Syllabus and Textbooks
The required reading will be mainly from select journal/conference articles (listed below for each lecture), which are all available online. The following books are recommended as well:
[GRL] Graph Representation Learning
William L. Hamilton
[NCM] Networks, Crowds, and Markets: Reasoning About a Highly Connected World
David Easley and Jon Kleinberg
Syllabus
GRL and NCM indicate the above texts. Slides, lecture ntoes and other materials will be available on Blackboard.
| W01: Sep 2 | Introduction | Lecture 0,1,2 |
| Ch.01 Introduction [GRL] Ch.02 Graphs [NCM] | ||
| W02: Sep 9 | Graph Basics | |
| Ch.03 Strong and Weak Ties [NCM] Ch.22 Elementary Graph Algorithms [CLRS] Ch.24 Single Source Shortest Paths [CLRS] | ||
| W03: Sep 16 | Graph Properties and Features 1 | |
| Ch.13 The Structure of the Web [NCM] Global connectivity and multilinguals in the Twitter network. Hale, S.A. SIGCHI’14 Fragile online relationship: a first look at unfollow dynamics in twitter. Kwak, H., et al. SIGCHI’11. What is Twitter, a social network or a news media? Kwak, H., et al. WWW’10.  Tutorial: Crawling data from large scale networks. | ||
| W04: Sep 23 | Graph Properties and Features 2 | |
| Ch.02 Background and Traditional Approaches [GRL] Searching for superspreaders of information in real-world social media. Pei, S., et al. Scientific reports’14. Structure and tie strengths in mobile communication networks. Onnela, J.P., et al. PNAS’07. Graph structure in the web. Broder, A., et al. Computer networks’00. | ||
| W05: Sep 30 | Node Embeddings 1 | |
| Ch.03 Neighborhood Reconstruction Method [GRL] Retrofitting word vectors to semantic lexicons. Faruqui, M., et al. NAACL’15. Glove: global vectors for word representation. Pennington, J., et al. EMNLP’14. Distributed representations of words and phrases and their compositionality. Mikolov, T., et al. NIPS’13. Tutorial: Distributional semantics. | ||
| W06: Oct 7 | Node Embeddings 2 | |
| Ch.03 Neighborhood Reconstruction Method [GRL] Node2vec: scalable feature learning for networks. Grover, A. and Leskovec, J. SIGKDD’16. Deepwalk: online learning of social representations. Perozzi, B., et al. SIGKDD’14.  Course Lecture: Graph Representation Learning. Leskovec J. 2019. AI2 talk: Beyond the Distributional Hypothesis: Learning Better Word Representations. Manaal F. 2016. | ||
| W07: Oct 14 | Graph Neural Networks | |
| Ch.05 The Graph Neural Network Model [GRL] Random walk graph neural networks. Giannis, N. et al. NeurIPS’20 Strategies for pre-training graph neural networks. Hu, Weihua, et al. ICLR’20. Inductive representation learning on large graphs. Hamilton, W., et al. NIPS’17. Semi-supervised classification with graph convolutional networks. Kipf, T.N., et al. ICLR’17. Learning convolutional neural networks for graphs. Niepert, M., et al. ICML’16. Tutorial: GraphSAGE. | ||
| W08: Oct 21 | Exam! | |
| Open book exam | ||
| W09: Oct 28 | Link Prediction | |
| Ch.05 Positive and Negative Relationships [NCM] How to hide one's relationships from link prediction algorithms. Waniek, M., et al. Scientific reports’19. Modeling polypharmacy side effects with GNNs. Zitnik, M., et al. Bioinformatics’18. Exploiting social network structure for person-to-person sentiment analysis. Robert, et al. TACL’14. Predicting positive and negative links in online social networks. Leskovec, J. et al. WWW’10. Tutorial: Link prediction. | ||
| W10: Nov 4 | Cascade Prediction | |
| Ch.16 Information Cascades [NCM] Ch.19 Cascading Behavior in Networks [NCM] Multi-winner contests for strategic diffusion in social networks. Shen, W., et al. AAAI’19. Do cascades recur? Cheng, J., et al. WWW’16. Emerging topic detection for organizations from microblogs. Chen, Y., et al. SIGIR’13. The anatomy of large facebook cascades. Alex, D., et al. ICWSM’13. Lecture: Information diffusion on Twitter. Nikolov, S. 2012. TED talk: How to start a movement. Sivers, D. 2010. | ||
| W11: Nov 11 | no class! | |
| Veteran's Day (university closed) | ||
| W12: Nov 18 | Power Laws and Popularity | |
| Ch.18 Power Laws and Rich-Get-Richer Phenomena [NCM] Ch.14 Link Analysis and Web search [NCM] The anatomy of the facebook social graph. Ugander, J., et al. arXiv’11. Inequality and unpredictability in an artificial cultural market. Salganik, M.J., et al. Science’06. The small world problem . Milgram S. Psychology Today’1967. Documentary: Connected: the power of six degrees. A documentary on networks, social and otherwise. 2008. | ||
| W13: Nov 25 | no class | |
| Thanksgiving Recess | ||
| W14: Dec 2 | Meta Learning with Graphs | |
| CurGraph: curriculum learning for graph classification. Wang, Yiwei, et al. WWW’21. Curriculum learning by dynamic instance hardness. Zhou, T., et al. NeurIPS’20. SuperLoss: a generic loss for robust curriculum learning. Castells, et al. NeurIPS’20. Multi-Modal curriculum learning over graphs. Chen, G., et al. TIST’19Neural self-training through spaced repetition. Amiri H. NAACL’19. Mentornet: Learning data-driven curriculum for very DNNs on corrupted labels. Lu, J., et al. ICML’18. Spaced repetition for efficient and effective training of neural networks. Amiri H., et al. EMNLP’17. Self-paced curriculum learning. Lu, J., et al. AAAI’15. Curriculum learning. Yoshua, B. et al. ICML’09. Tutorial: Leitner system. | ||
| W15: Dec 9 | Project presentations | |
| Project presentations. |