Model-invariant Weight Distribution Descriptors for Visual Exploration of Neural Networks en Masse
| dc.contributor.author | Eilertsen, Gabriel | en_US |
| dc.contributor.author | Jönsson, Daniel | en_US |
| dc.contributor.author | Unger, Jonas | en_US |
| dc.contributor.author | Ynnerman, Anders | en_US |
| dc.contributor.editor | Tominski, Christian | en_US |
| dc.contributor.editor | Waldner, Manuela | en_US |
| dc.contributor.editor | Wang, Bei | en_US |
| dc.date.accessioned | 2024-05-17T18:48:04Z | |
| dc.date.available | 2024-05-17T18:48:04Z | |
| dc.date.issued | 2024 | |
| dc.description.abstract | We present a neural network representation which can be used for visually analyzing the similarities and differences in a large corpus of trained neural networks. The focus is on architecture-invariant comparisons based on network weights, estimating similarities of the statistical footprints encoded by the training setups and stochastic optimization procedures. To make this possible, we propose a novel visual descriptor of neural network weights. The visual descriptor considers local weight statistics in a model-agnostic manner by encoding the distribution of weights over different model depths. We show how such a representation can extract descriptive information, is robust to different parameterizations of a model, and is applicable to different architecture specifications. The descriptor is used to create a model atlas by projecting a model library to a 2D representation, where clusters can be found based on similar weight properties. A cluster analysis strategy makes it possible to understand the weight properties of clusters and how these connect to the different datasets and hyper-parameters used to train the models. | en_US |
| dc.description.sectionheaders | Applications | |
| dc.description.seriesinformation | EuroVis 2024 - Short Papers | |
| dc.identifier.doi | 10.2312/evs.20241068 | |
| dc.identifier.isbn | 978-3-03868-251-6 | |
| dc.identifier.pages | 5 pages | |
| dc.identifier.uri | https://doi.org/10.2312/evs.20241068 | |
| dc.identifier.uri | https://diglib.eg.org/handle/10.2312/evs20241068 | |
| dc.publisher | The Eurographics Association | en_US |
| dc.rights | Attribution 4.0 International License | |
| dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | |
| dc.title | Model-invariant Weight Distribution Descriptors for Visual Exploration of Neural Networks en Masse | en_US |