FastSHAP: Real-Time Shapley Value Estimation

Jethani, Neil; Sudarshan, Mukund; Covert, Ian; Lee, Su-In; Ranganath, Rajesh

doi:10.48550/arxiv.2107.07436

Cited by 7 publications

(6 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SHAP (SHapley Additive exPlanations) values were calculated using the fastshap ver.0.1.0 [73] R package, based on the nestedcv results. This was achieved through the fastshap::explain function, with the nsim = 10 parameter, evaluated independently for the 100 nestcv.train iterations.…”

Section: Classification Of Datamentioning

confidence: 99%

Multiomics-Based Feature Extraction and Selection for the Prediction of Lung Cancer Survival

Jaksik,

Szumała,

Dinh

et al. 2024

IJMS

View full text Add to dashboard Cite

Lung cancer is a global health challenge, hindered by delayed diagnosis and the disease’s complex molecular landscape. Accurate patient survival prediction is critical, motivating the exploration of various -omics datasets using machine learning methods. Leveraging multi-omics data, this study seeks to enhance the accuracy of survival prediction by proposing new feature extraction techniques combined with unbiased feature selection. Two lung adenocarcinoma multi-omics datasets, originating from the TCGA and CPTAC-3 projects, were employed for this purpose, emphasizing gene expression, methylation, and mutations as the most relevant data sources that provide features for the survival prediction models. Additionally, gene set aggregation was shown to be the most effective feature extraction method for mutation and copy number variation data. Using the TCGA dataset, we identified 32 molecular features that allowed the construction of a 2-year survival prediction model with an AUC of 0.839. The selected features were additionally tested on an independent CPTAC-3 dataset, achieving an AUC of 0.815 in nested cross-validation, which confirmed the robustness of the identified features.

show abstract

Section: Classification Of Datamentioning

confidence: 99%

Multiomics-Based Feature Extraction and Selection for the Prediction of Lung Cancer Survival

Jaksik,

Szumała,

Dinh

et al. 2024

IJMS

View full text Add to dashboard Cite

show abstract

“…A broader range of neighbourhood contexts will be explored to refine the effectiveness of XAI for an explanandum. We will also explore optimisation techniques that can be used with XAI frameworks for generating explanations faster [42].…”

Section: Limitations and Future Workmentioning

confidence: 99%

Optimal Neighborhood Contexts in Explainable AI: An Explanandum-Based Evaluation

Pawar,

O'Shea,

O'Reilly

et al. 2024

IEEE Open J. Comput. Soc.

View full text Add to dashboard Cite

Over the years, several frameworks have been proposed in the domain of Explainable AI (XAI), however their practical applicability and utility need to be clarified. The neighbourhood contexts are shown to significantly impact the explanations generated by XAI frameworks, thus directly affecting their utility in addressing specific questions, or "explananda". This work introduces a methodology that use a comprehensive range of neighbourhood contexts to evaluate and enhance the utility of specific XAI techniques, particularly Feature Importance and CounterFactuals. In this evaluation, two explananda are targeted. The first one examines whether features' collection should be halted as per the AI model based on the sufficiency of the current set of information. Here, the information refers to the features present in the data used to train the AI-based system. The second one explores what is the most effective information (features) that should be collected next to ensure that the AI outputs the same classification as it would have generated with all the information present. These questions serve as a platform to demonstrate our methodology's ability to assess the impact of customised neighbourhood contexts on the utility of XAI.

show abstract

“…Various modifications of SHAP have been developed to explain different machine learning models and tools [46,47,48,49,50,51,52]. Applications of SHAP can be found in [53,54,55], Approaches to reduce the computational complexity of SHAP were also proposed in [56,57,58,59,60]. Many interpretation methods and their comparison were considered and studied in survey papers [61,62,63,64,65,66,67,68] in detail.…”

Section: Related Workmentioning

confidence: 99%

Interpretable Ensembles of Hyper-Rectangles as Base Models

Konstantinov¹,

Utkin²

2023

Preprint

View full text Add to dashboard Cite

A new extremely simple ensemble-based model with the uniformly generated axis-parallel hyper-rectangles as base models (HRBM) is proposed. Two types of HRBMs are studied: closed rectangles and corners. The main idea behind HRBM is to consider and count training examples inside and outside each rectangle. It is proposed to incorporate HRBMs into the gradient boosting machine (GBM). Despite simplicity of HRBMs, it turns out that these simple base models allow us to construct effective ensemble-based models and avoid overfitting. A simple method for calculating optimal regularization parameters of the ensemble-based model, which can be modified in the explicit way at each iteration of GBM, is considered. Moreover, a new regularization called the "step height penalty" is studied in addition to the standard L1 and L2 regularizations. An extremely simple approach to the proposed ensemble-based model prediction interpretation by using the well-known method SHAP is proposed. It is shown that GBM with HRBM can be regarded as a model extending a set of interpretable models for explaining black-box models. Numerical experiments with real datasets illustrate the proposed GBM with HRBMs for regression and classification problems. Experiments also illustrate computational efficiency of the proposed SHAP modifications. The code of proposed algorithms implementing GBM with HRBM is publicly available.

show abstract

FastSHAP: Real-Time Shapley Value Estimation

Cited by 7 publications

References 25 publications

Multiomics-Based Feature Extraction and Selection for the Prediction of Lung Cancer Survival

Multiomics-Based Feature Extraction and Selection for the Prediction of Lung Cancer Survival

Optimal Neighborhood Contexts in Explainable AI: An Explanandum-Based Evaluation

Interpretable Ensembles of Hyper-Rectangles as Base Models

Contact Info

Product

Resources

About