Graph Machine Learning

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.

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.

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

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.

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.

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

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.

Post: Knowledge Graph Insights A series of posts from 2020 by Giuseppe Futia on construction, performance, and applications of knowledge graphs.

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.

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).

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.