# HiTSKT: A Hierarchical Transformer Model for Session-Aware Knowledge Tracing

arXiv: https://arxiv.org/abs/2212.12139 · HTML: https://mlsanity.com/paper/2212.12139/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 54 references that are in the map.
- First posted on arXiv 23 Dec 2022.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Knowledge Tracing](https://mlsanity.com/paper/1506.05908/) (2015)
- [Context-Aware Attentive Knowledge Tracing](https://mlsanity.com/paper/2007.12324/) (2020)
- [A Self-Attentive model for Knowledge Tracing](https://mlsanity.com/paper/1907.06837/) (2019)
- [Dynamic Key-Value Memory Networks for Knowledge Tracing](https://mlsanity.com/paper/1611.08108/) (2016)
- [HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization](https://mlsanity.com/paper/1905.06566/) (2019)
- [EKT: Exercise-aware Knowledge Tracing for Student Performance Prediction](https://mlsanity.com/paper/1906.05658/) (2019)
- [EdNet: A Large-Scale Hierarchical Dataset in Education](https://mlsanity.com/paper/1912.03072/) (2019)
- [RKT : Relation-Aware Self-Attention for Knowledge Tracing](https://mlsanity.com/paper/2008.12736/) (2020)
- [Knowledge Tracing with Sequential Key-Value Memory Networks](https://mlsanity.com/paper/1910.13197/) (2019)
- [Enhancing Knowledge Tracing via Adversarial Training](https://mlsanity.com/paper/2108.04430/) (2021)
- [Deep Graph Memory Networks for Forgetting-Robust Knowledge Tracing](https://mlsanity.com/paper/2108.08105/) (2021)

## Built on by (most cited first, 8 of 8)

- [Automated Knowledge Concept Annotation and Question Representation Learning for Knowledge Tracing](https://mlsanity.com/paper/2410.01727/) (2024)
- [Personalized Exercise Recommendation with Semantically-Grounded Knowledge Tracing](https://mlsanity.com/paper/2507.11060/) (2025)
- [Improving Low-Resource Knowledge Tracing Tasks by Supervised Pre-training and Importance Mechanism Fine-tuning](https://mlsanity.com/paper/2403.06725/) (2024)
- [Quiz-based Knowledge Tracing](https://mlsanity.com/paper/2304.02413/) (2023)
- [Personalized Forgetting Mechanism with Concept-Driven Knowledge Tracing](https://mlsanity.com/paper/2404.12127/) (2024)
- [Graph Enhanced Reinforcement Learning for Effective Group Formation in Collaborative Problem Solving](https://mlsanity.com/paper/2403.10006/) (2024)
- [MOSAIC: Orchestrating Collaborative Knowledge Tracing with Hierarchical Semantic Alignment](https://mlsanity.com/paper/2606.29049/) (2026)
- [SenseWeather: Multimodal Sensing for Robust Robotic Perception under Extreme Conditions](https://mlsanity.com/paper/2610.14082/) (2026)

## Abstract (arXiv)

Knowledge tracing (KT) aims to leverage students' learning histories to estimate their mastery levels on a set of pre-defined skills, based on which the corresponding future performance can be accurately predicted. As an important way of providing personalized experience for online education, KT has gained increased attention in recent years. In practice, a student's learning history comprises answers to sets of massed questions, each known as a session, rather than merely being a sequence of independent answers. Theoretically, within and across these sessions, students' learning dynamics can be very different. Therefore, how to effectively model the dynamics of students' knowledge states within and across the sessions is crucial for handling the KT problem. Most existing KT models treat student's learning records as a single continuing sequence, without capturing the sessional shift of students' knowledge state. To address the above issue, we propose a novel hierarchical transformer model, named HiTSKT, comprises an interaction(-level) encoder to capture the knowledge a student acquires within a session, and a session(-level) encoder to summarise acquired knowledge across the past sessions. To predict an interaction in the current session, a knowledge retriever integrates the summarised past-session knowledge with the previous interactions' information into proper knowledge representations. These representations are then used to compute the student's current knowledge state. Additionally, to model the student's long-term forgetting behaviour across the sessions, a power-law-decay attention mechanism is designed and deployed in the session encoder, allowing it to emphasize more on the recent sessions. Extensive experiments on three public datasets demonstrate that HiTSKT achieves new state-of-the-art performance on all the datasets compared with six state-of-the-art KT models.