A Survey on Temporal Link Prediction

PhD Qualifying Examination


Title: "A Survey on Temporal Link Prediction"

by

Mr. Meng QIN


Abstract:

For various complex systems, dynamic graph serves as a generic abstraction and 
description of their evolutionary behaviors. Temporal link prediction (TLP) is 
a classic inference task on dynamic graphs, which aims to predict possible 
future linkage using the historical dynamic topology. The predicted future 
topology can be further used to support some advanced applications on 
real-world systems for better performance. This survey provides a comprehensive 
review of existing representative TLP methods. Concretely, we first give the 
formal statements regarding the data models, task settings, and learning 
paradigms used in related approaches. A hierarchical taxonomy is further 
introduced to categorize existing TLP methods in terms of their data models, 
learning paradigms, and techniques. From a generic perspective, we use a 
unified encoder-decoder framework to formulate all the methods reviewed in this 
survey, where each method can be described by an encoder, a decoder, and a loss 
function. To conclude this survey, we also summarize some advanced topics in 
recent research and highlight possible future directions.


Date:  			Friday, 24 June 2022

Time:                  	10:00am - 12:00noon

Zoom Meeting:
https://hkust.zoom.us/j/95877658018?pwd=aWlpeHI1UHhQMmNmVVBXTEtocW1wUT09

Committee Members:	Prof. Dit-Yan Yeung (Supervisor)
 			Dr. Yangqiu Song (Chairperson)
 			Prof. Raymond Wong
 			Prof. Tong Zhang
 			Prof. Xiaofang Zhou


**** ALL are Welcome ****