Generative Adversarial Networks for Graph Data Imputation from Signed Observations

Amarlingam Madapu; Santiago Segarra; Sundeep Prabhakar Chepuri; Antonio G. Marques

ICASSP 2020accepted0 citations

Generative Adversarial Networks for Graph Data Imputation from Signed Observations

Amarlingam Madapu, Santiago Segarra, Sundeep Prabhakar Chepuri, Antonio G. Marques

Abstract

We study the problem of missing data imputation for graph signals from signed one-bit quantized observations. More precisely, we consider that the true graph data is drawn from a distribution of signals that are smooth or bandlimited on a known graph. However, instead of observing these signals, we observe a signed version of them and only at a subset of the nodes on the graph. Our goal is to estimate the true underlying graph signals from our observations. To achieve this, we propose a generative adversarial network (GAN) where the key is to incorporate graph-aware losses in the associated minimax optimization problem. We illustrate the benefits of the proposed method via numerical experiments on hand-written digits from the MNIST dataset.

BibTeX

@inproceedings{icassp2020_generativeadvers,
  title = {Generative Adversarial Networks for Graph Data Imputation from Signed Observations},
  author = {Amarlingam Madapu and Santiago Segarra and Sundeep Prabhakar Chepuri and Antonio G. Marques},
  booktitle = {ICASSP 2020},
  year = {2020}
}