(original) (raw)

Time: Tuesdays & Fridays 1:35  3:15 PM Eastern<o:p>

Place: 177 Huntington Ave, 2^nd Floor Conference Room (#207)<o:p>

Instructor: Tina Eliassi-Rad<o:p>

Course website on Canvas: https://northeastern.instructure.com/courses/194307� <o:p>

Office hours: Available by appointment. Email eliassi [at] ccs [dot] neu [dot] edu
to setup an appointment; begin the subject line with [fa24 nets].<o:p>

TA: Ayan Chatterjee. Available by appointment. Email chatterjee [dot] ay [at]
northeastern [dot] edu to setup an appointment; begin the subject line with [fa24 nets].<o:p>

Date<o:p>

Lecturer<o:p>

Readings<o:p>

Fri Sep 6

Tina Eliassi-Rad

Overview<o:p>

<![if !supportLists]>�      <![endif]>The Why, How, and When of Representations for Complex Systems<o:p>

Tue Sep 10

Tina Eliassi-Rad

Homophily<o:p>

<![if !supportLists]>�      <![endif]>Distribution of Node Characteristics in Complex Networks<o:p>

<![if !supportLists]>�      <![endif]>Combinatorial Characterizations and Impossibilities for Higher-order Homophily<o:p>

<![if !supportLists]>�      <![endif]>Higher-order Homophily on Simplicial Complexes<o:p>

Axiomatic Approaches<o:p>

<![if !supportLists]>�      <![endif]>Measuring Tie Strength in Implicit Social Networks <o:p>

Fri Sep 13

Tina Eliassi-Rad

Network Comparison and Graph Distances<o:p>

<![if !supportLists]>�      <![endif]>A Guide to Selecting a Network Similarity Method <o:p>

<![if !supportLists]>�      <![endif]>Network Comparison and the Within-ensemble Graph Distance<o:p>

<![if !supportLists]>�      <![endif]>Non-backtracking Cycles: Length Spectrum Theory and Graph Mining Applications<o:p>

<![if !supportLists]>�      <![endif]>[reference] netrd: A library for Network Reconstruction and Graph Distances<o:p>

Tue Sep 17

Tina Eliassi-Rad

Role Discovery<o:p>

<![if !supportLists]>�      <![endif]>It's Who You Know: Graph Mining Using Recursive Structural Features<o:p>

<![if !supportLists]>�      <![endif]>RolX: Structural Role Extraction & Mining in Large Graphs<o:p>

<![if !supportLists]>�      <![endif]>Guided learning for Role Discovery (GLRD): Framework, Algorithms, and Applications<o:p>

Fri Sep 20

Tina Eliassi-Rad

Graph Representation Learning: Node Embedding<o:p>

<![if !supportLists]>�      <![endif]>Laplacian Eigenmaps for Dimensionality Reduction and Data Representation<o:p>

<![if !supportLists]>�      <![endif]>node2vec: Scalable Feature Learning for Networks<o:p>

<![if !supportLists]>�      <![endif]>Structural Deep Network Embedding<o:p>

<![if !supportLists]>�      <![endif]>STABLE: Identifying and Mitigating Instability in Embeddings of the Degenerate Core<o:p>

<![if !supportLists]>�      <![endif]>[reference] Machine Learning on Graphs: A Model and Comprehensive Taxonomy<o:p>

<![if !supportLists]>�      <![endif]>[reference] Network Representation Learning: From Preprocessing, Feature Extraction to Node Embedding<o:p>

<![if !supportLists]>�      <![endif]>[optional] Next Waves in Veridical Network Embedding <o:p>

Tue Sep 24

Team 1: Sharaj Kunjar, Tamanna Urmi, Xiyu Yang

Low-rank Representations of Complex Networks<o:p>

<![if !supportLists]>�      <![endif]>The Impossibility of Low-rank Representations for Triangle-Rich Complex Networks<o:p>

<![if !supportLists]>�      <![endif]>Node Embeddings and Exact Low-rank Representations of Complex Networks<o:p>

<![if !supportLists]>�      <![endif]>[optional] Classic Graph Structural Features Outperform Factorization-Based Graph Embedding Methods on Community Labeling<o:p>

<![if !supportLists]>�      <![endif]>[optional] Link Prediction Using Low-dimensional Node Embeddings: The Measurement Problem<o:p>

Fri Sep 27

Team 2: Amanuel Tesfaye, Narayan Sabhahit, Yiyuan Zhang

Graph Neural Networks<o:p>

<![if !supportLists]>�      <![endif]>Semi-Supervised Classification with Graph Convolutional Networks<o:p>

