The reviewed record of science sign in
Pith

arxiv: 2103.14998 · v1 · pith:72SLJ6W5 · submitted 2021-03-27 · cs.LG

Tensor Networks for Multi-Modal Non-Euclidean Data

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:72SLJ6W5record.jsonopen to challenge →

classification cs.LG
keywords tensorlearningdatadomainsirregularnetworksabilitydeep
0
0 comments X
read the original abstract

Modern data sources are typically of large scale and multi-modal natures, and acquired on irregular domains, which poses serious challenges to traditional deep learning models. These issues are partially mitigated by either extending existing deep learning algorithms to irregular domains through graphs, or by employing tensor methods to alleviate the computational bottlenecks imposed by the Curse of Dimensionality. To simultaneously resolve both these issues, we introduce a novel Multi-Graph Tensor Network (MGTN) framework, which leverages on the desirable properties of graphs, tensors and neural networks in a physically meaningful and compact manner. This equips MGTNs with the ability to exploit local information in irregular data sources at a drastically reduced parameter complexity, and over a range of learning paradigms such as regression, classification and reinforcement learning. The benefits of the MGTN framework, especially its ability to avoid overfitting through the inherent low-rank regularization properties of tensor networks, are demonstrated through its superior performance against competing models in the individual tensor, graph, and neural network domains.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.