Concept Prerequisite Relation Prediction by Using Permutation-Equivariant Directed Graph Neural Networks

Xiran Qu, Xuequn Shang, Yupei Zhang
Proceedings of the 2024 AAAI Conference on Artificial Intelligence, PMLR 257:39-47, 2024.

Abstract

This paper studies the problem of CPRP, concept prerequisite relation prediction, which is a fundamental task in using AI for education. CPRP is usually formulated into a link- prediction task on a relationship graph of concepts and solved by training the graph neural network (GNN) model. However, current directed GNNs fail to manage graph isomor- phism which refers to the invariance of non-isomorphic graphs, reducing the expressivity of resulting representations. We present a permutation-equivariant directed GNN model by introducing the Weisfeiler-Lehman test into directed GNN learning. Our method is then used for CPRP and evaluated on three public datasets. The experimental results show that our model delivers better prediction performance than the state-of-the-art methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v257-qu24a, title = {Concept Prerequisite Relation Prediction by Using Permutation-Equivariant Directed Graph Neural Networks}, author = {Qu, Xiran and Shang, Xuequn and Zhang, Yupei}, booktitle = {Proceedings of the 2024 AAAI Conference on Artificial Intelligence}, pages = {39--47}, year = {2024}, editor = {Ananda, Muktha and Malick, Debshila Basu and Burstein, Jill and Liu, Lydia T. and Liu, Zitao and Sharpnack, James and Wang, Zichao and Wang, Serena}, volume = {257}, series = {Proceedings of Machine Learning Research}, month = {26--27 Feb}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v257/main/assets/qu24a/qu24a.pdf}, url = {https://proceedings.mlr.press/v257/qu24a.html}, abstract = {This paper studies the problem of CPRP, concept prerequisite relation prediction, which is a fundamental task in using AI for education. CPRP is usually formulated into a link- prediction task on a relationship graph of concepts and solved by training the graph neural network (GNN) model. However, current directed GNNs fail to manage graph isomor- phism which refers to the invariance of non-isomorphic graphs, reducing the expressivity of resulting representations. We present a permutation-equivariant directed GNN model by introducing the Weisfeiler-Lehman test into directed GNN learning. Our method is then used for CPRP and evaluated on three public datasets. The experimental results show that our model delivers better prediction performance than the state-of-the-art methods. } }
Endnote
%0 Conference Paper %T Concept Prerequisite Relation Prediction by Using Permutation-Equivariant Directed Graph Neural Networks %A Xiran Qu %A Xuequn Shang %A Yupei Zhang %B Proceedings of the 2024 AAAI Conference on Artificial Intelligence %C Proceedings of Machine Learning Research %D 2024 %E Muktha Ananda %E Debshila Basu Malick %E Jill Burstein %E Lydia T. Liu %E Zitao Liu %E James Sharpnack %E Zichao Wang %E Serena Wang %F pmlr-v257-qu24a %I PMLR %P 39--47 %U https://proceedings.mlr.press/v257/qu24a.html %V 257 %X This paper studies the problem of CPRP, concept prerequisite relation prediction, which is a fundamental task in using AI for education. CPRP is usually formulated into a link- prediction task on a relationship graph of concepts and solved by training the graph neural network (GNN) model. However, current directed GNNs fail to manage graph isomor- phism which refers to the invariance of non-isomorphic graphs, reducing the expressivity of resulting representations. We present a permutation-equivariant directed GNN model by introducing the Weisfeiler-Lehman test into directed GNN learning. Our method is then used for CPRP and evaluated on three public datasets. The experimental results show that our model delivers better prediction performance than the state-of-the-art methods.
APA
Qu, X., Shang, X. & Zhang, Y.. (2024). Concept Prerequisite Relation Prediction by Using Permutation-Equivariant Directed Graph Neural Networks. Proceedings of the 2024 AAAI Conference on Artificial Intelligence, in Proceedings of Machine Learning Research 257:39-47 Available from https://proceedings.mlr.press/v257/qu24a.html.

Related Material