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

Published in PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE by Association for the Advancement of Artificial Intelligence (AAAI).

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)
Read Archived PDF
Preserved and Accessible
Type  article-journal
Stage   published
Date   2022-06-28
Proceedings Metadata
Not in DOAJ
Not in Keepers Registry
ISSN-L:  2159-5399
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: d51a4316-07d8-43a4-bbd7-a5f99d436e5a
API URL: JSON