Book: Probabilistic Machine Learning: An Introduction

In addition to two books dedicated to graph ML that I described in the past, there is a new draft of ML book that includes a chapter on graph embeddings. This describes graph embeddings as a encoder-decoder problem and dives into unsupervised and supervised ways to define encoder/decoder parts. It covers matrix factorization methods, label propagation, GNNs, and applications of embeddings.

Fresh picks from ArXiv
Today at ArXiv: thesis on graph matching, image search with scene graphs, and decentralized agent's control 👮

If I forgot to mention your paper, please shoot me a message and I will update the post.

Conferences
* Image-to-Image Retrieval by Learning Similarity between Scene Graphs AAAI 21
* A Paragraph-level Multi-task Learning Model for Scientific Fact-Verification Workshop AAAI 21

Applications
* Decentralized Control with Graph Neural Networks with Alejandro Ribeiro
* Graph Networks with Spectral Message Passing with Peter Battaglia


Survey
* Some Algorithms on Exact, Approximate and Error-Tolerant Graph Matching
* Algorithms for Learning Graphs in Financial Markets

TRIPODS Winter School & Workshop on Graph Learning and Deep Learning

A series of tutorials and hands-on sessions, followed by a workshop covering recent results on graph ML by top researchers in this field. Starts today, requires registration (probably directly asking organizers).

SuperGlue: Learning Feature Matching with Graph Neural Network

Another cool application of GNNs, done at Magic Leap, which specializes in 3D computer-generated graphics. They use GNN for graph matching in real-time videos, which is used for tasks such as 3D reconstruction, place recognition, localization, and mapping. The architecture called SuperGlue (presented at CVPR 2020) is an attention based model with Sinkhorn algorithm, similar to other graph matching works, but is that has been successfully integrated into much bigger pipeline that extracts graphs from the images in end-to-end fashion.

What 2021 holds for Graph ML?

Great format of mini interviews with researchers in graph ML about what's important in the field. I participated too, speaking on the great applications of GNNs we had in 2020 and what we may see changing in 2021. It's very interesting to hear what others think is important and while there are some common themes (e.g. drug discovery, graph construction, stronger GNNs), the interviewees share their distinct predictions (e.g new specialized hardware, applications to RL, causal reasoning, decision making).

Cleora: new unsupervised graph embedding model for hypergraphs

A new library Cleora, written in Rust (for efficiency), by Synerise, a startup building AI platform, builds graph embeddings in unsupervised, inductive, and scalable manner. The algorithm itself is very simple, PageRank-like, just iterative multiplication of the adjacency matrix. It claims to be ~5x faster than PyTorch-BigGraph (with better performance) and provides some nice features including real-time updates, determinism of embeddings, independence of each dimension, compositionality of embeddings of the same entity on different datasets. They also claim they use it in production, so worth a try if you have a graph with billions of edges.

Post: Knowledge Graph Insights

A series of posts from 2020 by Giuseppe Futia on construction, performance, and applications of knowledge graphs.

Book: The Atlas for the Aspiring Network Scientist

A new introductory book of network science by Michele Coscia. 760 pages covering Hitting Time Matrix, Kronecker graph model, network measurement error, graph embedding techniques, and more. As the author describes he aims it to be broad, not deep, so there is not much math involved.

Graph Machine Learning research groups: Michele Coscia

I do a series of posts on the groups in graph research, previous post is here. The 21st is Michele Coscia, the author of the atlas of the network science.

Michele Coscia (~1985)
- Affiliation: IT University of Copenhagen
- Education: Ph.D. at University of Pisa in 2012 (advisor: Dino Pedreschi)
- h-index 22
- Awards: KDD Dissertation Award, ERCIM Cor Baayen Award
- Interests: homophily, community detection, network science

Survey: Utilising Graph Machine Learning within Drug Discovery and Development

A new survey with Michael Bronstein and his colleagues on application of GNNs to drug discovery. This is very exciting line of research and I bet there will be much more effort in 2021 not only from the academia but also from the startups and big pharmacies. In this domain graphs appear as a natural structure to model relationships in molecules or more complex bio entities, for examples protein to protein interactions. There are also many valuable tasks such as target identification, molecule property prediction, de-novo drug design and more. Relation Therapeutics, a London-based startup that also participates in writing this survey, even has an opening for Graph ML researcher.

