Multiview Graph Restricted Boltzmann Machines

Nan Zhang, Shiliang Sun

2021IEEE Transactions on Cybernetics18 citationsDOI

Abstract

Recently, the restricted Boltzmann machine (RBM) has aroused considerable interest in the multiview learning field. Although effectiveness is observed, like many existing multiview learning models, multiview RBM ignores the local manifold structure of multiview data. In this article, we first propose a novel graph RBM model, which preserves the data manifold structure and is amenable to Gibbs sampling. Then, we develop a multiview graph RBM model on the basis of the graph RBM, which performs local structural learning and multiview representation learning simultaneously. The proposed multiview model has the following merits: 1) it preserves the data manifold structure for multiview classification and 2) it performs view-consistent representation learning and view-specific representation learning simultaneously. The experimental results show that the proposed multiview model outperforms other state-of-the-art multiview classification algorithms.

Topics & Concepts

Artificial intelligenceRestricted Boltzmann machineComputer scienceGraphRepresentation (politics)Boltzmann machinePattern recognition (psychology)Feature learningManifold (fluid mechanics)External Data RepresentationManifold alignmentNonlinear dimensionality reductionAlgorithmDeep learningMachine learningTheoretical computer scienceDimensionality reductionMechanical engineeringPoliticsLawEngineeringPolitical scienceAdvanced Graph Neural NetworksDomain Adaptation and Few-Shot LearningGenerative Adversarial Networks and Image Synthesis