<![if !supportLists]>�      <![endif]>Graph Attention Networks<o:p>

<![if !supportLists]>�      <![endif]>Gated Graph Sequence Neural Networks<o:p>

<![if !supportLists]>�      <![endif]>[reference] Graph Neural Networks: A Review of Methods and Applications<o:p>

<![if !supportLists]>�      <![endif]>[reference] A Comprehensive Survey on Graph Neural Networks<o:p>

<![if !supportLists]>�      <![endif]>[optional] Everything is Connected: Graph Neural Networks<o:p>

Tue Oct 1

Team 3: Jesseba Fernando, Joshua  Josh Rosen, Yicheng  Andy Zhang

This and That<o:p>

<![if !supportLists]>�      <![endif]>Hyperbolic Graph Convolutional Neural Networks<o:p>

<![if !supportLists]>�      <![endif]>Principal Neighbourhood Aggregation for Graph Nets<o:p>

<![if !supportLists]>�      <![endif]>Pitfalls of Graph Neural Network Evaluation<o:p>

<![if !supportLists]>�      <![endif]>[optional] The Numerical Stability of Hyperbolic Representation Learning<o:p>

Fri Oct 4

Team 1: Sharaj Kunjar, Tamanna Urmi, Xiyu Yang

Collective Classification<o:p>

<![if !supportLists]>�      <![endif]>Collective Classification in Network Data<o:p>

<![if !supportLists]>�      <![endif]>Graph Belief Propagation Networks<o:p>

<![if !supportLists]>�      <![endif]>[optional] Cautious Collective Classification<o:p>

Tue Oct 8

Team 2: Amanuel Tesfaye, Narayan Sabhahit, Yiyuan Zhang

Label Propagation on Graphs<o:p>

<![if !supportLists]>�      <![endif]>Combining Label Propagation and Simple Models Out-performs Graph Neural Networks<o:p>

<![if !supportLists]>�      <![endif]>Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification<o:p>

<![if !supportLists]>�      <![endif]>Design Space for Graph Neural Networks (GitHub page)<o:p>

<![if !supportLists]>�      <![endif]>[optional] Message passing all the way up<o:p>

Class project proposals are due at 11:59 PM Eastern.

Fri Oct 11

Team 3: Jesseba Fernando, Joshua  Josh Rosen, Yicheng  Andy Zhang

Graph Transformers<o:p>

<![if !supportLists]>�      <![endif]>Graph Transformer Networks<o:p>

<![if !supportLists]>�      <![endif]>A Generalization of Transformer Networks to Graphs<o:p>

<![if !supportLists]>�      <![endif]>Transformers are Graph Neural Networks<o:p>

<![if !supportLists]>�      <![endif]>[reference] Graph Transformers: A Survey<o:p>

Tue Oct 15

Team 1: Sharaj Kunjar, Tamanna Urmi, Xiyu Yang

ML on Heterogeneous Graphs<o:p>

<![if !supportLists]>�      <![endif]>Modeling Relational Data with Graph Convolutional Networks<o:p>

<![if !supportLists]>�      <![endif]>Heterogeneous Graph Transformer<o:p>

Fri Oct 18

Team 2:Amanuel Tesfaye, Narayan Sabhahit, Yiyuan Zhang

GNNs for Recommendation Systems<o:p>

<![if !supportLists]>�      <![endif]>Neural Graph Collaborative Filtering<o:p>

<![if !supportLists]>�      <![endif]>Graph Convolutional Neural Networks for Web-Scale Recommender Systems<o:p>

Tue Oct 22

Team 3: Jesseba Fernando, Joshua  Josh Rosen, Yicheng  Andy Zhang

W-L Graph Kernels and Power of GNNs<o:p>

<![if !supportLists]>�      <![endif]>Weisfeiler-Lehman Graph Kernels<o:p>

<![if !supportLists]>�      <![endif]>How Powerful are Graph Neural Networks?<o:p>

<![if !supportLists]>�      <![endif]>[optional] A Reduction of a Graph to a Canonical Form and an Algebra arising during this Reduction<o:p>

<![if !supportLists]>�      <![endif]>[reference] Theory of Graph Neural Networks: Representation and Learning<o:p>

Fri Oct 25

Team 1: Sharaj Kunjar, Tamanna Urmi, Xiyu Yang

Stability and Counting in GNNs<o:p>

<![if !supportLists]>�      <![endif]>Tree Mover s Distance: Bridging Graph Metrics and Stability of Graph Neural Networks<o:p>

