Instructor | Feng Chen |
Office | ECSS 3.901 |
Number | (518) 442-4270 |
feng.chen@utdallas.edu | |
Office Hour |
Tuesdays 1:00PM to 2:00PM; Fridays 8:45AM to 9:45AM
|
TA | Yi-Hui Lee |
Office | |
Number | |
Yi-Hui.Lee@UTDallas.edu | |
Office Hour |
Class Time and Location | Fr 10:00AM-12:45PM, JO 3.516 |
Course Description:
This seminar course introduces advanced machine learning and deep learning techniques for detecting and forecasting patterns in complex networks. Examples of applications include disease outbreak detection using public health data, such as hospital visits and medication sales; detection and prediction of cyber attacks (e.g., spammers, fake users, and compromised normal users) using from social networks and financial data, discovery of anomalous or novel patterns from knowledge graph data, and crowdsourcing human mobility and social media data to detect traffic congestion, air pollution, and power leakage.
In this course, I will lead the students in reading and discussion of a collection of machine learning and data mining papers related to graph mining and deep learning (e.g., deep reinforcement learning, graph neural networks, few-short learning, and meta-learning) that I have carefully selected. My goal is to help the students fully understand the papers and learn advanced machine learning techniques that will be helpful to their research.
Starting from Mar. 30th, we will go online. A web conferencing tool called Blackboard Collaborate has been made available in your eLearning section. The tool is located in the left-hand side course menu.
Course Description:
Topic | Paper # | Paper Title | Reading Materials | Presenters |
Graph Neural Networks | 1 | Kipf, Thomas N., and Max Welling. "Semi-supervised classification with graph convolutional networks." ICLR, 2019. (2407 citations) |
|
Jincheng Li |
Graph Neural Networks | 2 | Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., & Bengio, Y. (2017). Graph attention networks. arXiv preprint arXiv:1710.10903.. (829 citations) | Haoliang Wang | |
Graph Neural Networks | 3 | Knyazev, Boris, Graham W. Taylor, and Mohamed Amer. "Understanding Attention and Generalization in Graph Neural Networks." Advances in Neural Information Processing Systems. 2019. | Saloni Agarwal, Diksha Godbole | |
Meta Learning | 4 | Finn, Chelsea, Pieter Abbeel, and Sergey Levine. "Model-agnostic meta-learning for fast adaptation of deep networks." Proceedings of the 34th International Conference on Machine Learning-Volume 70. JMLR. org, 2017. (1248 citations) | Junfeng Guo, Yibo Hu | |
Few-Shot Learning, Graph Neural Networks | 5 | Victor Garcia Satorras, Joan Bruna Estrach: Few-Shot Learning with Graph Neural Networks. ICLR (Poster) 2018 | Harsha Kokel, Zelun Kong | |
Meta Learning, Graph Neural Networks, Adversarial Attacks | 6 | Adversarial Attacks on Graph Neural Networks via Meta Learning | Shuo Li, Changbin Li | |
Meta Learning, Causual Learning | 7 | A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms | Yuzhe Ou, Omer Ozarslan | |
Meta Learning, | 8 | Shahab Shams, Guihong Wan | ||
9 | Zhuoyi Wang, Chengen Wang | |||
10 | ||||
11 | Wu Hao, Kairui Xu | |||
12 | Qifan Zhang, Zhao Chen | |||
13 | Xujiang Zhao |
Reading Materials:
Tutorial on Fourier Transformation and Wavelet Transformation: Part I Part II Part III Part IV My Notes
Papers related to spectrum-domain graph neural networks
Examinations and Grading:
Course Project Requirement
Policy on Cheating:
Cheating in an exam will result in an E grade for the course. Further, the students involved will be referred to the Dean's o ce for disciplinary action.
Homework problems are meant to be individual exercises; you must do these by yourself. Any of the following actions will be considered as cheating.
Cheating in a homework exercise will result in the following penalty for all the students involved.
Students who cheat in two or more homework assignments will receive an E grade for the course. The names of such students will also be forwarded to the Dean's office for disciplinary action.
For a complete list of UTD policies and procedures, see here.