# Multi-Graph Tensor Networks

arXiv: https://arxiv.org/abs/2010.13209 · HTML: https://mlsanity.com/paper/2010.13209/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Oct 2020.

## Built on by (most cited first, 5 of 5)

- [Graph Tensor Networks: An Intuitive Framework for Designing Large-Scale Neural Learning Systems on Multiple Domains](https://mlsanity.com/paper/2303.13565/) (2023)
- [Continuous Product Graph Neural Networks](https://mlsanity.com/paper/2405.18877/) (2024)
- [Tensor Networks for Multi-Modal Non-Euclidean Data](https://mlsanity.com/paper/2103.14998/) (2021)
- [Graph-Regularized Tensor Regression: A Domain-Aware Framework for Interpretable Multi-Way Financial Modelling](https://mlsanity.com/paper/2211.05581/) (2022)
- [Second-Order Tensorial Partial Differential Equations on Graphs](https://mlsanity.com/paper/2509.02015/) (2025)

## Abstract (arXiv)

The irregular and multi-modal nature of numerous modern data sources poses serious challenges for traditional deep learning algorithms. To this end, recent efforts have generalized existing algorithms to irregular domains through graphs, with the aim to gain additional insights from data through the underlying graph topology. At the same time, tensor-based methods have demonstrated promising results in bypassing the bottlenecks imposed by the Curse of Dimensionality. In this paper, we introduce a novel Multi-Graph Tensor Network (MGTN) framework, which exploits both the ability of graphs to handle irregular data sources and the compression properties of tensor networks in a deep learning setting. The potential of the proposed framework is demonstrated through an MGTN based deep Q agent for Foreign Exchange (FOREX) algorithmic trading. By virtue of the MGTN, a FOREX currency graph is leveraged to impose an economically meaningful structure on this demanding task, resulting in a highly superior performance against three competing models and at a drastically lower complexity.