2 citations · 5 across the 5 of their papers we have counts for
5 papers
Domain matters: Towards domain-informed evaluation for link prediction
Yilin Bi, Junhao Bian, Shuyan Wan +2
Link prediction, a foundational task in complex network analysis, has extensive applications in critical scenarios such as social recommendation, drug target discovery, and knowled…
DropEdge not Foolproof: Effective Augmentation Method for Signed Graph Neural Networks
Zeyu Zhang, Lu Li, Shuyan Wan +5
The paper discusses signed graphs, which model friendly or antagonistic relationships using edges marked with positive or negative signs, focusing on the task of link sign predicti…
Quantifying discriminability of evaluation metrics in link prediction for real networks
Shuyan Wan, Yilin Bi, Xinshan Jiao +1
Link prediction is one of the most productive branches in network science, aiming to predict links that would have existed but have not yet been observed, or links that will appear…
Comparing discriminating abilities of evaluation metrics in link prediction
Xinshan Jiao, Shuyan Wan, Qian Liu +5
Link prediction aims to predict the potential existence of links between two unconnected nodes within a network based on the known topological characteristics. Evaluation metrics a…
SGA: A Graph Augmentation Method for Signed Graph Neural Networks
Zeyu Zhang, Shuyan Wan, Sijie Wang +5
Signed Graph Neural Networks (SGNNs) are vital for analyzing complex patterns in real-world signed graphs containing positive and negative links. However, three key challenges hind…