Graph Machine Learning

Graph Neural Networks User Group: July meeting This month GNN user group talks about a new release of DGL and applications of GNNs. Please join this Thursday! 4:00 - 4:15 PM (PDT): DGL 0.7 release(Dr. Minjie Wang, Amazon) 4:15 - 4:30 PM (PDT): Storing Node Features in GPU memory to speedup billion-scale GNN training (Dr. Dominique LaSalle, NVIDIA) 4:30 - 5:00 PM (PDT): Locally Private Graph Neural Networks (Sina Sajadmanesh, Idiap Research Institute, Switzerland). 5:00 - 5:30 PM (PDT): Graph Embedding and Application in Meituan (Mengdi Zhang, Meituan).

Fresh picks from ArXiv This week on ArXiv: SOTA for protein energy prediction, another solution to OGB-LSC challenge, and a new dataset based on Wikipedia 📚 If I forgot to mention your paper, please shoot me a message and I will update the post. Applications * X-GGM: Graph Generative Modeling for Out-of-Distribution Generalization in Visual Question Answering * Structure-aware Interactive Graph Neural Networks for the Prediction of Protein-Ligand Binding Affinity KDD 2021 GNNs * Local2Global: Scaling global representation learning on graphs via local training * Ego-GNNs: Exploiting Ego Structures in Graph Neural Networks with William L. Hamilton * Bridging the Gap between Spatial and Spectral Domains: A Theoretical Framework for Graph Neural Networks * Large-scale graph representation learning with very deep GNNs and self-supervision with Petar Veličković * Group Contrastive Self-Supervised Learning on Graphs with Shuiwang Ji Datasets * WikiGraphs: A Wikipedia Text - Knowledge Graph Paired Dataset with Oriol Vinyals

Interpretable Deep Learning for New Physics Discovery In this video, Miles Cranmer (Princeton) discusses a method for converting a neural network into an analytic equation using a particular set of inductive biases. The technique relies on a sparsification of latent spaces in a deep neural network, followed by symbolic regression. In their paper, they demonstrate that they can recover physical laws for various simple and complex systems. For example, they discover gravity along with planetary masses from data; they learn a technique for doing cosmology with cosmic voids and dark matter halos; and they show how to extract the Euler equation from a graph neural network trained on turbulence data.

labml.ai Annotated PyTorch Paper Implementations A very cool collection of popular deep learning blocks, nicely formatted in the browser with extensive comments. Among others there is a GAT implementation.

Awesome Explainable Graph Reasoning An awesome collection of research papers and software related to explainability in graph machine learning, provided by AstraZeneca. It covers papers on explainable predictions and reasoning, libraries, and survey papers.

Graph Papers at ICML 2021 ICML 2021 is happening this week and here is a list of all relevant graph papers that you can encounter there. There are papers on improving expressiveness, explainability, robustness, normalization and theory.

Fresh picks from ArXiv This week on ArXiv: QA in images, graph matching, and learning robot dynamics 🤖 If I forgot to mention your paper, please shoot me a message and I will update the post. GNNs * Train on Small, Play the Large: Scaling Up Board Games with AlphaZero and GNN * Reasoning-Modulated Representations with Petar Veličković and Thomas Kipf * SENSORIMOTOR GRAPH: Action-Conditioned Graph Neural Network for Learning Robotic Soft Hand Dynamics * Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and More with Stephan Günnemann * Graphhopper: Multi-Hop Scene Graph Reasoning for Visual Question Answering with Stephan Günnemann * Elastic Graph Neural Networks Survey * A Survey of Knowledge Graph Embedding and Their Applications

Effortless Distributed Training of Ultra-Wide GCNs A great post about distributed training of GNNs on large graphs. The architecture splits the GNN into several submodules where each is trained independently on separate GPUs, providing the flexibility to increase significantly the hidden dimension of embeddings. As such this approach is GCN model agnostic, compatible with existing sampling methods, and performs the best in very large graphs.

LOGML Videos LOGML is an exciting summer school with projects and talks about graph ML happening this week. A collection of videos that includes presentations of the cutting edge research as well as industrial applications from leading companies are available now for everyone.

