Information Package / Course Catalogue
Graph Mining
Course Code: MCS513
Course Type: Area Elective
Couse Group: Second Cycle (Master's Degree)
Education Language: English
Work Placement: N/A
Theory: 3
Prt.: 0
Credit: 3
Lab: 0
ECTS: 6
Objectives of the Course

The objectives of the course is to understand where graphs are being used, why they are important and what new applications exisits for graph mining. Graph neural networks will be discussed for their compatibility with machine learning techniques in graph mining.

Course Content

The cource is intended to provide an introduction to the broad and rising topic of graph mining with a focus on challanges, algoritmic solutions and new problems.

Name of Lecturer(s)
Learning Outcomes
1.Database methods; graph querying.
2.Community and anomaly detection
3.Graph summarization
4.Core concepts about graph neural networks
5.Knowledge graph use in graph neural networks
Recommended or Required Reading
1.Aggarwal, C.C. and Wang, H. eds., 2010.Managing and mining graph data (Vol. 40). New York: Springer
2.Chakrabarti, D. and Faloutsos, C., 2012. Graph mining: laws, tools, and case studies. Synthesis Lectures on Data Mining and Knowledge Discovery, 7(1), pp.1-207.
3.Hamilton, William L. 2020. Graph Representation Learning. Synthesis Lectures on Artificial Intelligence and Machine Learning. Morgan and Claypool.
Weekly Detailed Course Contents
Week 1 - Theoretical
Introduction to graph mining
Week 2 - Theoretical
Basic concepts about graphs and linear algebra
Week 3 - Theoretical
Graph queries
Week 4 - Theoretical
Community Identification
Week 5 - Theoretical
Frequent Subgraph Mining
Week 6 - Theoretical
Link Prediction
Week 7 - Theoretical
Graph Summarization and graph embeddings
Week 8 - Theoretical
Introduction to Graph Neural Networks (GNNs)
Week 9 - Theoretical
Node Embeddings
Week 10 - Theoretical
GNNs
Week 11 - Theoretical
GNN Training
Week 12 - Theoretical
Knowledge graphs
Week 13 - Theoretical
Fast neural subgraph matching
Week 14 - Theoretical
Advanced graph mining techniques with GNNs
Assessment Methods and Criteria
Type of AssessmentCountPercent
Attending Lectures1%5
Assignment1%10
Midterm Examination1%15
Final Examination1%70
Workload Calculation
ActivitiesCountPreparationTimeTotal Work Load (hours)
Lecture - Theory142370
Assignment141242
Individual Work140114
Midterm Examination18311
Final Examination110515
TOTAL WORKLOAD (hours)152
Contribution of Learning Outcomes to Programme Outcomes
PÇ-1
PÇ-2
PÇ-3
PÇ-4
PÇ-5
PÇ-6
PÇ-7
PÇ-8
PÇ-9
OÇ-1
3
3
3
3
5
3
5
3
3
OÇ-2
4
4
4
3
5
4
3
4
3
OÇ-3
3
3
5
5
5
4
3
5
5
OÇ-4
5
4
5
4
4
4
5
5
4
OÇ-5
3
3
3
3
4
3
4
3
3
Adnan Menderes University - Information Package / Course Catalogue
2026