Description automatically generated

Spring 2021: PHYS 7332 – Network Data Science 2 (Machine Learning with Graphs), CRN 37113


General Information

Time: Tuesdays & Fridays 3:25 – 5:05 PM Eastern

Place: Online via Zoom

Instructor: Tina Eliassi-Rad

Course website on Canvas: https://northeastern.instructure.com/courses/65015

Office hours: Tuesdays 5:05 – 6:00 PM Eastern via Zoom
Also, available by appointment. Email eliassi [at] ccs [dot] neu [dot] edu
to setup appointment; begin the subject line with
[sp21 nets].



This 4-credit graduate-level course covers state-of-the-art research on mining and learning with graphs. Topics include, but are not limited to, vertex classification, graph clustering, link prediction and analysis, graph distances, graph embedding and network representation learning, deep learning on graphs, anomaly detection on graphs, graph summarization, network inference, adversarial learning on networks, and notions of fairness in social networks.



Students are expected to have taken courses on or have knowledge of the following:

o   Calculus and linear algebra

o   Basic statistics, probability, machine learning, or data mining

o   Algorithms and programming skills (e.g., Python, Julia, C, Java, Matlab, or any programming language of their preference)



This course does not have a designated textbook. The readings are assigned in the syllabus (see below).


Here are some textbooks (all optional) on machine learning and data mining:





o   Class presentations (45%)

o   Students team up into groups of three.

o   Each week has an assigned team. That team is responsible for presenting the readings for that week.

o   Besides the readings, each paper is likely to have additional materials on the Web. Examples include supplemental materials, video, code, data, etc. These are helpful for presentations and class projects.

o   During the semester, each team will present three times.

o   Class project (55%)

o   Each team will choose (by Saturday February 13, 2021 at 11:59 PM Eastern) one of the papers in the syllabus to replicate.

o   In addition to replication, each team will propose extension(s) to the chosen paper and implement those extension(s).

o   Each team will write a report (maximum 6 pages) detailing what was learned. Use the ACM formatting guidelines.

o   Reports are due on Saturday April 24, 2021 at 11:59 PM Eastern.


Schedule/Syllabus (Subject to Change)




Jan 19

Tina Eliassi-Rad

Ekta Gujral, Evangelos E. Papalexakis: SMACD: Semi-supervised Multi-Aspect Community Detection. SDM 2018: 702-710

Ekta Gujral, Ravdeep Pasricha, Evangelos E. Papalexakis: Beyond Rank-1: Discovering Rich Community Structure in Multi-Aspect Graphs. WWW 2020: 452-462

Jan 22

Prof. Vagelis Papalexakis
(University of California Riverside)

Jan 26

Team 1

Jan Overgoor, Austin R. Benson, Johan Ugander: Choosing to Grow a Graph: Modeling Network Formation as Discrete Choice. WWW 2019: 1409-1420

Jan Overgoor, George Pakapol Supaniratisai, Johan Ugander: Scaling Choice Models of Relational Social Data. KDD 2020: 1990-1998

Jan 29

Prof. Johan Ugander
(Stanford University)

Feb 2

Team 2

Peter Morales, Rajmonda Sulo Caceres, Tina Eliassi-Rad: Selective Network Discovery via Deep Reinforcement Learning on Embedded Spaces. CoRR abs/1909.07294v2 (2020)

Feb 5

Dr. Rajmonda Caceres
(MIT Lincoln Laboratory)

Feb 9

Team 3

José Bento, Stratis Ioannidis: A Family of Tractable Graph Metrics. Appl. Netw. Sci. 4(1): 107:1-107:27 (2019)

Armin Moharrer, Jasmin Gao, Shikun Wang, José Bento, Stratis Ioannidis: Massively Distributed Graph Distances. IEEE Trans. Signal Inf. Process. over Networks 6: 667-683 (2020)

Feb 12

Prof. Stratis Ioannidis
(Northeastern University)

Feb 16

Team 4

Jiong Zhu, Yujun Yan, Lingxiao Zhao, Mark Heimann, Leman Akoglu, Danai Koutra: Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs. NeurIPS 2020

Jiong Zhu, Ryan A. Rossi, Anup B. Rao, Tung Mai, Nedim Lipka, Nesreen K. Ahmed, Danai Koutra: Graph Neural Networks with Heterophily. CoRR abs/2009.13566 (2020)

