paper-with-me

Papers

Interpretation of multi-label classification models using shapley values

2021-04-21 · Shikun Chen

Multi-label classification is a type of classification task, it is used when there are two or more classes, and the data point we want to predict may belong to none of the classes or all of them at the same time. In the real world, many applications are actually multi-label involved, including information retrieval, multimedia content annotation, web mining, and so on. A game theory-based framework known as SHapley Additive exPlanations (SHAP) has been applied to explain various supervised learning models without being aware of the exact model. Herein, this work further extends the explanation of multi-label classification task by using the SHAP methodology. The experiment demonstrates a comprehensive comparision of different algorithms on well known multi-label datasets and shows the usefulness of the interpretation.

📄 PDF Abstract BibTeX arXiv:2104.10505

Code (1)

jialei1107/Final 공식 구현

Tasks

ClassificationGeneral ClassificationInformation RetrievalMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATIONRetrieval

Methods 이 논문이 사용한 방법론

AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…
SHAP 설명 없음

Similar Papers 제목 키워드 기반

A Baseline for Shapley Values in MLPs: from Missingness to Neutrality

2020-06-08 · Cosimo Izzo, Aldo Lipani, Ramin Okhrati, Francesca Medda

Deep neural networks have gained momentum based on their accuracy, but their interpretability is often criticised. As a result, they are labelled as black boxes. In response, several methods have been proposed in the lit…

Binary Classification

Shapley Chains: Extending Shapley Values to Classifier Chains

2023-03-30 · Célia Wafa Ayad, Thomas Bonnier, Benjamin Bosch, Jesse Read

In spite of increased attention on explainable machine learning models, explaining multi-output predictions has not yet been extensively addressed. Methods that use Shapley values to attribute feature contributions to th…

AttributeDecision MakingFeature Importance

CS-Shapley: Class-wise Shapley Values for Data Valuation in Classification

2022-11-13 · Stephanie Schoch, Haifeng Xu, Yangfeng Ji

Data valuation, or the valuation of individual datum contributions, has seen growing interest in machine learning due to its demonstrable efficacy for tasks such as noisy label detection. In particular, due to the desira…

Data Valuation

From Shapley Values to Generalized Additive Models and back

2022-09-08 · Sebastian Bordt, Ulrike Von Luxburg

In explainable machine learning, local post-hoc explanation algorithms and inherently interpretable models are often seen as competing approaches. This work offers a partial reconciliation between the two by establishing…

Additive models

Multivariate outlier explanations using Shapley values and Mahalanobis distances

2022-10-18 · Marcus Mayrhofer, Peter Filzmoser

For the purpose of explaining multivariate outlyingness, it is shown that the squared Mahalanobis distance of an observation can be decomposed into outlyingness contributions originating from single variables. The decomp…

Outlier InterpretationPosition