Grale
Jonathan Halcrow, Alexandru Moșoi, Sam Ruth, Bryan Perozzi
Abstract
How can we find the right graph for semi-supervised learning? In real world applications, the choice of which edges to use for computation is the first step in any graph learning process. Interestingly, there are often many types of similarity available to choose as the edges between nodes, and the choice of edges can drastically affect the performance of downstream semi-supervised learning systems. However, despite the importance of graph design, most of the literature assumes that the graph is static.
Topics & Concepts
Computer scienceGraphTheoretical computer scienceComputationArtificial intelligenceMachine learningAlgorithmAdvanced Graph Neural NetworksRecommender Systems and TechniquesMachine Learning and Data Classification