Graph Signal Recovery Using Restricted Boltzmann Machines
This work addresses the problem of recovering graph signals from noisy data, which is relevant for researchers working with graph-structured datasets and expert systems.
This paper proposes a model-agnostic pipeline to recover graph signals from an expert system. It leverages the content addressable memory of Restricted Boltzmann Machines and the representational ability of neural networks, demonstrating that denoising learned representations is more effective than denoising the raw data itself.
We propose a model-agnostic pipeline to recover graph signals from an expert system by exploiting the content addressable memory property of restricted Boltzmann machine and the representational ability of a neural network. The proposed pipeline requires the deep neural network that is trained on a downward machine learning task with clean data, data which is free from any form of corruption or incompletion. We show that denoising the representations learned by the deep neural networks is usually more effective than denoising the data itself. Although this pipeline can deal with noise in any dataset, it is particularly effective for graph-structured datasets.