Video: Grandmaster Series – How to Predict Which Candidate COVID-19 mRNA Vaccines Are Stable with AI

Live now from the Kaggle grandmasters, discussing top-performing machine learning model for the COVID-19 Vaccine Degradation Prediction Kaggle competition.

Fresh picks from ArXiv
Today at ArXiv: LP on graph with attributes, dynamic graph embeddings, and food recommendation with knowledge graphs 🍕

If I forgot to mention your paper, please shoot me a message and I will update the post.

Conferences
* Predicting Patient Outcomes with Graph Representation Learning with Petar Veličković, Workshop AAAI 2021
* Reinforced Imitative Graph Representation Learning for Mobile User Profiling: An Adversarial Training Perspective AAAI 2021
* Personalized Food Recommendation as Constrained Question Answering over a Large-scale Food Knowledge Graph WSDM 2021
* SDGNN: Learning Node Representation for Signed Directed Networks AAAI 2021

GNNs
* Symmetry-adapted graph neural networks for constructing molecular dynamics force fields
* SE(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
* GraphHop: An Enhanced Label Propagation Method for Node Classification
* MöbiusE: Knowledge Graph Embedding on Möbius Ring
* Node2Seq: Towards Trainable Convolutions in Graph Neural Networks

Survey
* A Survey on Embedding Dynamic Graphs
* Does double-blind peer-review reduce bias? Evidence from a top computer science conference

Datasets: Twitch Gamers

In addition to this repo, Benedek Rozemberczki collected a bunch of social network datasets, which can be useful for node classification/regression. The Twitch Gamers dataset is designed for structural role-based node embedding assessment.

Graph Papers at ICLR 2021: Decisions

Here is an updated list of graph papers with decisions and keywords at ICLR 2021.

There are 201 graph papers: 1 Oral, 9 Spotlights, 40 Posters.

Among most common topics are generalization bounds, equivariance, knowledge graphs, applications to physics/biology/RL/videos.

Post: Top Applications of Graph Neural Networks 2021

In my new post I discuss applications of GNNs in real-world settings. There are ~100 new papers each month on ArXiv about GNNs, indicating that it's a very hot topic 🔥 However, until lately there were not many applications of GNNs in the industry.

I gathered the most interesting applications of GNNs including discovering new medicine 💊, optimizing the power of computer chips 🖥, approximating chemical reactions for renewable energy💨 I really hope that this list will extend in 2021, with more people using GNNs as a default tool for graph structured data.

Podcast: Twiml with Michael Bronstein and Taco Cohen

There are two recent podcasts on Twiml. One with Taco Cohen, a researcher at Qualcomm, on their NeurIPS 20 work with Max Welling and Pim de Haan, called Natural Graph Networks.

The second is with Michael Bronstein, who looks back at the ML achievements of 2020 such as GPT-3 and Neural Implicit Representations. He also discusses the landscape of the Graph ML field in 2021.

Post: AlphaFold 2 & Equivariance

"AlphaFold 2 probably used some network/algorithm to map graph features to obtain the initial XYZ coordinates. Later in the pipeline, they improved their initial prediction by iteratively running their structure module."

Scrutiny of the AlphaFold 2 inner workings by Justas Dauparas & Fabian Fuchs.

GML Newsletter: Do we do it right?

My new issue of the Graph ML newsletter: looking back and ahead for the field. This time I want to raise a point that with all the great research we have in GML, we have comparatively fewer applications of it in real world and that's maybe up to us to pitch and use these developments for the good of people.

Also I moved the platform to substack and there is a wonderful button to support my writings altogether. When I moved to substack I actually just considered eliminating the costs of the previous platform, but surprisingly a few people became paying customers right from the start (which pleasantly surprised me of course). There are some perks of being a paying subscriber (no T-shirts yet:), but my plan is to continue to write for everybody, so hopefully win-win for me and the readers.