RSGNN: A Model-agnostic Approach for Enhancing the Robustness of Signed Graph Neural Networks

Zhang, Zeyu; Liu, Jiamou; Zheng, Xianda; Wang, Yifei; Han, Pengqian; Wang, Yupan; Zhao, Kaiqi; Zhang, Zijian

doi:10.1145/3543507.3583221

Cited by 5 publications

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Signed Graph Representation Learning Methods: Predicting student performance involves the unique task of sign prediction in a signed bipartite graph, where positive edges signify correct answers and negative edges denote incorrect ones (Derr, Ma, and Tang 2018;Zhang et al 2023b). Traditional methods like SIDE (Kim et al 2018) and SGDN (Jung, Yoo, and Kang 2020) leveraged random walks, while neural-based approaches like SGCN (Derr, Ma, and Tang 2018) extended Graph Convolutional Networks (GCN) (Kipf and Welling 2016) to balance theory-guided sign prediction.…”

Section: Related Workmentioning

confidence: 99%

Enhancing Student Performance Prediction on Learnersourced Questions with SGNN-LLM Synergy

Ni,

Wang,

Zhang

et al. 2024

AAAI

View full text Add to dashboard Cite

Learnersourcing offers great potential for scalable education through student content creation. However, predicting student performance on learnersourced questions, which is essential for personalizing the learning experience, is challenging due to the inherent noise in student-generated data. Moreover, while conventional graph-based methods can capture the complex network of student and question interactions, they often fall short under cold start conditions where limited student engagement with questions yields sparse data. To address both challenges, we introduce an innovative strategy that synergizes the potential of integrating Signed Graph Neural Networks (SGNNs) and Large Language Model (LLM) embeddings. Our methodology employs a signed bipartite graph to comprehensively model student answers, complemented by a contrastive learning framework that enhances noise resilience. Furthermore, LLM's contribution lies in generating foundational question embeddings, proving especially advantageous in addressing cold start scenarios characterized by limited graph data. Validation across five real-world datasets sourced from the PeerWise platform underscores our approach's effectiveness. Our method outperforms baselines, showcasing enhanced predictive accuracy and robustness.

show abstract