<![if !supportLists]>�      <![endif]>Can Graph Neural Networks Count Substructures?<o:p>

Tue Oct 29

Team 2: Amanuel Tesfaye, Narayan Sabhahit, Yiyuan Zhang

Invariance and Equivariance

<![if !supportLists]>�      <![endif]>E(n) Equivariant Graph Neural Networks<o:p>

<![if !supportLists]>�      <![endif]>Invariant and Equivariant Graph Networks<o:p>

Fri Nov 1

Team 3: Jesseba Fernando, Joshua  Josh Rosen, Yicheng  Andy Zhang

Hypergraphs and Higher-order Models<o:p>

<![if !supportLists]>�      <![endif]>Random Walks on Hypergraphs with Edge-Dependent Vertex Weights <o:p>

<![if !supportLists]>�      <![endif]>Hypergraph Neural Networks<o:p>

<![if !supportLists]>�      <![endif]>[reference] A Survey on Hypergraph Mining: Patterns, Tools, and Generators<o:p>

<![if !supportLists]>�      <![endif]>[optional] Simplicial Attention Networks<o:p>

Tue Nov 5

Team 1: Sharaj Kunjar, Tamanna Urmi, Xiyu Yang

Graph ML for Optimization<o:p>

<![if !supportLists]>�      <![endif]>Assigning Entities to Teams as a Hypergraph Discovery Problem<o:p>

<![if !supportLists]>�      <![endif]>Distributed constrained combinatorial optimization leveraging hypergraph neural networks<o:p>

Fri Nov 8<o:p>

Guest Lecturer:
Alesia Chernikova<o:p>

Cyber networks and ML<o:p>

<![if !supportLists]>�      <![endif]>Cyber Network Resilience against Self-Propagating Malware Attacks<o:p>

<![if !supportLists]>�      <![endif]>Modeling Self-Propagating Malware with Epidemiological Models<o:p>

Tue Nov 12

Team 2: Amanuel Tesfaye, Narayan Sabhahit, Yiyuan Zhang

Explainability in GNNs<o:p>

<![if !supportLists]>�      <![endif]>Explainability in Graph Neural Networks: A Taxonomic Survey<o:p>

<![if !supportLists]>�      <![endif]>GNNExplainer: Generating Explanations for Graph Neural Networks<o:p>

Fri Nov 15

Team 3: Jesseba Fernando, Joshua  Josh Rosen, Yicheng  Andy Zhang

Explainability and Trustworthiness of GNNs<o:p>

<![if !supportLists]>�      <![endif]>GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networks<o:p>

<![if !supportLists]>�      <![endif]>Trustworthy Graph Neural Networks: Aspects, Methods and Trends<o:p>

Tue Nov 19

Team 1: Sharaj Kunjar, Tamanna Urmi, Xiyu Yang

Fairness and Equality<o:p>

<![if !supportLists]>�      <![endif]>FAIRGEN: Towards Fair Graph Generation<o:p>

<![if !supportLists]>�      <![endif]>Information Access Equality on Generative Models of Complex Networks<o:p>

Fri Nov 22

Team 2: Amanuel Tesfaye, Narayan Sabhahit, Yiyuan Zhang

Oversmooting and Oversquashing<o:p>

<![if !supportLists]>�      <![endif]>A Survey on Oversmoothing in Graph Neural Networks<o:p>

<![if !supportLists]>�      <![endif]>How does over-squashing affect the power of GNNs?<o:p>

<![if !supportLists]>�      <![endif]>Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs<o:p>

Tue Nov 26

Team 3: Jesseba Fernando, Joshua  Josh Rosen, Yicheng  Andy Zhang

ICML 2024 Position Papers<o:p>

<![if !supportLists]>�      <![endif]>Future Directions in the Theory of Graph Machine Learning<o:p>

<![if !supportLists]>�      <![endif]>Why We Must Rethink Empirical Research in Machine Learning <o:p>

Fri Nov 29

No class  Thanksgiving break

Tue Dec 3<o:p>

Guest lecturer:
Germans Savcisens<o:p>

ML for Computational Social Science<o:p>

<![if !supportLists]>�      <![endif]>Using Sequences of Life-events to Predict Human Lives
(Website: https://www.life2vec.dk)<o:p>

Fri Dec 6

In-class project presentations

Your slides are due at 12pm Eastern.

Tue Dec 10

No class  Project reports are due on Tue Dec 10 at 11:59pm Eastern.

Fri Dec 13

No class