HARMONIA: Interpretable Graph Learning through Mixtures of Neural Bases
Existing interpretable graph additive models still face limitations in either computational scalability or modeling flexibility. In terms of structural modeling, previous approaches either face quadratic scaling costs or sacrifice explicit source-to-target contribution decomposition. In terms of feature components, the...
Quan D. Bui, D. Nguyen, A. Dang et al.
· 0 citations