MemoryKT: An Integrative Memory-and-Forgetting Method for Knowledge Tracing

2025-08-11

AI Summary

Existing knowledge tracing models predominantly employ a single, non-personalized forgetting mechanism, neglecting the three-stage cognitive process of memory—encoding, storage, and retrieval. To address this limitation, we propose the first memory-augmented framework that jointly integrates these cognitive stages with personalized forgetting modeling. Specifically, we embed a personalized forgetting module into a Temporal Variational Autoencoder (TVAE) to holistically model memory dynamics over time. Our approach enables fine-grained and interpretable knowledge state tracking through three key components: latent feature distribution learning, exercise feedback reconstruction, and dynamic memory strength modulation. Extensive experiments on four public benchmark datasets demonstrate that our method consistently outperforms state-of-the-art baselines across multiple metrics, confirming its effectiveness, robustness, and capacity to capture individual learning differences.

Technology Category

• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Machine Learning: Deep Generative Models & Autoencoders
• Knowledge Representation and Reasoning: Knowledge Acquisition

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Knowledge Tracing (KT) is committed to capturing students' knowledge mastery from their historical interactions. Simulating students' memory states is a promising approach to enhance both the performance and interpretability of knowledge tracing models. Memory consists of three fundamental processes: encoding, storage, and retrieval. Although forgetting primarily manifests during the storage stage, most existing studies rely on a single, undifferentiated forgetting mechanism, overlooking other memory processes as well as personalized forgetting patterns. To address this, this paper proposes memoryKT, a knowledge tracing model based on a novel temporal variational autoencoder. The model simulates memory dynamics through a three-stage process: (i) Learning the distribution of students' knowledge memory features, (ii) Reconstructing their exercise feedback, while (iii) Embedding a personalized forgetting module within the temporal workflow to dynamically modulate memory storage strength. This jointly models the complete encoding-storage-retrieval cycle, significantly enhancing the model's perception capability for individual differences. Extensive experiments on four public datasets demonstrate that our proposed approach significantly outperforms state-of-the-art baselines.

Problem

• Modeling personalized forgetting patterns in knowledge tracing
• Integrating memory encoding, storage, retrieval processes
• Enhancing interpretability and performance of KT models

Innovation

• Temporal variational autoencoder for knowledge tracing
• Three-stage memory dynamics simulation
• Personalized forgetting module integration