Network Representation Learning: Opportunities and Open Challenges
|
|
Ling Liu
School of Computer Science
Georgia Institute of Technology
|
Abstract
Mining information networks have traditionally relied on observable features, such as node and link properties as well as user-defined statistical features extracted from complex networks, such as node degree, traversal path.
With the recent success of deep neural networks, a wide variety of deep neural network models have been proposed, which can automatically learn to encode network structure into low-dimensional embeddings, using techniques based on deep learning and nonlinear dimensionality reduction.
These network representation learning (NRL) approaches replace the need for manual feature engineering with automated learning of latent features of network representation, and have led to state-of-the-art results in network-based tasks, such as node classification, node clustering, and link prediction.
In this keynote, I will describe the recent advancements in NRL, including network embedding, graph neural networks, including the methods to embed individual nodes as well as algorithms to embed entire (sub)graphs.
Most existing models learn node embeddings through flat information propagation across the edges or traversal paths within each node's local neighborhood.
I will share our experience with employing NRL for Bitcoin transaction forecasting, and a general framework for graph neural networks to learn node representations, which can generate node embeddings that preserve the global structure of the original graphs at different levels of the graph hierarchy.
Biography
Ling Liu is a Professor in the School of Computer Science at Georgia Institute of Technology.
She directs the research programs in the Distributed Data Intensive Systems Lab (DiSL), examining various aspects of large scale big data-powered artificial intelligence (AI) systems, and machine learning (ML) algorithms and analytics, including performance, availability, privacy, security and trust.
Prof. Liu is an elected IEEE Fellow, a recipient of IEEE Computer Society Technical Achievement Award (2012), and a recipient of the best paper award from numerous top venues, including IEEE ICDCS, WWW, ACM/IEEE CCGrid, IEEE Cloud, IEEE ICWS.
Prof. Liu served on editorial board of over a dozen international journals, including the editor in chief of IEEE Transactions on Service Computing (2013-2016) and currently, the editor in chief of ACM Transactions on Internet Computing (TOIT).
Prof. Liu is a frequent keynote speaker in top-tier venues in Big Data, AI and ML systems and applications, Cloud Computing, Services Computing, Privacy, Security and Trust.
Her current research is primarily supported by USA National Science Foundation under CISE programs and IBM.
|
|
|
