HUA, Fengrui - HKUST Class Schedule & Quota

Class Schedule & Quota
2025-26 Spring 2025-26 Winter 2025-26 Fall 2024-25 Summer
2025-26 Spring
Common Core Course
The class information on this page will normally be updated every 15 to 20 minutes during class enrollment period.
» Student Information System (SIS)» PG Program/Course Catalog
Notes & Links
This service was first adapted from a student contribution in 2011-12 Fall. The efforts of all concerned are duly acknowledged.

AIAA AMAT BSBE CMAA CNCC CNGF DLED DSAA EOAS FTEC FUNH INFH INTR IOTA IPEN LANG MICS MSSM PDEV PLED ROAS SEEN SMMG SOCH SYSH UCMP UCUG UFUG UGOD

COURSE INFO

VECTOR	[3-0-0:3]
DESCRIPTION	Graph data are pervasive in finance and business management. The course will be organized in three parts. Part I introduces graph data types and representations, including typical simple/weighted and directed/undirected graphs; bipartite, heterogeneous and knowledge graphs; temporal/dynamic graphs; hypergraphs together with node/edge attributes and common storage/processing patterns. Part II introduces graph data modeling methods from shallow embeddings to modern graph neural networks (message passing mechanism, heterogeneous/temporal architectures, contrastive pretraining) and LLM-based approaches (graph-aware prompting, graph-based RAG, graph foundation models). Part III examines graph data based applications in finance and business management, including anomaly and fraud detection, stock market prediction, and recommendation systems, with emphasis on reproducible, practice-oriented implementation.

VECTOR

[3-0-0:3]

DESCRIPTION

Graph data are pervasive in finance and business management. The course will be organized in three parts. Part I introduces graph data types and representations, including typical simple/weighted and directed/undirected graphs; bipartite, heterogeneous and knowledge graphs; temporal/dynamic graphs; hypergraphs together with node/edge attributes and common storage/processing patterns. Part II introduces graph data modeling methods from shallow embeddings to modern graph neural networks (message passing mechanism, heterogeneous/temporal architectures, contrastive pretraining) and LLM-based approaches (graph-aware prompting, graph-based RAG, graph foundation models). Part III examines graph data based applications in finance and business management, including anomaly and fraud detection, stock market prediction, and recommendation systems, with emphasis on reproducible, practice-oriented implementation.

FTEC 6910H - Graph Machine Learning: Methods and Applications (3 units)

Section	Date & Time	Room	Instructor	Quota	Enrol	Avail	Wait	Remarks
L01 (6087)	Tu 06:00PM - 08:50PM	Rm 201, E4	HUA, Fengrui ZHANG, Liang	20	10	10	0