Machine Learning for Graphs and Sequential Data

Module IN2323

This Module is offered by TUM Department of Informatics.

This module handbook serves to describe contents, learning outcome, methods and examination type as well as linking to current dates for courses and module examination in the respective sections.

Module version of WS 2019/20 (current)

There are historic module descriptions of this module. A module description is valid until replaced by a newer one.

Whether the module’s courses are offered during a specific semester is listed in the section Courses, Learning and Teaching Methods and Literature below.

available module versions
WS 2019/20	SS 2015

Basic Information

IN2323 is a semester module in English language at Master’s level which is offered in summer semester.

This Module is included in the following catalogues within the study programs in physics.

Focus Area Imaging in M.Sc. Biomedical Engineering and Medical Physics

Total workload	Contact hours	Credits (ECTS)
150 h	60 h	5 CP

Content, Learning Outcome and Preconditions

Content

1. Introduction & Advanced ML Principles
* Machine Learning, Data Mining Process
* Basic Terminology
* Variational Inference
* Deep Generative Models: VAE, Implicit Models, GANs

2. Sequential Data
* ML models for text data and temporal data
* Autoregressive Models
* HMMs, Kalman Filter
* Embeddings (e.g. Word2Vec)
* Neural Networks (e.g. RNN, LSTM)
* Temporal Point Processes

3. Graphs & Networks
* Laws, Patterns
* (Deep) Generative Models for Graphs
* Spectral Methods
* Ranking (e.g., PageRank, HITS)
* Community Detection
* Node/Graph Classification
* Label Propagation
* Graph Neural Networks
* (Unsupervised) Node Embeddings
* Dynamic/temporal graphs

Learning Outcome

Upon successful completion of this module, students will be able to describe data
mining and machine learning methods and their applicability for complex data types.
The students will get to know concepts for handling non-independent data in machine
learning models. Furthermore, the students will be able to understand, apply, and
evaluate principles for analyzing complex data such as graphs, network data, and
temporal data.

Preconditions

Core modules from the Bachelor’s Informatics, semester 1-4 & knowledge of machine
learning principles (e.g. lecture IN2064)

Courses, Learning and Teaching Methods and Literature

Courses and Schedule

SS 2023 SS 2022 SS 2021 SS 2020 SS 2019 SS 2018 WS 2016/7 WS 2015/6

Type	SWS	Title	Lecturer(s)	Dates	Links
VI	4	Machine Learning for Graphs and Sequential Data (IN2323)	Fuchsgruber, D. Günnemann, S. Scholten, Y. Schuchardt, J. Sommer, J.	Wed, 14:00–16:00, Interims I 101 Thu, 14:00–16:00, Interims I 101	eLearning documents

Learning and Teaching Methods

Lecture, problems for individual study, assignments including project work

Media

Slides, exercise sheets, white board, project work

Literature

- Mining of Massive Datasets. Jure Leskovec, Anand Rajaraman, Jeffrey David Ullman. Cambridge University Press. 2014
- Data Mining: The Textbook. Charu Aggarwal. Springer. 2015
- The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Trevor Hastie, Robert Tibshirani, Jerome Friedman. Springer. 2011

Module Exam

Description of exams and course work

The academic assessment will be done by a written 75 minutes exam. Assignments
checking knowledge to verify the familiarity with machine learning models for graphs
and sequential data; programming assignments verify the ability to implement and
critically evaluate advanced algorithms and methods; small scenarios with defined
applications have to be set up by applying the learnt methods to verify the ability
to develop precise partial solutions.

Exam Repetition

The exam may be repeated at the end of the semester.

Current exam dates

Currently TUMonline lists the following exam dates. In addition to the general information above please refer to the current information given during the course.

Title
Time	Location	Info	Registration
Machine Learning for Graphs and Sequential Data
	101 0350 2501 2502