Skip to main content
DORAS
DCU Online Research Access Service
Login (DCU Staff Only)
Extracting knowledge from deep neural networks through graph analysis

Horta, Vitor A.C., Tiddi, Ilaria ORCID: 0000-0001-7116-9338, Little, Suzanne ORCID: 0000-0003-3281-3471 and Mileo, Alessandra ORCID: 0000-0002-6614-6462 (2021) Extracting knowledge from deep neural networks through graph analysis. Future Generation Computer Systems, 120 . pp. 109-118. ISSN 0167-739X

Full text available as:

[img]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
2MB

Abstract

The popularity of deep learning has increased tremendously in recent years due to its ability to efficiently solve complex tasks in challenging areas such as computer vision and language processing. Despite this success, low-level neural activity reproduced by Deep Neural Networks (DNNs) generates extremely rich representations of the data. These representations are difficult to characterise and cannot be directly used to understand the decision process. In this paper we build upon our exploratory work where we introduced the concept of a co-activation graph and investigated the potential of graph analysis for explaining deep representations. The co-activation graph encodes statistical correlations between neurons’ activation values and therefore helps to characterise the relationship between pairs of neurons in the hidden layers and output classes. To confirm the validity of our findings, our experimental evaluation is extended to consider datasets and models with different levels of complexity. For each of the considered datasets we explore the co-activation graph and use graph analysis to detect similar classes, find central nodes and use graph visualisation to better interpret the outcomes of the analysis. Our results show that graph analysis can reveal important insights into how DNNs work and enable partial explainability of deep learning models.

Item Type:Article (Published)
Refereed:Yes
Uncontrolled Keywords:Explainable AI; Deep representation learning; Graph analysis
Subjects:Computer Science > Artificial intelligence
Computer Science > Machine learning
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Research Initiatives and Centres > INSIGHT Centre for Data Analytics
Publisher:Elsevier
Official URL:https://dx.doi.org/10.1016/j.future.2021.02.009
Copyright Information:© 2021 The Authors. Open Access. (CC-BY-4.0)
ID Code:25855
Deposited On:18 May 2021 13:02 by Vitor Araujo Cautiero horta . Last Modified 13 Oct 2022 12:13

Downloads

Downloads per month over past year

Archive Staff Only: edit this record

  • Student Email
  • Staff Email
  • Student Apps
  • Staff Apps
  • Loop
  • Disclaimer
  • Privacy
  • Contact Us