Seoul National University
M2177.003000 Advanced Data Mining
Fall 2020 - U Kang

News and Announcements

Course Information

Data mining attracted much interests as an essential tool for big data analysis. Especially, designing and implementing advanced data mining algorithms and analysis platforms play crucial roles in extracting executable knowledges from big data. This course covers advanced data mining techniques, algorithms, and core platforms for big data analysis. This course also covers the techniques to effectively analyze very large data and high-speed data.

A very important aspect of this course is the course project. Students will pick an interesting data mining project, and do data mining researches on the topic. At the end of the course, students will learn how to do interesting researches in data mining, and how to write good papers.

Schedule

Date Topic Due
Sep. 2 Course introduction
7 Graph-1: basics and diameter
(Optional Reading)
9 Graph-2: models for graphs
(Mandatory Reading) (Optional Reading)
Hw1
14 Graph-3: power law
(Mandatory Reading) (Optional Reading)
Hw2
16 Graph-4: structure analysis
(Optional Reading)
21 Spectral analysis-1: random walk
(Optional Reading)
23, 28 Spectral analysis-2: link analysis
(Mandatory Reading) (Optional Reading)
Hw3
30 Spectral analysis-3: random walk with restart
(Optional Reading)
Oct. 5 Spectral analysis-4: link prediction
(Optional Reading)
7 Spectral analysis-5: triangle counting
(Mandatory Reading) (Optional Reading)
Hw4
12 MapReduce-1: architecture
(Mandatory Reading)
Hw5
14 MapReduce-2: data mining algorithms
(Optional Reading)
19 SVD-1: basic definition
(Optional Reading)
21 Midterm
26 Guest lecture 1
28 SVD-2: case studies
(Mandatory Reading) (Optional Reading)
Hw6
Nov. 2 SVD-3: properties
(Optional Reading)
4 Tensor analysis 1
(Mandatory Reading) (Optional Reading)
Hw7
9 Tensor analysis 2
(Optional Reading)
11 Recommendation 1
(Mandatory Reading)
Hw8
16 Recommendation 2
(Mandatory Reading)
Hw9
18 Time series analysis
(Optional Reading)
23 Approximation
(Optional Reading)
25 Graph compression
(Mandatory Reading) (Optional Reading)
Hw10
30 Community detection
(Optional Reading)
Dec. 2 Anomaly detection
(Mandatory Reading) (Optional Reading)
Hw11
7 How to do great research
9 Final exam week
14 Final exam week

Grading

Late policy - for all deliverables:

Textbook

There is no textbook required.

Prerequisite

Undergraduate level algorithm, statistics and linear algebra.
Last modified Aug. 25, 2020, by U Kang