Graph Machine Learning research groups: Joan Bruna

I do a series of posts on the groups in graph research, previous post is here. The seventh is Joan Bruna. He was one of the authors of the survey Geometric Deep Learning: going beyond Euclidean Data and now has increasingly more papers on the theoretical explanations of GNN.


Joan Bruna (~1981)
- Affiliation: New York University
- Education: Ph.D. at Ecole Polytechnique, France in 2013 (supervised by Stephane Mallat);
- h-index: 27;
- Awards: NSF career award, Sloan fellowship, ICMLA best paper;
- Interests: GNN theory, equivariant networks

ICML 2020 arxiv links

There is a nice website that gather all (available) links to papers at ICML. There are some interesting insights.
First, it's interesting to see what is the oldest paper that was accepted to ICML this year. Apparently this paper was published on arxiv in Sep 2017, waiting for a little bit less than 3 years to get accepted. There are 8 papers from 2018. And the authors probably started working on these papers 6-9 months before the publication date. It's brutal.
Another interesting observation is that the word graph appeared to be top-5 word among all words in titles, which show increased interest in graphs at ICML.

Fresh picks from ArXiv
This week is rich on explainable GNN literature, as well as papers on compression of graphs, combinatorial optimization and recommendation.

GNN
• Learning to Solve Combinatorial Optimization Problems on Real-World Graphs in Linear Time
• Are Graph Convolutional Networks Fully Exploiting Graph Structure?
• Accurately Solving Physical Systems with Graph Learning
• Single-Layer Graph Convolutional Networks For Recommendation
• XAI for Graphs: Explaining Graph Neural Network Predictions by Identifying Relevant Walks
• XGNN: Towards Model-Level Explanations of Graph Neural Networks
• Universal Graph Compression: Stochastic Block Models
• Convergence and Stability of Graph Convolutional Networks on Large Random Graphs
• Fairness-Aware Explainable Recommendation over Knowledge Graphs

Graph Theory
• Hierarchical hyperbolicity of graph products
• Tree-Projected Gradient Descent for Estimating Gradient-Sparse Parameters on Graphs
• The Weisfeiler-Leman dimension of chordal bipartite graphs without bipartite claw

Conferences
• Multi-level Graph Convolutional Networks for Cross-platform Anchor Link Prediction KDD 20

Surveys
• Generate FAIR Literature Surveys with Scholarly Knowledge Graphs
• A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions

Gradient Boosting Meets Graph Neural Networks for Heterogeneous Data

We have two short paper submissions this year to GRL workshop this year. One of them is about application of gradient boosting decision trees (GBDT) to graphs. We know that Xgboost, LightGBM, and CatBoost perform extremely well on tabular data and are preferred methods for competitions like Kaggle. But how do you generalize it to graph-structured data?

A naïve approach is to train first GBDT on node features only, ignoring graph topology and then use predictions as additional features to your model. But that misses graph information, possibly leading to inaccurate predictions. Instead, we propose to train GBDT and GNN end-to-end such that each tree of GBDT approximates mistakes made by GNN in the forward passes. We call the model Boosted Graph Neural Network and show that it can lead to significant uplift in performance in node regression task, while being very efficient.

Are Hyperbolic Representations in Graphs Created Equal?

The second submission to GRL workshop was on hyperbolic embeddings for graphs. We first make a good introduction to the distances and dot products in k-Stereographic model (a Riemannian manifold with constant curvature) and fix the issue with taking gradients at zero curvature, by taking a Taylor series expansion around the origin. This allows seamless gradient descent optimization in non-Euclidean space.

Then we make experiments on node and graph classification, link prediction, and graph embedding task (i.e. preserving distances in the latent space) and show that for link prediction and graph embedding there is an uplift in using hyperbolic manifolds, while for node and graph classification Euclidean models work better.

ICML 2020 collaboration graph

As a preview to my future post (next week) about ICML 2020, I want to share a collaboration graph between different organizations. Final graph has 429 nodes (organizations) and 1206 edges (collaborations). Each edge has a weight: the number of papers the organizations collaborated with. As the final graph is too big to display nicely, you can also look at the subgraph between organizations that collaborated the most (at least 30 collaborations). I will release a colab notebook so that you can play with it.

