Deep Loopy Neural Network Model for Graph Structured Data Representation Learning
This addresses a problem for researchers and practitioners working with graph data, but it appears incremental as it builds on existing deep learning models with a specific adaptation for loops.
The paper tackles the challenge of training deep neural networks on graph-structured data by introducing a deep loopy neural network and a learning algorithm that back-propagates errors through extracted spanning trees, with experiments on real-world datasets showing effectiveness.
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.