The Machine Learning Hub seminar series presents:
“Representation Learning from Graphs, Algorithms and Applications”
by Dr. Xiangliang Zhang, an Associate Professor of Computer Science (CS) and Principal Investigator of the Machine Intelligence & kNowledge Engineering (MINE) Laboratory at KAUST.
Wednesday, October 30
12:00 p.m. – 1:00 p.m.
Building 9, hall 2
Abstract:
Graph/Network embedding is to represent graph vertices or a graph itself as new low-dimensional vectors. It has been playing important roles in diverse network management and analysis applications. Learning representation from graphs faces challenges of the preservation of vertex-vertex relevance, the integration of structure and text information, and the heterogeneity of vertex attributes, and the large size of graphs, etc.
This talk will introduce recent solutions to them based on reinforcement learning for intelligently aggregating a vertex’s neighborhood information to represent itself, based on variational autoencoder for encoding the uncertainty, and based on information fusion/propagation for resolving the node heterogeneity. The obtained embedding results will be demonstrated in standard applications of node classification and link prediction, user profiling, as well as recommendation and graph alignment.
To read the speaker’s bio and learn more about her work, please click here.
KAUST Machine Learning Hub
http://ml.kaust.edu.sa/