Covid Knowledge Graph

A knowledge graph on COVID-19 that integrates various public datasets. This includes relevant publications, case statistics, genes and functions, molecular data and much more. It's implemented in Neo4j and can be accessed via browser.

The ‘Useless’ Perspective That Transformed Mathematics

Matrix algebra is well understood, while group theory, which is used in many proofs of graph theory and other fields, is much more complicated to study. Representation theory creates a bridge between group theory and linear algebra by assigning a matrix to each element in a group, according to certain rules. This nice article introduces to the world of representation theory.

Fresh picks from ArXiv
This week people share their works they submitted to NeurIPS, a lot of interesting papers from the top people in GML.

GNN
• From Graph Low-Rank Global Attention to 2-FWL Approximation with Yaron Lipman
• Graph Meta Learning via Local Subgraphs with Marinka Zitnik
• Data Augmentation for Graph Neural Networks
• Towards Deeper Graph Neural Networks with Differentiable Group Normalization
• Learning Graph Models for Template-Free Retrosynthesis with Regina Barzilay
• Wide and Deep Graph Neural Networks with Distributed Online Learning
• Pointer Graph Networks with Petar Veličković
• Optimal Transport Graph Neural Networks with Octavian-Eugen Ganea, Regina Barzilay, Tommi Jaakkola
• Manifold structure in graph embeddings
• On the Bottleneck of Graph Neural Networks and its Practical Implications

Conferences
• Exploring Algorithmic Fairness in Robust Graph Covering Problems NeurIPS 2019

Surveys
• A Survey on Generative Adversarial Networks: Variants, Applications, and Training

ICML 2020. Comprehensive analysis of authors, organizations, and countries.

Finally here is my post on the analysis of ICML 2020. There are several things I learned from that. For example that USA participates in 3/4 of the papers 😱 Or that DeepMind makes approximately half of all papers for UK. Or that Google does not collaborate with other companies. Or that, except the USA, there is only China that can brag about several companies that publish regularly. Or that a Japanese professor published 12 papers. And much more.

The code and data is on the github, but the cool part is that you can make your own interactive plots in colab notebook (with no installation required) including a collaboration graph between universities and companies.

Deep learning on graphs: successes, challenges, and next steps

The first blog post of Michael Bronstein about graph learning.

Optimal transport: a hidden gem that empowers today’s machine learning

Very simple explanation of what optimal transport problem is and how it can be applied to various domains such as computer vision. Interestingly just yesterday there was a paper on optimal transport GNN.

June Arxiv: how many graphs papers?

From 18 March to 17 April there were 282 new and 98 updated papers in ArXiv CS section. This is 18 papers less that in the previous period.

PhD Theses on Graph Machine Learning

Here are some PhD dissertations on GML. Part 2 (previous here).

Haggai Marron: Deep and Convex Shape Analysis

Benoit Playe: Machine learning approaches for drug virtual screening

Graph Machine Learning research groups: Tommi Jaakkola

I do a series of posts on the groups in graph research, previous post is here. The eighth is Tommi Jaakkola. He has 7 papers in upcoming ICML 2020. His recent interests include molecular graph design and he maintains AI initiative for finding promising antiviral molecules for COVID-19.


Tommi Jaakkola (~1971)
- Affiliation: MIT
- Education: Ph.D. at MIT in 1997 (supervised by Michael Jordan);
- h-index: 76;
- Awards: Sloan research fellowship, AAAI Fellow;
- Interests: molecular generation, models of GNN

DeepSnap

There is a release of DeepSnap by Stanford group. I have not tested it, but it should allow applying graph algorithms from networkx to pytorch-geometric graphs.

Implicit Neural Representations by Yaron Lipman

The talk Implicit Neural Representations by Yaron Lipman from CVPR 20 workshop on Deep Learning Foundations of Geometric Shape.