Fall 2026: Machine Learning with Graphs – CS 7332 (NU Course Info) & NETS 7332 (NU Course Info)

 

General Information

Time: Mondays & Wednesdays 2:50 – 4:30 PM Eastern	Place: 101 Belvidere Street, 3rd Floor, Rooms 140 A & B. (directions)
Instructor: Tina Eliassi-Rad Course website on Canvas: https://northeastern.instructure.com/courses/261008	Office hours: Available by appointment. Email teliassirad [at] ccs [dot] northeastern [dot] edu to setup an appointment; begin the subject line with [fa26 nets]. TA: Samantha “Sam” Dies. Available by appointment. Email dies [dot] s [at] northeastern [dot] edu to setup an appointment; begin the subject line with [fa26 nets].

 

Overview

This 4-credit PhD-level course covers state-of-the-art research on data mining and machine 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, notions of fairness in social networks, and generative AI methods on graphs.

 

Prerequisites

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, C++, Java, Ruby, Matlab, or any programming language of their preference)

 

Textbooks

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:

• Deep Learning and Graph Representation Learning
• Charu C. Aggarwal. Neural Networks and Deep Learning: A Textbook. Springer, 2018.
• Michael Bronstein, Joan Bruna, Taco Cohen and Petar Veličković. Geometric Deep Learning: Grids, Graphs, Groups, Geodesics, and Gauges. arXiv:2104.13478, April 2021.
• Ian Goodfellow, Yoshua Bengio, Aaron Courville. Deep Learning. MIT Press, 2016.
• William L. Hamilton. Graph Representation Learning. Synthesis Lectures on Artificial Intelligence and Machine Learning, Vol. 14, No. 3, Pages 1-159, 2020.
• Jure Leskovec. Machine Learning with Graphs Video Lectures, Stanford Online, 2021.
• Michael M. Bronstein, Joan Bruna, Taco Cohen, Petar Veličković. Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges, 2021.
• Xavier Bresson. Graph Machine Learning, 2022-23.
• Data Mining and Graph Mining
• Charu C. Aggarwal. Data Mining, The Textbook. Springer 2015.
• Christos Faloutsos, Deepayan Chakrabarti. Graph Mining: Laws, Tools, and Case Studies. Morgan & Claypool Publishers, 2012.
• Jiawei Han, Micheline Kamber, Jian Pei. Data Mining: Concepts and Techniques. Morgan Kaufmann, 3rd edition, 2011.
• David J. Hand, Heikki Mannila, Padhraic Smyth. Principles of Data Mining. A Bradford Book, 2001
• Anand Rajaraman, Jurij Leskovec, and Jeffrey Ullman. Mining of Massive Datasets. Cambridge University Press, v2.1, 2014. (free online) (Errata)
• Pang-Ning Tan, Michael Steinbach, Vipin Kumar. Introduction to Data Mining. Pearson, 2nd edition, 2018.
• Machine Learning
• Charu C. Aggarwal. Linear Algebra and Optimization for Machine Learning: A Textbook. Springer, 2020.
• Christopher Bishop. Pattern Recognition and Machine Learning. Springer, 2006.
• Peter Flach. Machine Learning: The Art and Science of Algorithms that Make Sense of Data. Cambridge University Press, 2012.
• Tom Mitchell. Machine Learning. McGraw Hill, 1997.
• Kevin P. Murphy. Machine Learning: A Probabilistic Perspective. MIT Press, 2012.
• Statistics
• Trevor Hastie, Robert Tibshirani, Jerome Friedman. Elements of Statistical Learning. Springer, 2nd edition, 2009. (free online)

 

Resources

• Probability Review (David Blei, Princeton)
• Probability Theory Review (Arian Maleki and Tom Do, Stanford)
• Linear Algebra Review and Reference (Zico Kolter and Chuong Do, Stanford)
• Theoretical CS Cheat Sheet (Princeton)
• Encyclopedia of Distances (Michel Marie Deza and Elena Deza)

 

Grading

o   Class presentations (50%)

o   Each paper will have a lead discussant (LD), an advocate (A), and a critic (C).

Ø  The lead discussant presents the paper (15 minutes with slides) and moderates the discussion.

Ø  The advocate makes the strongest case for the paper (5 minutes with slides): its contributions, what it gets right, and why it matters.

Ø  The critic makes the strongest case against the paper (5 minutes with slides): its methodological weaknesses, unsupported claims, and missed comparisons.

Ø  The advocate and critic should use this slide template. Their slides should include a one-sentence summary; strengths (at least three specific points for A and at least one for C); weaknesses (at least three specific points for C and at least one for A); clarifying questions (at least one specific point you are unsure about); and concrete suggestions (at least once). The advocate and the critic should conclude by stating what would change their assessment.

Ø  Everyone else should come with at least one question or comment.

Ø  I got this idea from Byron Wallace.

