![[2602.17036] LiveGraph: Active-Structure Neural Re-ranking for Exercise Recommendation](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.17036] LiveGraph: Active-Structure Neural Re-ranking for Exercise Recommendation
Summary
The paper presents LiveGraph, a novel neural re-ranking framework aimed at improving exercise recommendations by addressing student engagement disparities and enhancing content diversity through a graph-based approach.
Why It Matters
As digital learning environments grow, personalized educational content becomes crucial. LiveGraph's innovative approach tackles the limitations of existing recommendation systems, potentially improving student engagement and learning outcomes. This research is significant for educators and developers of educational technologies seeking to enhance personalized learning experiences.
Key Takeaways
- LiveGraph improves exercise recommendations by addressing engagement disparities.
- Utilizes a graph-based representation to enhance content diversity.
- Demonstrates superior predictive accuracy compared to existing models.
- Integrates dynamic re-ranking mechanisms for personalized learning.
- Experimental evaluations validate the effectiveness of the proposed framework.
Computer Science > Information Retrieval arXiv:2602.17036 (cs) [Submitted on 19 Feb 2026] Title:LiveGraph: Active-Structure Neural Re-ranking for Exercise Recommendation Authors:Rong Fu, Zijian Zhang, Haiyun Wei, Jiekai Wu, Kun Liu, Xianda Li, Haoyu Zhao, Yang Li, Yongtai Liu, Ziming Wang, Rui Lu, Simon Fong View a PDF of the paper titled LiveGraph: Active-Structure Neural Re-ranking for Exercise Recommendation, by Rong Fu and 11 other authors View PDF HTML (experimental) Abstract:The continuous expansion of digital learning environments has catalyzed the demand for intelligent systems capable of providing personalized educational content. While current exercise recommendation frameworks have made significant strides, they frequently encounter obstacles regarding the long-tailed distribution of student engagement and the failure to adapt to idiosyncratic learning trajectories. We present LiveGraph, a novel active-structure neural re-ranking framework designed to overcome these limitations. Our approach utilizes a graph-based representation enhancement strategy to bridge the information gap between active and inactive students while integrating a dynamic re-ranking mechanism to foster content diversity. By prioritizing the structural relationships within learning histories, the proposed model effectively balances recommendation precision with pedagogical variety. Comprehensive experimental evaluations conducted on multiple real-world datasets demonstrate that LiveGraph surp...
