Year: 2021
Type: preprint
Abstract: In this paper, we consider an inverse problem in graph learning domain -- ``given the graph representations smoothed by Graph Convolutional Network (GCN), how can we reconstruct the input graph signal?" We propose Graph Deconvolutional Network (GDN) and motivate the design of GDN via a combination of inverse filters in spectral domain and de-noising layers in wavelet domain, as the inverse operation results in a high frequency amplifier and may amplify the noise. We demonstrate the effectiveness of the proposed method on several tasks including graph feature imputation and graph structure generation.
Source: arXiv (Cornell University)
Authors: Li, Jia, Li, Jiajin, Liu, Yang, Yu, Jianwei, Li, Yueting, Cheng, Hong
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Award: G6705365387
OpenAlex ID: W3208378893