to accurately discern 8 different skin cancer classes, including melanoma, basal cell carcinoma, and squamous cell carcinoma. The YOLOv7 model is the robust backbone, enriched with features tailored for precise multi‐class classification. Concurrently, integrating XAI elements, Local Interpretable Modal‐agnostic Explanations (LIME) and Shapley Additive Explanations (SHAP) ensures transparent decision‐making processes, enabling healthcare professionals to interpret and trust the model's predictions. This innovative synergy between YOLOv7 and XAI heralds a new era in interpretability, resulting in high‐performance skin cancer diagnostics. The obtained results are 96.8%, 94.2%, 95.6%, and 95.8%, evaluated with popular quantitative metrics such as accuracy, precision, recall, and F1 score, respectively.

show abstract

Counterfactual Shapley Additive Explanations

Cited by 28 publications

References 28 publications

Robust Counterfactual Explanations for Tree-Based Ensembles

Robust Counterfactual Explanations for Tree-Based Ensembles

Local and Global Explainability Metrics for Machine Learning Predictions

YOLOv7‐XAI: Multi‐Class Skin Lesion Diagnosis Using Explainable AI With Fair Decision Making

Contact Info

Product

Resources

About