Graph Neural Networks for Knowledge Graph Systems (Wintersemester 2022/2023)

Lecturer: Prof. Dr. Holger Giese (Systemanalyse und Modellierung) , Christian Medeiros Adriano (Systemanalyse und Modellierung) , Matthias Barkowsky (Systemanalyse und Modellierung) , Iqra Zafar (Systemanalyse und Modellierung)

General Information

• Weekly Hours: 4
• Credits: 6
• Graded: yes
• Enrolment Deadline: 01.10.2022 - 31.10.2022
• Examination time §9 (4) BAMA-O: 01.02.2023
• Teaching Form: Project / Seminar
• Enrolment Type: Compulsory Elective Module
• Course Language: English

Programs, Module Groups & Modules

Description

Graph Neural Networks are a set of novel techniques aimed at enabling deep neural networks to work on heterogeneous graphs, e.g., social networks, knowledge graphs, recommender systems, gene regulatory networks, traffic networks, etc. These heterogeneous graphs became central components of complex software systems, which make predictions and interventions on the structure and behavior of the system and its context (e.g., users, environment). Take, for instance, the mitigation of the spread of an event (accident, rumors, disease) through a network (traffic, social network). The heterogeneous network would model the current state of connections, their strength, and multiple properties in their nodes and edges. This complex data would be used to predict the propagation paths and indicate the best set of nodes to intervene to mitigate the spread of rumors or disease and its effect on a system as a whole (traffic, population). Interventions can involve changes in the connections (isolate, circumvent, shortcut) and the attributes of the nodes (duplicate, reset, extend).

Note, however, that neural networks algorithms were initially developed to solve problems in the domains of computer vision (3D and 2D) and natural language processing (1D). These domains present Euclidean spaces that allow neural networks to leverage on the regularities inherent to coordinate systems, vector space structures, or fixed distributions. Because these regularities are not guaranteed to be present in heterogeneous networks, new extensions were developed to these algorithms.

In this project seminar, we will study extensions to neural networks and apply them to heterogeneous graphs of real-world problems. We will tackle these domain-specific problems in a principled way by solving the more generic graph-related problems of node classification, structure discovery, path identification, subgraph generation. 

Topics:

• Intro to Graph Neural Networks 
  • Descriptive Graph Models
    • Graph Structural Features  (Metrics, Clustering)
    • Graph Simulation (Generative Models, Random Models)
  • Prediction on Graph Models
    • Graph Embeddings - Message Passing
    • Graph Convolutional Networks
    • Graph Attention Networks
  • Knowledge Graph Systems
    • Traditional applications (semantic web, knowledge Discovery)
    • Advanced applications
      • Evolution phenomena (new nodes, edges)
      • Temporal phenomena (anomalies, event propagation, influence, spread)

Literature

Books, Surveys and Tutorials

• Kejriwal, M., Knoblock, C. A., & Szekely, P. (2021). Knowledge graphs: Fundamentals, techniques, and applications. MIT Press.
• Abu-Salih, B. (2021). Domain-specific knowledge graphs: A survey. Journal of Network and Computer Applications, 185, 103076.
• Yu, S., Xu, C., Bai, X., Kuncheerathodi, R., Firmin, S., & Xia, F. (2022). Deep Learning Meets Knowledge Graphs: A Comprehensive Survey.
• Hamilton, W. L. (2020). Graph representation learning. Synthesis Lectures on Artificial Intelligence and Machine Learning, 14(3), 1-159.
• Sanchez-Lengeling, B., Reif, E., Pearce, A., & Wiltschko, A. B. (2021). A gentle introduction to graph neural networks. Distill, 6(9), e33.
• Zhou, J., Cui, G., Hu, S., Zhang, Z., Yang, C., Liu, Z., ... & Sun, M. (2020). Graph neural networks: A review of methods and applications. AI Open, 1, 57-81.
• Ma, X., Wu, J., Xue, S., Yang, J., Zhou, C., Sheng, Q. Z., ... & Akoglu, L. (2021). A comprehensive survey on graph anomaly detection with deep learning. IEEE Transactions on Knowledge.

Papers

• Vaska, N., & Helus, V. (2022). Context-Dependent Anomaly Detection with Knowledge Graph Embedding Models. arXiv preprint arXiv:2203.09354.
• Zheng, L., Li, Z., Li, J., Li, Z., & Gao, J. (2019, August). AddGraph: Anomaly Detection in Dynamic Graph Using Attention-based Temporal GCN. In IJCAI (pp. 4419-4425).
• Qiu, J., Du, Q., Yin, K., Zhang, S. L., & Qian, C. (2020). A causality mining and knowledge graph based method of root cause diagnosis for performance anomaly in cloud applications. Applied Sciences, 10(6), 2166.
• Sun, Y., Zhao, L., Wang, Z., Cui, D., Yang, Y., & Gao, Z. (2021, August). Fault Root Rank Algorithm Based on Random Walk Mechanism in Fault Knowledge Graph. In 2021 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB) (pp. 1-6). IEEE.
• Li, Z., Zhao, Y., Li, Y., Rahman, S., Wang, F., Xin, X., & Zhang, J. (2021). Fault localization based on knowledge graph in software-defined optical networks. Journal of Lightwave Technology, 39(13), 4236-4246.

Learning

The course is a project seminar, which has an introductory phase comprising initial short lectures. After that, the students will work in groups on jointly identified experiments applying specific solutions to given problems and finally prepare a presentation and write a report about their findings concerning the experiments.

There will be an introductory phase to present basic concepts for the theme, including the necessary foundations.

Lectures will happen in a seminar room and the students interested can also join online via Zoom (credentials)*

Examination

We will grade the group's reports (80%) and presentations (20%). Note that the report includes documenting the experiments and the obtained results. Therefore, the grading of the report includes the experiments. During the project phase, we will require participation in meetings and other groups' presentations in the form of questions and feedback to their peers.

Dates

The first lecture will take place on October 18, 2022 (Tuesday) from 11:00-12:30. The lectures will take place in rooms L-1.02(Tuesdays) and A-2.1(Wednesdays) and remotely via Zoom (credentials)*

We will follow the recurrent schedule of:

• Tuesdays from 11:00-12:30 in room A-1.2
• Wednesdays from 15:15-17:00 in room A-2.1 (different room)

* In case that you do not have access to GitLab, please email christian.adriano [at] hpi.de

Zurück