Feb 19

Prof. Danai Koutra
(University of Michigan)

Feb 23

Team 5

Yao Ma, Xiaorui Liu, Tong Zhao, Yozen Liu, Jiliang Tang, Neil Shah: A Unified View on Graph Neural Networks as Graph Signal Denoising. CoRR abs/2010.01777 (2020)

Yao Ma, Suhang Wang, Charu C. Aggarwal, Jiliang Tang: Graph Convolutional Networks with EigenPooling. KDD 2019: 723-731

Feb 26

Prof. Jiliang Tang
(Michigan State University)

Mar 2

Team 1

Emily Alsentzer, Samuel G. Finlayson, Michelle M. Li, Marinka Zitnik: Subgraph Neural Networks. NeurIPS 2020

Kexin Huang, Marinka Zitnik: Graph Meta Learning via Local Subgraphs. NeurIPS 2020

Mar 5

Prof. Marinka Zitnik
(Harvard University)

Mar 9

Team 2

Junteng Jia, Austin R. Benson: Residual Correlation in Graph Neural Network Regression. KDD 2020: 588-598

Qian Huang, Horace He, Abhay Singh, Ser-Nam Lim, Austin R. Benson: Combining Label Propagation and Simple Models Out-performs Graph Neural Networks. CoRR abs/2010.13993 (2020)

Mar 12

Prof. Austin Benson
(Cornell University)

Mar 16

Team 3

Antonis Matakos, Evimaria Terzi, Panayiotis Tsaparas: Measuring and Moderating Opinion Polarization in Social Networks. Data Min. Knowl. Discov. 31(5): 1480-1505 (2017)

Mar 19

Prof. Evimaria Terzi
(Boston University)

Mar 23

Team 4

Jian Kang, Jingrui He, Ross Maciejewski, Hanghang Tong: InFoRM: Individual Fairness on Graph Mining. KDD 2020: 379-389

Mar 26

Prof. Hanghang Tong
(University of Illinois at Urbana-Champaign)

Mar 30

Teams 5 & 1

Petar Velickovic, Lars Buesing, Matthew C. Overlan, Razvan Pascanu, Oriol Vinyals, Charles Blundell: Pointer Graph Networks. NeurIPS 2020

Gabriele Corso, Luca Cavalleri, Dominique Beaini, Pietro Liò, Petar Velickovic: Principal Neighbourhood Aggregation for Graph Nets. NeurIPS 2020

[optional] Andreea Deac, Petar Velickovic, Ognjen Milinkovic, Pierre-Luc Bacon, Jian Tang, Mladen Nikolic: XLVIN: eXecuted Latent Value Iteration Nets. CoRR abs/2010.13146 (2020)

Apr 2

Dr. Petar Veličković


Apr 6

Team 2

Lingxiao Zhao, Leman Akoglu: On Using Classification Datasets to Evaluate Graph Outlier Detection: Peculiar Observations and New Insights. CoRR abs/2012.12931 (2020)

Apr 9

Prof. Leman Akoglu
(Carnegie Mellon University)

Apr 13

Teams 3 & 4

Johannes Klicpera, Aleksandar Bojchevski, Stephan Günnemann: Predict then Propagate: Graph Neural Networks meet Personalized PageRank. ICLR 2019

Aleksandar Bojchevski, Johannes Klicpera, Bryan Perozzi, Amol Kapoor, Martin Blais, Benedek Rózemberczki, Michal Lukasik, Stephan Günnemann: Scaling Graph Neural Networks with Approximate PageRank. KDD 2020: 2464-2473.

Apr 16

Prof. Stephan Günnemann
(Technical University of Munich)

Apr 20

Team 5

To be determined

Apr 23

Prof. B. Aditya Prakash
(Georgia Institute of Technology)


Notes, Policies, and Guidelines

o   You are expected to have read the assigned material before each lecture.

o   We will use Northeastern’s Canvas for announcements, assignments, and your contributions.

o   When emailing me, begin the subject line with [sp21 nets].

o   For your class project, you can use whatever programming language that you like.

o   Refresh your knowledge of the university's academic integrity policy and plagiarism. There is zero-tolerance for cheating!