Explaining dimensionality reduction results using Shapley values

Autor(es)

Marcilio-Jr, Wilson E. ; Eler, Danilo M. ^[1]

Afiliação do(s) autor(es)

^[1] Marcilio-Jr, Jr., Wilson E., Sao Paulo State Univ UNESP, Fac Sci & Technol, BR-19060900 Presidente Prudente, SP - Brazil

• Tipo de documento: Artigo Científico
• Fonte: EXPERT SYSTEMS WITH APPLICATIONS; v. 178, SEP 15 2021.
• Citações Web of Science: 0

Resumo

Dimensionality reduction (DR) techniques have been consistently supporting high-dimensional data analysis in various applications. Besides the patterns uncovered by these techniques, the interpretation of DR results based on each feature's contribution to the low-dimensional representation supports new finds through exploratory analysis. Current literature approaches designed to interpret DR techniques do not explain the features' contributions well since they focus only on the low-dimensional representation or do not consider the relationship among features. This paper presents ClusterShapley to address these problems, using Shapley values to generate explanations of dimensionality reduction techniques and interpret these algorithms using a cluster-oriented analysis. ClusterShapley explains the formation of clusters and the meaning of their relationship, which is useful for exploratory data analysis in various domains. We propose novel visualization techniques to guide the interpretation of features' contributions on clustering formation and validate our methodology through case studies of publicly available datasets. The results demonstrate our approach's interpretability and analysis power to generate insights about pathologies and patients in different conditions using DR results. (AU)

• Processo FAPESP: 18/17881-3 - Representação visual multinível para auxiliar a exploração de conjuntos de dados
• Beneficiário: Danilo Medeiros Eler
• Modalidade de apoio: Auxílio à Pesquisa - Regular
• Processo FAPESP: 18/25755-8 - Representação visual multinível para auxiliar a exploração de conjuntos de dados
• Beneficiário: Wilson Estécio Marcílio Júnior
• Modalidade de apoio: Bolsas no Brasil - Programa Capacitação - Treinamento Técnico