VINE: Visualizing Statistical Interactions in Black Box Models
As machine learning becomes more pervasive, there is an urgent need for interpretable explanations of predictive models. Prior work has developed effective methods for visualizing global model behavior, as well as generating local (instance-specific) explanations. However, relatively little work has addressed regional explanations - how groups of similar instances behave in a complex model, and the related issue of visualizing statistical feature interactions. The lack of utilities available for these analytical needs hinders the development of models that are mission-critical, transparent, and align with social goals. We present VINE (Visual INteraction Effects), a novel algorithm to extract and visualize statistical interaction effects in black box models. We also present a novel evaluation metric for visualizations in the interpretable ML space.
Code (1)
Similar Papers 제목 키워드 기반
Mixed vine copulas as joint models of spike counts and local field potentials
Concurrent measurements of neural activity at multiple scales, sometimes performed with multimodal techniques, become increasingly important for studying brain function. However, statistical methods for their concurrent …
Mutual Information EstimationRavines in quantum cost landscapes: opportunities for improved VQA predictions
The geometric and topological structure of quantum cost landscapes (QCLs) governs the optimization and thus the predictive power of variational quantum algorithms (VQAs). We systematically analyze ravines - low-cost path…
Bivariate vine copula based regression, bivariate level and quantile curves
The statistical analysis of univariate quantiles is a well developed research topic. However, there is a need for research in multivariate quantiles. We construct bivariate (conditional) quantiles using the level curves …
regressionvalidDIVINE: Diverse Influential Training Points for Data Visualization and Model Refinement
As the complexity of machine learning (ML) models increases, resulting in a lack of prediction explainability, several methods have been developed to explain a model's behavior in terms of the training data points that m…
Data VisualizationFairnessPVINet: Point-Voxel Interlaced Network for Point Cloud Compression
In point cloud compression, the quality of a reconstructed point cloud relies on both the global structure and the local context, with existing methods usually processing global and local information sequentially and lac…