DeepVisualInsight: Time-Travelling Visualization for Spatio-Temporal Causality of Deep Classification Training
release_7bhaegzyhrh5fdtvk2kfd3wqvi
by
Xianglin Yang, Yun Lin, Ruofan Liu, Zhenfeng He, Chao Wang, Jin Song Dong, Hong Mei
2022 Volume 36, p5359-5366
Abstract
Understanding how the predictions of deep learning models are formed during the training process is crucial to improve model performance and fix model defects, especially when we need to investigate nontrivial training strategies such as active learning, and track the root cause of unexpected training results such as performance degeneration.
In this work, we propose a time-travelling visual solution DeepVisualInsight (DVI), aiming to manifest the spatio-temporal causality while training a deep learning image classifier. The spatio-temporal causality demonstrates how the gradient-descent algorithm and various training data sampling techniques can influence and reshape the layout of learnt input representation and the classification boundaries in consecutive epochs. Such causality allows us to observe and analyze the whole learning process in the visible low dimensional space. Technically, we propose four spatial and temporal properties and design our visualization solution to satisfy them. These properties preserve the most important information when projecting and inverse-projecting input samples between the visible low-dimensional and the invisible high-dimensional space, for causal analyses. Our extensive experiments show that, comparing to baseline approaches, we achieve the best visualization performance regarding the spatial/temporal properties and visualization efficiency. Moreover, our case study shows that our visual solution can well reflect the characteristics of various training scenarios, showing good potential of DVI as a debugging tool for analyzing deep learning training processes.
In application/xml+jats
format
Archived Files and Locations
application/pdf 2.5 MB
file_o3xuoyziazhavgzr6tofstxvra
|
ojs.aaai.org (publisher) web.archive.org (webarchive) |
article-journal
Stage
published
Date 2022-06-28
access all versions, variants, and formats of this works (eg, pre-prints)
Crossref Metadata (via API)
Worldcat
SHERPA/RoMEO (journal policies)
wikidata.org
CORE.ac.uk
Semantic Scholar
Google Scholar