Human-centric Transfer Learning Explanation via Knowledge Graph [Extended Abstract]
This addresses the need for interpretability in transfer learning, making it accessible to non-experts, though it appears incremental as it builds on existing knowledge graph techniques.
The paper tackles the problem of uninterpretable transfer learning methods by introducing two knowledge graph-based frameworks to provide human-understandable explanations for feature transferability in CNN pre-training/fine-tuning and model justification in zero-shot learning.
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.