Graph Representation Learning and Its Applications: A Survey

Abstract

Graphs are data structures that effectively represent relational data in the real world. Graph representation learning is a significant task since it could facilitate various downstream tasks, such as node classification, link prediction, etc. Graph representation learning aims to map graph entities to low-dimensional vectors while preserving graph structure and entity relationships. Over the decades, many models have been proposed for graph representation learning. This paper aims to show a comprehensive picture of graph representation learning models, including traditional and state-of-the-art models on various graphs in different geometric spaces. First, we begin with five types of graph embedding models: graph kernels, matrix factorization models, shallow models, deep-learning models, and non-Euclidean models. In addition, we also discuss graph transformer models and Gaussian embedding models. Second, we present practical applications of graph embedding models, from constructing graphs for specific domains to applying models to solve tasks. Finally, we discuss challenges for existing models and future research directions in detail. As a result, this paper provides a structured overview of the diversity of graph embedding models.

Assessing Sensor Integrity for Nuclear Waste Monitoring Using Graph Neural Networks

“…A GNN is a machine learning algorithm that takes a graph as the input and by modifying the graph’s embeddings (from the nodes and the edges), can perform various prediction tasks (i.e., clustering, classification and regression). GNNs can operate predictions at multiple levels [ 1 , 2 , 3 , 4 , 5 , 6 , 7 ]: At the graph level, for instance, one could give a molecule (as an input graph) and try to find out whether the molecule is toxic. At the edge level, typical operations are friend recommendations on a social network graph.…”

“…Thus, the input graph was updated iteratively using a mechanism called message passing, which was described by Gilmer et al, 2017 [ 8 ]. The message-passing mechanism can be divided into the following tasks [ 1 , 2 , 3 , 4 , 5 , 6 , 7 , 8 , 9 ]: Select a node v . Collect information (the messages) from the neighboring nodes (and edges).…”

“…The message-passing mechanism can be understood as a convolution operation on the graph [ 4 , 5 , 6 , 9 , 10 , 11 , 12 , 13 , 14 ].…”

“…There exist various models of GNNs [ 2 , 3 , 4 , 5 , 6 , 7 , 15 ]. This study focused on a GNN that used convolution operators [ 2 , 3 , 4 , 5 , 6 , 7 , 15 ], contrary to the historical recurrent operators [ 16 , 17 , 18 , 19 , 20 ].…”

“…There exist various models of GNNs [ 2 , 3 , 4 , 5 , 6 , 7 , 15 ]. This study focused on a GNN that used convolution operators [ 2 , 3 , 4 , 5 , 6 , 7 , 15 ], contrary to the historical recurrent operators [ 16 , 17 , 18 , 19 , 20 ]. Convolution operators can either be spectral [ 8 , 9 , 10 , 11 , 12 , 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 , 30 ] or spatial [ 13 , 14 , 31 , 32 ].…”