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   Slides for class presentations are due at 12:00 PM (noon) Eastern on the day assigned to you.

o   Check the schedule for your presentation date.

o   Class project (50%)

o   Breakdown: proposal (10%), report (25%), slides & in-class presentation (15%)

o   I will team up students into groups.

o   Each team will choose (by Wednesday, October 14, 2026 at 11:59 PM Eastern) one of the papers in the syllabus to reproduce.

o   In addition to the reproduction, 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 style files at https://media.neurips.cc/Conferences/NeurIPS2025/Styles.zip.

o   Reports & slides on class projects are due on Wednesday, December 16, 2026 at 12:00 PM (noon) Eastern.

 

Schedule/Syllabus (Subject to Change)

Date	Lecturer	Readings
Wed Sep 9	Tina Eliassi-Rad	Overview
Mon Sep 14	Tina Eliassi-Rad	Representations of Complex Systems The Why, How, and When of Representations for Complex Systems   [optional] Networks beyond Pairwise Interactions: Structure and Dynamics [optional] The Physics of Higher-order Interactions in Complex Systems
Wed Sep 16	Tina Eliassi-Rad	Homophily Distribution of Node Characteristics in Complex Networks Combinatorial Characterizations and Impossibilities for Higher-order Homophily Higher-order Homophily on Simplicial Complexes   [optional] Information Access Equality on Generative Models of Complex Networks [optional] Effects of Higher-order Interactions and Homophily on Information Access Inequality   Axiomatic Approaches Measuring Tie Strength in Implicit Social Networks
Mon Sep 21	Tina Eliassi-Rad	Network Comparison and Graph Distances A Guide to Selecting a Network Similarity Method  Network Comparison and the Within-ensemble Graph Distance Non-backtracking Cycles: Length Spectrum Theory and Graph Mining Applications   [reference] netrd: A library for Network Reconstruction and Graph Distances [optional] Optimal Transport for Network Comparison: A Review with Machine Learning Applications
Wed Sep 23	Tina Eliassi-Rad	Role Discovery It's Who You Know: Graph Mining Using Recursive Structural Features RolX: Structural Role Extraction & Mining in Large Graphs Guided learning for Role Discovery (GLRD): Framework, Algorithms, and Applications
Mon Sep 28 & Wed Sep 30	Tina Eliassi-Rad	Graph Representation Learning: Node Embedding Laplacian Eigenmaps for Dimensionality Reduction and Data Representation node2vec: Scalable Feature Learning for Networks Structural Deep Network Embedding STABLE: Identifying and Mitigating Instability in Embeddings of the Degenerate Core   [reference] Machine Learning on Graphs: A Model and Comprehensive Taxonomy [reference] Network Representation Learning: From Preprocessing, Feature Extraction to Node Embedding [optional] DeepWalk: Online Learning of Social Representations [optional] Bypassing Skip-Gram Negative Sampling: Dimension Regularization as a More Efficient Alternative for Graph Embeddings [optional] REGE: A Method for Incorporating Uncertainty in Graph Embeddings [optional] Next Waves in Veridical Network Embedding
Mon Oct 5		Low-rank Representations of Complex Networks [paper 1] The Impossibility of Low-rank Representations for Triangle-Rich Complex Networks [paper 2] Node Embeddings and Exact Low-rank Representations of Complex Networks [paper 3] Link Prediction Using Low-dimensional Node Embeddings: The Measurement Problem   [optional] Classic Graph Structural Features Outperform Factorization-Based Graph Embedding Methods on Community Labeling [optional] Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec
Wed Oct 7		Graph Neural Networks I [paper 1] Semi-Supervised Classification with Graph Convolutional Networks [paper 2] Graph Attention Networks [paper 3] Inductive Representation Learning on Large Graphs   [reference] Graph Neural Networks: A Review of Methods and Applications [reference] A Comprehensive Survey on Graph Neural Networks [optional] Everything is Connected: Graph Neural Networks [optional] Geometric Deep Learning: the Erlangen Programme of ML (ICLR 2021 keynote)
Mon Oct 12	No class (US holiday)
Wed Oct 14	Class project proposals are due at 11:59 PM Eastern.	Graph Neural Networks II [paper 1] Hyperbolic Graph Convolutional Neural Networks [paper 2] Pitfalls of Graph Neural Network Evaluation [paper 3] Design Space for Graph Neural Networks (GitHub page)   [optional] The Numerical Stability of Hyperbolic Representation Learning
Mon Oct 19		Graph Neural Networks III & Collective Classification [paper 1] Hierarchical Graph Representation Learning with Differentiable Pooling [paper 2] Collective Classification in Network Data [paper 3] Graph Belief Propagation Networks   [optional] Cautious Collective Classification
Wed Oct 21		Label Propagation on Graphs and Counting [paper 1] Combining Label Propagation and Simple Models Out-performs Graph Neural Networks [paper 2] Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification [paper 3] Can Graph Neural Networks Count Substructures?   [optional] Message passing all the way up
