Graphs and more Complex structures for Learning and Reasoning (GCLR) workshop was held at AAAI 2021. For more details about the workshop, please visit website: https://sites.google.com/view/gclr2021/.
Speaker's Bio: Ines Chami is a Ph.D. candidate in ICME at Stanford University. Her research interests include Machine Learning, Representation Learning, Deep learning and Relational Reasoning. More specifically, she is interested in designing models that can learn representations for complex relational structures such as graphs. In this talk, she will review basic notions of hyperbolic geometry and then go over machine learning algorithms that learn embeddings into hyperbolic space followed by a recent application of such embeddings, namely link prediction in Knowledge Graphs.
Title of the talk: Hyperbolic Embeddings and a Knowledge Graph Application
Abstract: Graph embedding methods aim at learning representations of nodes that preserve graph properties (e.g. graph distances). These embeddings can then be used in downstream applications such as recommendation systems. Most machine learning algorithms learn embeddings into the standard Euclidean space. Recent research shows promise for more faithful embeddings by leveraging non-Euclidean geometries, such as hyperbolic or spherical geometries. In particular, trees can be embedded almost perfectly into hyperbolic space, while this is not possible in standard Euclidean space. In this talk, we review basic notions of hyperbolic geometry and then go over machine learning algorithms that learn embeddings into hyperbolic space. We cover a recent application of such embeddings, namely link prediction in Knowledge Graphs.