City Research Online

Human-centric Transfer Learning Explanation via Knowledge Graph [Extended Abstract]

Geng, Y., Chen, J., Jimenez-Ruiz, E. ORCID: 0000-0002-9083-4599 and Chen, H. (2019). Human-centric Transfer Learning Explanation via Knowledge Graph [Extended Abstract]. Paper presented at the AAAI-19 Workshop on Network Interpretability for Deep Learning, 27 - 28 January 2019, Honolulu, Hawaii, USA.

Abstract

Transfer learning which aims at utilizing knowledge learned from one problem (source domain) to solve another different but related problem (target domain) has attracted wide research attentions. However, the current transfer learning methods are mostly uninterpretable, especially to people without ML expertise. In this extended abstract, we brief introduce two knowledge graph (KG) based frameworks towards human understandable transfer learning explanation. The first one explains the transferability of features learned by Convolutional Neural Network (CNN) from one domain to another through pre-training and fine-tuning, while the second justifies the model of a target domain predicted by models from multiple source domains in zero-shot learning (ZSL). Both methods utilize KG and its reasoning capability to provide rich and human understandable explanations to the transfer procedure.

Publication Type: Conference or Workshop Item (Paper)
Additional Information: In AAAI-19 Workshop on Network Interpretability for Deep Learning
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Departments: School of Mathematics, Computer Science & Engineering > Computer Science
URI: https://openaccess.city.ac.uk/id/eprint/22934
[img]
Preview
Text - Accepted Version
Download (513kB) | Preview

Export

Downloads

Downloads per month over past year

View more statistics

Actions (login required)

Admin Login Admin Login