4 papers
A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs
Bizu Feng, Zhimu Yang, Shuming Wang +4
We study feature-level and node-level explanations for graph neural networks (GNNs) through the lens of Aumann-Shapley attribution. Path-integral methods such as Integrated Gradien…
Ultra-High-Definition Image Quality Assessment via Graph Representation Learning
Shaode Yu, Enqi Chen, Ming Huang +4
Blind image quality assessment (BIQA) for ultrahighdefinition (UHD) images remains challenging because native-resolution inference is computationally expensive, whereas aggressive…
FSX: Message Flow Sensitivity Enhanced Structural Explainer for Graph Neural Networks
Bizu Feng, Zhimu Yang, Shaode Yu +1
Despite the widespread success of Graph Neural Networks (GNNs), understanding the reasons behind their specific predictions remains challenging. Existing explainability methods fac…
Taylor expansion-based Kolmogorov-Arnold network for blind image quality assessment
Ze Chen, Shaode Yu
Kolmogorov-Arnold Network (KAN) has attracted growing interest for its strong function approximation capability. In our previous work, KAN and its variants were explored in score r…