About this Research Topic
Graph structured data are a universal way to structure data for representing the relationship between interconnected objects in the real-world. They are ubiquitous throughout a variety of disciplines and domains ranging from computer science, social science, quantum chemistry, to bioinformatics. Such data are high-dimensional, irregular, and have a complex structure that can be naturally represented by a graph. Given the high prevalence of graphs, learning representations of graphs is important for various downstream tasks such as recommender systems, chemical synthesis, 3D-vision, question answering, information retrieval and social network analysis, etc.
The goal of this Research Topic is to introduce recent advances on graph representation learning and various applications of graph-based machine learning. Inspired by the recent unprecedented developments in deep learning in various fields such as computer vision and natural language processing, recent efforts on graph representation learning have mainly utilized machine learning approaches. The main challenge in machine learning on graphs is finding a way to incorporate information about the structure of the graph and all sorts of information related to nodes and edges into the machine learning model.
We invite submissions of high-quality manuscripts that introduce novel methods for graph representation learning and their applications in various domains. The list of possible topics includes, but not limited to:
• Machine learning on graphs: kernel-based techniques, clustering methods, scalable algorithms
• Novel methods for learning embeddings
• Graph embedding
• Deep learning on Graphs
• Applications for biological data (brain networks, protein-to-protein interactions)
• Applications for finance, economic, user behavior analysis, knowledge graphs, and social networks
• Applications to communications, power, and transportation networks
The goal of this Research Topic is to introduce recent advances on graph representation learning and various applications of graph-based machine learning. Inspired by the recent unprecedented developments in deep learning in various fields such as computer vision and natural language processing, recent efforts on graph representation learning have mainly utilized machine learning approaches. The main challenge in machine learning on graphs is finding a way to incorporate information about the structure of the graph and all sorts of information related to nodes and edges into the machine learning model.
We invite submissions of high-quality manuscripts that introduce novel methods for graph representation learning and their applications in various domains. The list of possible topics includes, but not limited to:
• Machine learning on graphs: kernel-based techniques, clustering methods, scalable algorithms
• Novel methods for learning embeddings
• Graph embedding
• Deep learning on Graphs
• Applications for biological data (brain networks, protein-to-protein interactions)
• Applications for finance, economic, user behavior analysis, knowledge graphs, and social networks
• Applications to communications, power, and transportation networks
Keywords: Graph representation learning, Graph-based machine learning, Graph mining, Graph embedding, Deep learning
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
