Learning with Hierarchical Data

PhD Thesis Proposal Defence


Title: "Learning with Hierarchical Data"

by

Miss Huiru XIAO


Abstract:

When coming to understand the world, for example, learning concepts, acquiring 
language, and grasping causal relations, we human minds construct structured 
knowledge from sparse, noisy, and ambiguous data. Therefore, humanlike machine 
learning should perform inference over hierarchies of flexibly structured data. 
Based on these beliefs, people usually construct real-world data as hierarchies 
to formulate the machine learning problem, where the hierarchical data serve as 
the hypotheses or the inference queries. In this thesis, we study learning with 
hierarchical data. First, we look into the classification problem with 
hierarchical classes, which corresponds to the hierarchical data acting as 
hypotheses. In specific, we investigate hierarchical text classification and 
propose a path cost-sensitive learning algorithm to utilize the structural 
information of classes.. Then we pay much attention to exploring the geometric 
representation learning for hierarchical structures in knowledge graphs, in 
which case the hierarchical data are inference queries. The choice of geometric 
space for knowledge graph embeddings can have significant effects on the 
multi-relational knowledge graph inference.  To build a representation learning 
framework for various structures in knowledge graphs, we propose to learn the 
knowledge base embeddings in different geometric spaces and apply manifold 
alignment to align the shared entities. We also focus on the representation of 
the single-relational hierarchical structures. To improve the hyperbolic 
embeddings, we propose to learn the embeddings of hierarchically structured 
data in the complex hyperbolic space, which has a more powerful representation 
capacity to capture a variety of hierarchical structures. Finally, we plan to 
extend the representation capacity of the complex hyperbolic geometry in 
multi-relational knowledge graph embeddings.


Date:			Wednesday, 15 June 2022

Time:                  	4:30pm - 6:30pm

Zoom Meeting: 		https://hkust.zoom.us/j/4326746945

Committee Members:	Dr. Yangqiu Song (Supervisor)
  			Dr. Qifeng Chen (Chairperson)
 			Prof. Raymond Wong
 			Prof. Dit-Yan Yeung


**** ALL are Welcome ****