Graph Tensor Networks: An Intuitive Framework for Designing Large-Scale Neural Learning Systems on Multiple Domains

03/23/2023
by   Yao Lei Xu, et al.
0

Despite the omnipresence of tensors and tensor operations in modern deep learning, the use of tensor mathematics to formally design and describe neural networks is still under-explored within the deep learning community. To this end, we introduce the Graph Tensor Network (GTN) framework, an intuitive yet rigorous graphical framework for systematically designing and implementing large-scale neural learning systems on both regular and irregular domains. The proposed framework is shown to be general enough to include many popular architectures as special cases, and flexible enough to handle data on any and many data domains. The power and flexibility of the proposed framework is demonstrated through real-data experiments, resulting in improved performance at a drastically lower complexity costs, by virtue of tensor algebra.

READ FULL TEXT
research
10/25/2020

Multi-Graph Tensor Networks

The irregular and multi-modal nature of numerous modern data sources pos...
research
03/27/2021

Tensor Networks for Multi-Modal Non-Euclidean Data

Modern data sources are typically of large scale and multi-modal natures...
research
04/06/2023

ElegansNet: a brief scientific report and initial experiments

This research report introduces ElegansNet, a neural network that mimics...
research
10/11/2021

Designing off-sample performance metrics

Modern machine learning systems are traditionally designed and tested wi...
research
05/15/2020

Quantum-Classical Machine learning by Hybrid Tensor Networks

Tensor networks (TN) have found a wide use in machine learning, and in p...
research
06/04/2020

Nimble: Efficiently Compiling Dynamic Neural Networks for Model Inference

Modern deep neural networks increasingly make use of features such as dy...
research
07/29/2021

On the combined effect of class imbalance and concept complexity in deep learning

Structural concept complexity, class overlap, and data scarcity are some...

Please sign up or login with your details

Forgot password? Click here to reset