Instructor: | A. Erdem Sariyuce (erdem AT buffalo.edu) |

Class hours: | Wed 6:00-8:30, Online (Zoom links will be sent to enrolled students, email me if not enrolled yet) |

Office hours: | Wed 12:00-2:00, Online over Zoom |

Graphs are everywhere. Their scale, rate of change, and the irregular nature pose many new challenges. Deep learning has been shown to be successful in a number of domains, ranging from images to natural language processing. However, applying deep learning to the ubiquitous graph data is non-trivial because of the unique characteristics. This seminar course covers recent papers in the last few years about deep learning on graphs. We will consider graph embeddings, knowledge graphs, graph kernels, graph neural networks, graph convolutional networks, graph adversarial methods. Students will learn the literature on deep learning on graphs, understand the state-of-the-art algorithms on various problems, and be familiar with the recent trends.

It is assumed that students have a solid background on discrete mathematics and algorithms. Basic research skills like paper reading, critical thinking, problem solving, report writing, communication, and presentation are important as well.

- Paper presentation: 40%
- Piazza questions: 30%
- Class participation: 30%

- Paper presentation: 40%
- Piazza questions: 20%
- Class participation: 20%
- Literature survey: 20%

The final grade is S/U and 75% score is needed for an S. Regarding the literature survey (for students taking 3 credits), topic will be decided with instructor.

Each student picks one paper from the reading list and present. Tentative schedule is below. A presentation is expected to be an hour long. Each week, all the students will read the papers of the week before class and will ask **a unique question** on Piazza (except the presenter) to facilitate a class discussion. Questions should be open-ended and provide ground for class discussions, i.e., 'can you explain alg 1?' is not that kind of question. Questions should be posted to Piazza by Monday night, 11.59 pm EST.

- Sep 2:
**Introduction, Course Overview by instructor****[Slides for the first class]**

- Sep 9:

**Geometric deep learning: going beyond Euclidean data IEEE Signal Processing Magazine 2017***by Nick*

- Sep 16:

**GraRep: Learning Graph Representations with Global Structural Information CIKM 2015***by Srijit*

- Sep 23:

**Asymmetric Transitivity Preserving Graph Embedding KDD 2016***by Shivaleela*

- Sep 30:

**node2vec: Scalable Feature Learning for Networks KDD 2016***by Penghang*

- Oct 7:

**Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec WSDM 2018***by Nanditha*

- Oct 14:

**The impossibility of low-rank representations for triangle-rich complex networks PNAS 2020***by Priyanka*

- Oct 21:

**Complex Embeddings for Simple Link Prediction ICML 2016***by Baoqian*

- Oct 28:

**Semi-supervised classification with graph convolutional networks ICLR 2017***by Menglong*

- Nov 4:

**A survey on graph kernels (2 STUDENTS) Applied Network Science 2020***by Bharat & Vinita*

- Nov 11:

**Graph attention networks. ICLR 2018***by Steve*

**Inductive Representation Learning on Large Graphs NIPS 2017***by Harishkandan*

- Nov 18:

**GNNExplainer: Generating Explanations for Graph Neural Networks NeurIPS 2019***by Rui*

- Nov 25:

**NO CLASS (FALL RECESS)**

- Dec 2:

**The logical expressiveness of graph neural networks ICLR 2020***by Saleem*

- Dec 9:

**Adversarial Attack on Graph Structured Data ICML 2018***by Jeff*

**Adversarial Attacks on Neural Networks for Graph Data KDD 2018***by Merwinraj*