(original) (raw)

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

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

Instructor: Tina Eliassi-Rad<o:p>

Course website on Canvas: https://northeastern.instructure.com/courses/158581 <o:p>

Office hours: Available by appointment. Email eliassi [at] ccs [dot] neu [dot] edu
to setup an appointment; begin the subject line with [fa23 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 [fa23 nets].<o:p>

Date<o:p>

Lecturer<o:p>

Readings<o:p>

Fri Sep 8

Tina Eliassi-Rad

Overview<o:p>

Tue Sep 12

Tina Eliassi-Rad

Various Representations<o:p>

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

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

Fri Sep 15

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

Tue Sep 19

Ayan Chatterjee

Graph Machine Learning for Drug Discovery + Graph Machine Learning Benchmarks<o:p>

<![if !supportLists]>�      <![endif]>AI-Bind: Improving Binding Predictions for Novel Protein Targets and Ligands<o:p>

<![if !supportLists]>�      <![endif]>Disentangling Node Attributes from Graph Topology for Improved Generalizability in Link Prediction<o:p>

<![if !supportLists]>�      <![endif]>OGB: Open Graph Benchmark<o:p>

<![if !supportLists]>�      <![endif]>DGL: Deep Graph Library<o:p>

<![if !supportLists]>�      <![endif]>TGB: Temporal Graph Benchmark<o:p>

<![if !supportLists]>�      <![endif]>GraphWorld

Fri Sep 22

Brennan Klein

Network Comparison and Graph Distances<o:p>

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

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

Tue Sep 26

David Liu

Node Embedding<o:p>

<![if !supportLists]>�      <![endif]>STABLE: Identifying and Mitigating Instability in Embeddings of the Degenerate Core<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]>Machine Learning on Graphs: A Model and Comprehensive Taxonomy

Fri Sep 29

Team 1

Alyssa Smith & Mel Allen & Remy LeWinter

More on Representation Learning<o:p>

<![if !supportLists]>�      <![endif]>Deep Graph Infomax<o:p>

<![if !supportLists]>�      <![endif]>Graph Representation Learning via Graphical Mutual Information Maximization<o:p>

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

Tue Oct 3

Team 2

Joey Ehlert & Mortiz Laber & Sam Dies

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

Fri Oct 6

Team 3

Julian Gullett & Sagar Kumar & Yixuan Liu

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

Tue Oct 10

Team 1

Alyssa Smith & Mel Allen & Remy LeWinter

Graph Neural Networks<o:p>

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

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

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

Fri Oct 13

Team 2

Joey Ehlert & Mortiz Laber & Sam Dies

This and That (I)<o:p>

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

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

Tue Oct 17

Tina Eliassi-Rad

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]>[optional] Message passing all the way up

Fri Oct 20

Team 3

Julian Gullett & Sagar Kumar & Yixuan Liu

ML on Heterogeneous Graphs<o:p>

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

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

Tue Oct 24

Team 1

Alyssa Smith & Mel Allen & Remy LeWinter

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]>[optional] Theory of Graph Neural Networks: Representation and Learning

Fri Oct 27

Team 2

Joey Ehlert & Mortiz Laber & Sam Dies

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?

Tue Oct 31

Team 3

Julian Gullett & Sagar Kumar & Yixuan Liu

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

Fri Nov 3

Team 1

Alyssa Smith & Mel Allen & Remy LeWinter

Ayan Chatterjee will emcee this lecture. <o:p>

Hypergraphs<o:p>

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

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

Tue Nov 7

Team 2

Joey Ehlert & Mortiz Laber & Sam Dies

David Liu will emcee this lecture.<o:p>

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

Fri Nov 10

Team 3

Julian Gullett & Sagar Kumar & Yixuan Liu

Explainability & 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

Tue Nov 14

Team 1

Alyssa Smith & Mel Allen & Remy LeWinter

This and That (II)<o:p>

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

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

Fri Nov 17

Team 2

Joey Ehlert & Mortiz Laber & Sam Dies

Oversmooting<o:p>

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

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

Tue Nov 21

Team 3

Julian Gullett & Sagar Kumar & Yixuan Liu

Fairness & 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

Fri Nov 24

No class  Thanksgiving break

Tue Nov 28

Team 1

Alyssa Smith & Mel Allen & Remy LeWinter

Learning on Signed Networks<o:p>

<![if !supportLists]>�      <![endif]>Learning Signed Network Embedding via Graph Attention<o:p>

<![if !supportLists]>�      <![endif]>Signed Graph Attention Networks

Fri Dec 1

Team 2

Joey Ehlert & Mortiz Laber & Sam Dies

Invariance and Equivariance<o:p>

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

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

Tue Dec 5

Team 3

Julian Gullett & Sagar Kumar & Yixuan Liu

*-aware GNNs<o:p>

<![if !supportLists]>�      <![endif]>Position-aware Graph Neural Networks<o:p>

<![if !supportLists]>�      <![endif]>Identity-aware Graph Neural Networks

Fri Dec 8

No class  Project reports are due on Sat Dec 9 at 11:59pm Eastern.

This and That (III)<o:p>

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

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

Tue Dec 12

No class  NetSI Qualifying Exam Week

Fri Dec 15

In-class project presentations

Your slides are due at 12pm Eastern.