| Lec. |
Date |
Topic |
Presented papers |
Suggested readings |
| 1 |
Jan. 6 |
Learning on graphs and networks |
|
Hamilton et al (2017)'s "Representation Learning on Graphs: Methods and Applications"
Battaglia et al (2018)'s "Relational inductive biases, deep learning, and graph networks"
|
| 2 |
Jan. 8 |
Graph statistics and kernel methods |
|
Kriege et al (2019)'s "A Survey on Graph Kernels" (especially Sections 3.1, 3.3 and 3.4)
Milo et al (2002)'s "Network motifs: simple building blocks of complex networks"
Watts and Strogatz (1998)'s "Collective Dynamics of Small-World Networks"
Jackson (2008)'s"Social and Economic Networks (Chapter 1)"
|
| 3 |
Jan. 13 |
Neighborhood overlap methods |
|
Lu et al (2010)'s "Link Prediction in Complex Networks: A Survey" (especially Sections 1-3)
|
| 4 |
Jan. 15 |
Graph Laplacians and spectral clustering |
|
von Luxburg (2007)'s "A Tutorial on Spectral Clustering"
|
| 5 |
Jan. 20 |
Node embeddings |
Perozzi et al (2014)'s "DeepWalk: Online Learning of Social Representations" [Presentation Slides]
Qiu et al (2018)'s "Network Embedding as Matrix Factorization"[Presentation Slides]
|
| 6 |
Jan. 22 |
Knowledge graphs (part 1) |
Bordes et al (2013)'s "Translating Embeddings for Modeling Multi-relational Data" [Presentation Slides]
|
|
| 7 |
Jan. 27 |
Knowledge graphs (part 2) |
Trouillon et al (2016)'s "Complex Embeddings for Simple Link Prediction"
Yang et al (2014)'s "Embedding Entities and Relations for Learning and Inference in Knowledge Bases"[Presentation Slides]
Sun et al (2019)'s "RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space"
|
Nickel et al (2015)'s "A Review of Relational Machine Learning
for Knowledge Graphs"
|
| 8 |
Jan. 29 |
Graph neural networks |
Scarselli et al (2008)'s "The Graph Neural Network Model"
Duvenaud et al (2015)'s "Convolutional Networks on Graphs for Learning Molecular Fingerprints"
[Presentation Slides]
|
|
| 9 |
Feb. 3 |
Generalized neighborhood aggregation |
Hamilton et al (2017)'s "Inductive Representation Learning on Large Graphs" [Presentation Slides]
Velickovic et al (2018)'s "Graph Attention Networks"[Presentation Slides]
|
Gilmer et al (2017)'s "Neural Message Passing for Quantum Chemistry"
|
| 10 |
Feb. 5 |
Generalized update methods |
Xu et al (2018)'s "Representation Learning on Graphs with Jumping Knowledge Networks"[Presentation Slides]
Li et al (2016)'s "Gated Graph Sequence Neural Networks"
|
Wu et al (2019)'s "A Comprehensive Survey on Graph Neural Networks"
|
|
Feb. 7 |
Proposals due (5pm) |
Project proposal instructions here
|
|
| 11 |
Feb. 10 |
Multi-relational GNNs |
Schlichtkrull et al (2017)'s "Modeling Relational Data with Graph Convolutional Networks"
Zitnik et al (2018)'s "Modeling Polypharmacy Side-effects with GCNs"
|
|
| 12 |
Feb. 12 |
Graph pooling |
Ying et al (2018)'s "Hierarchical Graph Representation Learning with Differentiable Pooling"
Zaheer et al (2018)'s "Deep Sets"
|
|
| 13 |
Feb. 17 |
Scalable GNNs |
Chen et al (2018)'s "FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling"
Ying et al (2018)'s "Graph Convolutional Neural Networks for Web-Scale Recommender Systems"
|
|
| 14 |
Feb. 19 |
Spectral GNNs (part 1) |
Bruna et al (2014)'s Spectral Networks and Deep Locally Connected Networks on Graphs
|
Ortega et al (2018)'s "Graph Signal Processing: Overview, Challenges and
Applications"
|
| 15 |
Feb. 24 |
Spectral GNNs (part 2) |
Kipf et al (2017)'s "Semi-Supervised Classification with Graph Convolutional Networks"
Defferrard et al (2016)'s "Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering"
|
Bronstein et al (2016)'s "Geometric deep learning: going beyond Euclidean data"
|
| 16 |
Feb. 26 |
Spectral GNNs (part 3) |
Liao et al (2019)'s "LanczosNet: Multi-Scale Deep Graph Convolutional Networks"
Wu et al (2019)'s "Simplifying Graph Convolutional Networks"
Monti et al (2016)'s "Geometric deep learning on graphs and manifolds using mixture model CNN"
|
|
|
Feb. 28 |
Proposal reviews due (11:59pm) |
|
|
|
March 2 |
Study week - no class |
|
|
|
March 4 |
Study week - no class |
|
|
| 17 |
March 9 |
GNNs and graphical models |
Dai et al (2016)'s "Discriminative Embeddings of Latent Variable Models for Structured Data"
Qu et al (2019)'s "GMNN: Graph Markov Neural Networks"
|
|
| 18 |
March 11 |
GNNs and isomorphism (part 1) |
Morris et al (2019)'s "Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks"
Xu et al (2019)'s "How Powerful are Graph Neural Networks?"
|
|
| 19 |
March 16 |
Lecture cancelled |
|
|
| 20 |
March 18 |
Lecture cancelled |
|
|
| 21 |
March 23 |
Lecture cancelled |
|
|
| 22 |
March 25 |
Lecture cancelled |
|
|
| 23 |
March 30 |
GNNs and isomorphism (part 2) |
|
|
| 24 |
April 1 |
Graph generation (part 1) |
|
|
|
April 3 |
Relevant research presentations
Recordings must be submitted via email by April 2nd at 11:59pm
|
Murphy et al (2019)'s "Relational Pooling for Graph Representations"
Maron et al (2019)'s "Provably Powerful Graph Networks"
Kipf et al (2016)'s "Variational Graph Auto-Encoders"
Grover et al (2019)'s "Graphite: Iterative Generative Modeling of Graphs"
Simonovsky et al (2019)'s "GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders"
De Cao et al (2018)'s "MolGAN: An implicit generative model for small molecular graphs"
|
|
| 25 |
April 6 |
Applications: COVID-19 |
Slides
|
|
| 26 |
April 8 |
Graph generation (part 2) |
|
|
|
April 10 |
Relevant research presentations
Recordings must be submitted via email by April 9th at 11:59pm
|
You et al (2018)'s "GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models"
Liao et al (2019)'s "Efficient Graph Generation with Graph Recurrent Attention Networks"
Jin et al (2018)'s "Junction Tree Variational Autoencoder for Molecular Graph Generation"
You et al (2019)'s "Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation"
Qui et al (2019)'s "Constrained Graph Variational Autoencoders for Molecule Design"
Marcheggiani et al (2017)'s "Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling"
Beck et al (2018)'s "Graph-to-Sequence Learning using Gated Graph Neural Networks"
Dai et al (2017)'s "Learning Combinatorial Optimization Algorithms over Graphs"
Li et al (2019)'s "Graph Matching Networks for Learning the Similarity of Graph Structured Objects"
Velickovic et al (2019)'s "Deep Graph Infomax"
Sanchez-Gonzalez et al (2019)'s "Graph networks as learnable physics engines for inference and control"
Zambaldi et al (2019)'s "Deep reinforcement learning with relational inductive biases"
|
|
|
April 14 |
Final papers due (11:59pm) |
Final project submission instructions here
|
|