Path Learning in Complex Networks

PhD Thesis Proposal Defence


Title: "Path Learning in Complex Networks"

by

Miss Wenyi XIAO


Abstract:

Graph representation learning (GRL) aims to encode the nodes and edges in 
complex networks into low dimensional vector space while preserving the 
inherent structure of the graphs. To learn better representations, three 
aspects of GRL, i.e., structural information in homogeneous graphs, relational 
information in heterogeneous graphs, and GRL to build side information for 
certain applications, e.g. recommendation systems, are extensively studied in 
the literature. However, sometimes two nodes in complex networks are located 
far away from each other. It is difficult for the GRL based models to capture 
the pairwise relationship with long distances. Besides, it will suffer from 
memory explosion if we aggregate all the high-order neighbors' information in 
graphs. Hence, we use path learning to select high-order neighbors to enrich 
the information for the target nodes. Recently, path-based models have 
exhibited their power in many machine learning tasks. Inspired by the analysis 
of paths in both academia and industry, we propose path learning in complex 
networks in this thesis proposal to address the three aspects of GRL in 
different ways.

In detail, we propose Reinforce2vec, a biased random walk based approach for 
network embedding on homogeneous graphs. Our model uses a non-Markovian process 
to fully use the history of a random walk path. Secondly, to capture the 
inductive bias for learning PathSim based similarity scores, we propose NeuPath 
to identify a fixed number of path instances that can best infer the target 
meta-path(s) in heterogeneous information networks. Thirdly, we study how the 
structural information learned by path learning could be applied as the side 
information for the news recommendation task. We design an MCTS based method to 
explore high-order friends for the target user A personalized hierarchical 
attention network is proposed for news recommendation on decentralized 
platforms. Besides, we construct a variant model for more industry-driven 
applications. Extensive experiments demonstrate the effectiveness of the path 
learning and efficiency of each search algorithm.


Date:			Tuesday, 19 October 2021

Time:                  	9:00am - 11:00am

Zoom Meeting: 
https://hkust.zoom.us/j/93963731726?pwd=OERVYUFZNDVGeS9OZC9QOU1ITk1IZz09

Committee Members:	Dr. Yangqiu Song (Supervisor)
 			Prof. Xiaofang Zhou (Chairperson)
 			Prof. Raymond Wong
 			Prof. Nevin Zhang


**** ALL are Welcome ****