Deconvolutional Networks on Graph Data

Jia Li, Jiajin Li, Yang Liu, Jianwei Yu, Yueting Li, Hong Cheng

Keywords: deconvolutional networks, inverse problem, graph generation

TL;DR: The first work about deconvolutional networks on graph data

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.

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.