Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 2, 2025AutomatikaOpen Access

Multimodal machine learning framework for predicting and enhancing higher education using reinforcement learning and graph neural networks

View Full Paper
Ask AI
Bookmark
Share

Authors

CJChen JieHMHuang MinCBChen Bin

Discussion

Loading...

Member takes

Overview

This study demonstrates improved dropout and engagement predictions in higher education, highlighting reinforcement learning and graph neural networks' impact.

Key Points

  • Engagement prediction improved by 22.1% using graph neural networks, indicating effective student support.
  • Dropout rate reduced by 39.6% using reinforcement learning techniques, impacting student outcomes positively.
  • Proximal Policy Optimization method was employed to define reinforced educational policies for better performance.
  • Findings suggest that adaptive education frameworks can redefine student support strategies in higher education.

Cite This Study

Jie et al. (2025) studied this question.

synapsesocial.com/papers/69254f97c0ce034ddc359d72https://doi.org/10.1080/00051144.2025.2565023
View Full Paper
Ask AI
Bookmark
Share