Adaptive Learning using Graph Neural Network and Knowledge Graph

MPhil Thesis Defence


Title: "Adaptive Learning using Graph Neural Network and Knowledge Graph"

By

Mr. Shing Chun YIP


Abstract

Adaptive learning is designed to serve as a personalization tool for 
providing recommendations such as study pathways, next-question 
suggestions for students with the study of knowledge tracing. Deep 
Knowledge Tracing (DKT) is the first deep learning model that traces the 
knowledge of students, with long short-term memory (LSTM). In this thesis, 
the DKT model is extended by exploiting the Graph Neural Network (GNN) and 
the knowledge graph to tackle the limitation of Recurrent Neural Network 
in handling long-term dependency. We demonstrate how the graph model can 
be used to improve the DKT model with the help of the knowledge graph 
structure. Our model can be applied to modern e-learning systems for 
adaptive learning which predicts the future performance of students and 
recommends encouraging questions.


Date:  			Wednesday, 30 December 2020

Time:			2:30pm - 4:30pm

Zoom meeting: 
https://hkust.zoom.us/j/94658203483?pwd=UGlKS0NoK0lDZW04eUlCeVliU3JPdz09

Committee Members:	Prof. Raymond Wong (Supervisor)
 			Prof. Dit-Yan Yeung (Chairperson)
 			Prof. Dik-Lun Lee


**** ALL are Welcome ****