We propose ClaVis, a visual analytics system for comparative analysis of classification models. ClaVis allows users to visually compare the performance and behavior of tens to hundreds of classifiers trained with different hyperparameter configurations. Our approach is plugin-based and classifier-agnostic and allows users to add their own datasets and classifier implementations. It provides multiple visualizations, including a multivariate ranking, a similarity map, a scatterplot that reveals correlations between parameters and scores, and a training history chart. We demonstrate the effectivity of our approach in multiple case studies for training classification models in the domain of natural language processing.
%0 Conference Paper
%1 10.1145/3399715.3399814
%A Heyen, Frank
%A Munz, Tanja
%A Neumann, Michael
%A Ortega, Daniel
%A Vu, Ngoc Thang
%A Weiskopf, Daniel
%A Sedlmair, Michael
%B Proceedings of the International Conference on Advanced Visual Interfaces (AVI)
%D 2020
%I ACM
%K 2020 A08 EXC2075 from:frankheyen from:leonkokkoliadis peerReviewed sfbtrr161 simtech vis(us) visus visus:heyenfk visus:munzta visus:sedlmaml visus:weiskopf
%P 9:1-9:9
%R 10.1145/3399715.3399814
%T ClaVis: An Interactive Visual Comparison System for Classifiers
%U https://doi.org/10.1145/3399715.3399814
%X We propose ClaVis, a visual analytics system for comparative analysis of classification models. ClaVis allows users to visually compare the performance and behavior of tens to hundreds of classifiers trained with different hyperparameter configurations. Our approach is plugin-based and classifier-agnostic and allows users to add their own datasets and classifier implementations. It provides multiple visualizations, including a multivariate ranking, a similarity map, a scatterplot that reveals correlations between parameters and scores, and a training history chart. We demonstrate the effectivity of our approach in multiple case studies for training classification models in the domain of natural language processing.
%@ 9781450375351
@inproceedings{10.1145/3399715.3399814,
abstract = {We propose ClaVis, a visual analytics system for comparative analysis of classification models. ClaVis allows users to visually compare the performance and behavior of tens to hundreds of classifiers trained with different hyperparameter configurations. Our approach is plugin-based and classifier-agnostic and allows users to add their own datasets and classifier implementations. It provides multiple visualizations, including a multivariate ranking, a similarity map, a scatterplot that reveals correlations between parameters and scores, and a training history chart. We demonstrate the effectivity of our approach in multiple case studies for training classification models in the domain of natural language processing.},
added-at = {2020-10-21T11:47:34.000+0200},
author = {Heyen, Frank and Munz, Tanja and Neumann, Michael and Ortega, Daniel and Vu, Ngoc Thang and Weiskopf, Daniel and Sedlmair, Michael},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2746c5421c7fdafa382be4df6a1b44150/visus},
booktitle = {Proceedings of the International Conference on Advanced Visual Interfaces (AVI)},
doi = {10.1145/3399715.3399814},
interhash = {5bcaeedc1ee8e009a637fa403fc78357},
intrahash = {746c5421c7fdafa382be4df6a1b44150},
isbn = {9781450375351},
keywords = {2020 A08 EXC2075 from:frankheyen from:leonkokkoliadis peerReviewed sfbtrr161 simtech vis(us) visus visus:heyenfk visus:munzta visus:sedlmaml visus:weiskopf},
pages = {9:1-9:9},
publisher = {ACM},
series = {AVI '20},
timestamp = {2020-10-21T10:16:09.000+0200},
title = {ClaVis: An Interactive Visual Comparison System for Classifiers},
url = {https://doi.org/10.1145/3399715.3399814},
year = 2020
}