• Corpus ID: 233423603

Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges

  title={Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges},
  author={Michael M. Bronstein and Joan Bruna and Taco Cohen and Petar Velivckovi'c},
The last decade has witnessed an experimental revolution in data science and machine learning, epitomised by deep learning methods. Indeed, many high-dimensional learning tasks previously thought to be beyond reach -- such as computer vision, playing Go, or protein folding -- are in fact feasible with appropriate computational scale. Remarkably, the essence of deep learning is built from two simple algorithmic principles: first, the notion of representation or feature learning, whereby adapted… 
A Survey on GNNs for Different Graph Types
  • 2022
Equivariant neural networks for recovery of Hadamard matrices
It is argued that a message passing neural network architecture designed to be equivariant to column and row permutations of a matrix is a powerful application of the principles of Geometric Deep Learning to fundamental mathematics, and a potential stepping stone toward more insights on the Hadamard conjecture using Machine Learning techniques.
PGCN: Progressive Graph Convolutional Networks for Spatial-Temporal Traffic Forecasting
The ability of PGCN to progressively adapt to input data enables the model to generalize in different study sites with robustness, and achieves state-of-the-art performance with consistency in all datasets.
Graph Neural Networks for Asset Management Graph Neural Networks for Asset Management
This paper builds portfolios and shows that graph layers act as a stabilizer to classical methods like LSTM, reducing transaction costs and filtering out high-frequency signals, and study the effect of different graph-based information on the forecast and observe that in 2021, supply chain information becomes much more informative than sectoral or correlation-based graphs.
Histogram Layers for Texture Analysis
A histogram layer for artificial neural networks (ANNs) that directly computes the spatial distribution of features for texture analysis and parameters for the layer are estimated during backpropagation.
Jointly Learnable Data Augmentations for Self-Supervised GNNs
This study proposes, GRAPHSURGEON, a novel SSL method for GNNs with the following features: a learnable data augmentation method that is jointly learned with the embeddings by leveraging the inherent signal encoded in the graph.
Recent advances in neural algorithmic reasoning with graph neural networks (GNNs) are propped up by the notion of algorithmic alignment. Broadly, a neural network will be better at learning to
GRAPHYP: A Scientific Knowledge Graph with Manifold Subnetworks of Communities. Detection of Scholarly Disputes in Adversarial Information Routes
This Article proposes, with SKG GRAPHYP, a novel graph designed geometric architecture which optimizes both the detection of the knowledge manifold of “cognitive communities”, and the representation of alternative paths to adversarial answers to a research question, for instance in the context of academic disputes.
Spatial State-Action Features for General Games
This paper forms a design and efficient implementation of spatial state-action features for general games that can be trained to incentivise or disincentivise actions based on whether or not they match variables of the state in a local area around action variables.
Unsupervised Time Series Classification for Climate Data
  • Alex Romanova
  • Computer Science
    Proceedings of the Northern Lights Deep Learning Workshop
  • 2022
Unsupervised machine learning model is presented that categorizes entity pairs to classes of similar and non similar pairs by converting pairs of entities to mirror vectors, transforming mirror vectors to Gramian Angular Fields (GAF) images and clas- sifying images using CNN transfer learning classi- fication.