Deep Loopy Neural Network Model for Graph Structured Data Representation Learning

TL;DR

This paper introduces a novel deep loopy neural network model designed for graph-structured data, along with a specialized learning algorithm that propagates errors through spanning trees, demonstrating effectiveness on real-world datasets.

Contribution

The paper presents a new deep neural network architecture for graphs with a tailored learning algorithm to handle complex loops, advancing graph data representation methods.

Findings

Effective on multiple real-world graph datasets

Outperforms existing models in handling graph loops

Demonstrates improved learning efficiency

Abstract

Existing deep learning models may encounter great challenges in handling graph structured data. In this paper, we introduce a new deep learning model for graph data specifically, namely the deep loopy neural network. Significantly different from the previous deep models, inside the deep loopy neural network, there exist a large number of loops created by the extensive connections among nodes in the input graph data, which makes model learning an infeasible task. To resolve such a problem, in this paper, we will introduce a new learning algorithm for the deep loopy neural network specifically. Instead of learning the model variables based on the original model, in the proposed learning algorithm, errors will be back-propagated through the edges in a group of extracted spanning trees. Extensive numerical experiments have been done on several real-world graph datasets, and the experimental results demonstrate the effectiveness of both the proposed model and the learning algorithm in handling graph data.