Efficient Variational Graph Autoencoders for Unsupervised Cross-domain Prerequisite Chains

TL;DR

This paper introduces DAVGAE, a novel domain-adversarial variational graph autoencoder that efficiently learns cross-domain prerequisite chains using simple homogeneous graphs, outperforming existing models in accuracy and efficiency.

Contribution

The paper presents DAVGAE, a new model combining VGAE and domain adversarial training for cross-domain prerequisite chain learning with reduced data and computational requirements.

Findings

Outperforms recent graph-based benchmarks

Uses only 1/10 of the graph scale

Requires 1/3 of the computation time

Abstract

Prerequisite chain learning helps people acquire new knowledge efficiently. While people may quickly determine learning paths over concepts in a domain, finding such paths in other domains can be challenging. We introduce Domain-Adversarial Variational Graph Autoencoders (DAVGAE) to solve this cross-domain prerequisite chain learning task efficiently. Our novel model consists of a variational graph autoencoder (VGAE) and a domain discriminator. The VGAE is trained to predict concept relations through link prediction, while the domain discriminator takes both source and target domain data as input and is trained to predict domain labels. Most importantly, this method only needs simple homogeneous graphs as input, compared with the current state-of-the-art model. We evaluate our model on the LectureBankCD dataset, and results show that our model outperforms recent graph-based benchmarks while using only 1/10 of graph scale and 1/3 computation time.