Speeding Up the Webcola Graph Viz Library with Rust + WebAssembly A captivating story about optimizing visualization of graphs in the browser. The code can be found here. Here is a performance comparison of different browser visualization libraries. And here is another efficient library for plotting graphs in a browser.

GNN User Group Meeting videos (June) Video from the June meeting of GNN user group that includes talks about binary GNNs and dynamic graph models by Mahdi Saleh and and about simplifying large-scale visual analysis of tricky data & models with GPUs, graphs, and ML by Leo Meyerovich.

Fresh picks from ArXiv This week on ArXiv: explanations of GNNs, generalization of GAE and generating natural proofs 👴 If I forgot to mention your paper, please shoot me a message and I will update the post. GNN * Automated Graph Learning via Population Based Self-Tuning GCN * Quantitative Evaluation of Explainable Graph Neural Networks for Molecular Property Prediction * Robust Counterfactual Explanations on Graph Neural Networks * Probabilistic Graph Reasoning for Natural Proof Generation * On Generalization of Graph Autoencoders with Adversarial Training * Private Graph Data Release: A Survey

Graph Machine Learning research groups: Andreas Krause I do a series of posts on the groups in graph research, previous post is here. The 31st is Andreas Krause, a professor at ETH Zurich and an advisor for Stefanie Jegelka. Andreas Krause (~1982) - Affiliation: ETH Zurich - Education: Ph.D. at CMU in 2008 (advisor: Carlos Guestrin) - h-index 81 - Interests: social network analysis, community detection, graphical models. - Awards: Rossler Prize, best papers (AISTATS, AAAI, KDD, ICML)

How to build E(n) Equivariant Normalizing Flows, for points with features? A nice post that discusses how one can use normalizing flows and equivariant GNNs to generate realistic molecules.

Fresh picks from ArXiv This week on ArXiv: WL to solve planar graphs, efficient molecule generation, and compressing graphs 🤐 If I forgot to mention your paper, please shoot me a message and I will update the post. Math Logarithmic Weisfeiler-Leman Identifies All Planar Graphs GNNs Curvature Graph Neural Network Relational VAE: A Continuous Latent Variable Model for Graph Structured Data GraphPiece: Efficiently Generating High-Quality Molecular Graph with Substructures Privacy-Preserving Representation Learning on Graphs: A Mutual Information Perspective KDD 2021 Partition and Code: learning how to compress graphs with Andreas Loukas and Michael M. Bronstein Evolving-Graph Gaussian Processes ICML Workshop 2021

Connecting the Dots: Harness the Power of Graphs & ML A new short book on graph ML that describes various algorithms on graphs and future challenges.

GNN Applications An overview presentation by Xavier Bresson about applications of GNNs, which include chip design, protein folding, autonomous driving, energy physics, and more.

On "On Graph Neural Networks versus Graph-Augmented MLPs" There is a cool ICLR'21 paper "On Graph Neural Networks versus Graph-Augmented MLPs" by Lei Chen, Zhengdao Chen, and Joan Bruna, which studies a question I had in mind for some time: can we replace a graph with some statistics of graph, which we will later use with standard MLP, and not lose in quality? The answer is that for graph-level task, such as graph isomorphism, we can indeed capture much of what's needed from the graph to solve graph isomorphism problem at the same level as WL test. However, for node-level tasks, there are provably less functions on nodes that graph-augmented MLPs can identify than GNNs. Roughly, the reason is that GNNs process graph topology and node features at the same time, while graph-augmented MLPs first treat the graph topology and then process node features with MLP. So theoretically we lose expressive power when we use MLPs instead of GNNs on graph-structured data.

Recordings: Graph Neural Networks at CAIMS Recordings of a session at CAIMS are now available. The topics are the cutting-edge research in the GNN world and is interesting if you want to see what researchers are currently working on in this space. From local structures to size generalization in graph neural networks by Haggai Maron (NVIDIA) On the generalization of graph neural networks and their applications to probabilistic inference by Renjie Liao (Google) Graph convolution for semi-supervised classification: improved linear separability and out-of-distribution generalization by Kimon Fountoulakis (University of Waterloo) Persistent message passing by Petar Veličković (DeepMind)

Speech recognition and Graph Transformer Networks A lecture by Awni Hannun talks about low-resource speech recognition, beam search decoding, finite-state automate, and graph transformer networks.