Mon Oct 26		GNNs for Recommendation Systems [paper 1] LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation [paper 2] Neural Graph Collaborative Filtering [paper 3] Graph Convolutional Neural Networks for Web-Scale Recommender Systems   [reference] Graph Neural Networks in Recommender Systems: A Survey [reference] A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions
Wed Oct 28		Hypergraphs and Higher-order Models with applications to Graph ML for Optimization [paper 1] Random Walks on Hypergraphs with Edge-Dependent Vertex Weights [paper 2] Assigning Entities to Teams as a Hypergraph Discovery Problem [paper 3] Distributed constrained combinatorial optimization leveraging hypergraph neural networks   [reference] A Survey on Hypergraph Mining: Patterns, Tools, and Generators [optional] Hypergraph Neural Networks [optional] Simplicial Attention Networks
Mon Nov 2		Oversmooting and Oversquashing [paper 1] A Survey on Oversmoothing in Graph Neural Networks [paper 2] How does over-squashing affect the power of GNNs? [paper 3] Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
Wed Nov 4		W-L Graph Kernels, Power of GNNs, Stability [paper 1] Weisfeiler-Lehman Graph Kernels [paper 2] How Powerful are Graph Neural Networks? [paper 3] Tree Mover’s Distance: Bridging Graph Metrics and Stability of Graph Neural Networks   [optional] A Reduction of a Graph to a Canonical Form and an Algebra arising during this Reduction [reference] Theory of Graph Neural Networks: Representation and Learning
Mon Nov 9		Invariance and Equivariance + 1 [paper 1] E(n) Equivariant Graph Neural Networks [paper 2] Invariant and Equivariant Graph Networks [paper 3] Uncertainty Quantification over Graph with Conformalized Graph Neural Networks
Wed Nov 11	No class (US holiday)
Mon Nov 16		*-aware GNNs + 1 [paper 1] Position-aware Graph Neural Networks [paper 2] Identity-aware Graph Neural Networks [paper 3] PRODIGY: Enabling In-context Learning Over Graphs
Wed Nov 18		Explainability in GNNs [paper 1] GNNExplainer: Generating Explanations for Graph Neural Networks [paper 2] GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networks [paper 3] Trustworthy Graph Neural Networks: Aspects, Methods and Trends   [optional] FAIRGEN: Towards Fair Graph Generation [optional] Explainability in Graph Neural Networks: A Taxonomic Survey
Mon Nov 23		Graph Transformers I [paper 1] Graph Transformer Networks [paper 2] A Generalization of Transformer Networks to Graphs [paper 3] Transformers are Graph Neural Networks   [reference] Graph Transformers: A Survey
Wed Nov 25	No class (US holiday)
Mon Nov 30		Graph Transformers II [paper 1] Do Transformers Really Perform Bad for Graph Representation?  [paper 2] Sign and Basis Invariant Networks for Spectral Graph Representation Learning  [paper 3] Attending to Graph Transformers   [reference] Graph Transformers: A Survey
Wed Dec 2		ML on Heterogeneous Graphs + Deep Generative Models for Graphs [paper 1] Modeling Relational Data with Graph Convolutional Networks [paper 2] Heterogeneous Graph Transformer [paper 3] GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
Mon Dec 7		Relational Deep Learning [paper 1] Relational Deep Learning - Graph Representation Learning on Relational Databases  [paper 2] Relational Graph Transformer [paper 3] RelGNN: Composite Message Passing for Relational Deep Learning   [optional] Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data [reference] RelBench: A Benchmark for Deep Learning on Relational Databases
Wed Dec 9	Moderator: Samantha Dies	Knowledge Graphs [paper 1] Translating Embeddings for Modeling Multi-relational Data [paper 2] Learning Entity and Relation Embeddings for Knowledge Graph Completion [paper 3] Embedding Entities and Relations for Learning and Inference in Knowledge Bases   [optional] Complex Embeddings for Simple Link Prediction  [optional] RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
Mon Dec 14		Recent Position Papers [paper 1] Future Directions in the Theory of Graph Machine Learning [paper 2] Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks [paper 3] Position: Graph Condensation Needs a Reset—Move Beyond Full-dataset Training and Model-Dependence [paper 4] Position: Neural Approximation Is Rarely Justified for Hard Combinatorial Problems [paper 5] Why We Must Rethink Empirical Research in Machine Learning
Wed Dec 16	Presentation of class projects	Reports and slides for class projects are due at 12:00 PM (noon) Eastern.
Tue Dec 22	Faculty Grade Deadline

 

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 [fa26 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!

o   AI Usage Policy: You may use AI tools in any way that supports your learning, with two conditions. (1) For each submission, disclose which tools you used, at what stage, and how much of the output you kept. Disclosure will never affect your grade; failing to disclose is an academic integrity violation. (2) You are responsible for everything you submit. Fabricated citations, incorrect arguments, and broken code are your errors and will be graded as such. You should be able to explain and defend any part of your work without the tool.

Ø  Disclosure: I gave Fable 5.1 my original policy. Fable 5.1 critiqued it and proposed a revised policy. I then edited Fable 5.1’s revised policy to produce this policy.