TensorLy: Tensor Learning in Python

By Jean Kossaifi, Yannis Panagakis, Maja Pantic. Journal of machine learning research, 2016

426 citations recorded by the source corpus.

Tensors are higher-order extensions of matrices. While matrix methods form the cornerstone of traditional machine learning and data analysis, tensor methods have been gaining increasing traction. However, software support for tensor operations is not on the same footing. In order to bridge this gap, we have developed TensorLy, a Python library that provides a high-level API for tensor methods and deep tensorized neural networks. TensorLy aims to follow the same standards adopted by the main projects of the Python scientific community, and to seamlessly integrate with them. Its BSD license makes it suitable for both academic and commercial applications. TensorLy's backend system allows users to perform computations with several libraries such as NumPy or PyTorch to name but a few. They can be scaled on multiple CPU or GPU machines. In addition, using the deep-learning frameworks as backend allows to easily design and train deep tensorized neural networks. TensorLy is available at https://github.com/tensorly/tensorly

Subfields: Artificial Intelligence, Computational Mathematics, Hardware and Architecture

View Paper: https://www.semanticscholar.org/paper/28d2503b0f86dd3947bf745efdd609dee7975cd8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Mathematics

In Hardware and Architecture

Citations in the corpus

Multi-Head Attention: Collaborate Instead of Concatenate (2020, methodology): “We use the tensor decomposition library Tensorly (Kossaifi et al., 2019) with the PyTorch backend (Paszke et al.”
Unsupervised Discovery of Demixed, Low-Dimensional Neural Dynamics across Multiple Timescales through Tensor Component Analysis (2017, background): “Other resources for ﬁtting tensor decompositions include [93–95].”
Tensor Regression Networks (2017, methodology): “The Tucker decomposition was performed using TensorLy (Kossaiﬁ et al., 2016).”
Coordinated Cellular Neighborhoods Orchestrate Antitumoral Immunity at the Colorectal Cancer Invasive Front (2019, methodology): “Non-negative Tucker decomposition as implemented in the Tensorly Python package was applied to each tensor (Kossaifi et al., 2019).”
Factorized Higher-Order CNNs With an Application to Spatio-Temporal Emotion Estimation (2019, methodology): “Implementation details We implemented all models using PyTorch [33] and TensorLy [22].”
Knowledge Extraction with No Observable Data (2019, methodology): “We initialize the compressed weights of student networks by running the singular value decomposition on the original weights and update them by Tucker decomposition to minimize the reconstruction errors [18].”