Learning Structure and Knowledge Aware Representation with Large Language Models for Concept Recommendation

TL;DR

A novel Structure and Knowledge Aware Representation learning framework for concept Recommendation (SKarREC) that leverages factual knowledge from LLMs as well as the precedence and succession relationships between concepts obtained from the knowledge graph to construct textual representations of concepts.

Abstract

Concept recommendation aims to suggest the next concept for learners to study based on their knowledge states and the human knowledge system. While knowledge states can be predicted using knowledge tracing models, previous approaches have not effectively integrated the human knowledge system into the process of designing these educational models. In the era of rapidly evolving Large Language Models (LLMs), many fields have begun using LLMs to generate and encode text, introducing external knowledge. However, integrating LLMs into concept recommendation presents two urgent challenges: 1) How to construct text for concepts that effectively incorporate the human knowledge system? 2) How to adapt non-smooth, anisotropic text encodings effectively for concept recommendation? In this paper, we propose a novel Structure and Knowledge Aware Representation learning framework for concept Recommendation (SKarREC). We leverage factual knowledge from LLMs as well as the precedence and succession relationships between concepts obtained from the knowledge graph to construct textual representations of concepts. Furthermore, we propose a graph-based adapter to adapt anisotropic text embeddings to the concept recommendation task. This adapter is pre-trained through contrastive learning on the knowledge graph to get a smooth and structure-aware concept representation. Then, it's fine-tuned through the recommendation task, forming a text-to-knowledge-to-recommendation adaptation pipeline, which effectively constructs a structure and knowledge-aware concept representation. Our method does a better job than previous adapters in transforming text encodings for application in concept recommendation. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed approach.

Figures (8)

• Figure 1: The concept recommendation strategy of combining the learner's knowledge state and the human knowledge system. The knowledge state is estimated by knowledge tracing, and the human knowledge system is modeled by graph-adapted encoding of the enhanced text of each concept.
• Figure 2: The overall framework of SKarRec. The left part shows the construction of concept interpretations integrates structure and knowledge. The right part is the demonstration of knowledge tracing. The bottom center details the graph-based text adaptation process. The top middle outlines the recommendation mechanism using transformed embeddings.
• Figure 3: Performance of comparison with/without sequence modeling tasks.
• Figure 4: Comparing different distributions of embeddings in ASSIST09. The smaller the DBI value upper in figure, the better.
• Figure 5: The matching ratios of the recommendation and graph structure.