Unsupervised Cross-Domain Prerequisite Chain Learning using Variational Graph Autoencoders
This work addresses the challenge of efficiently acquiring knowledge in unfamiliar domains, such as from NLP to CV, by leveraging shared concepts, but it is incremental as it builds on existing graph autoencoder techniques.
The paper tackles the problem of learning prerequisite chains across domains by proposing an unsupervised method using a variational graph autoencoder to transfer concept prerequisite relations from a source to a target domain, achieving substantial improvements over baseline models.
Learning prerequisite chains is an essential task for efficiently acquiring knowledge in both known and unknown domains. For example, one may be an expert in the natural language processing (NLP) domain but want to determine the best order to learn new concepts in an unfamiliar Computer Vision domain (CV). Both domains share some common concepts, such as machine learning basics and deep learning models. In this paper, we propose unsupervised cross-domain concept prerequisite chain learning using an optimized variational graph autoencoder. Our model learns to transfer concept prerequisite relations from an information-rich domain (source domain) to an information-poor domain (target domain), substantially surpassing other baseline models. Also, we expand an existing dataset by introducing two new domains: CV and Bioinformatics (BIO). The annotated data and resources, as well as the code, will be made publicly available.