mvlearn: Multiview Machine Learning in Python
Authors: Ronan Perry, Gavin Mischler, Richard Guo, Theodore Lee, Alexander Chang, Arman Koul, Cameron Franz, Hugo Richard, Iain Carmichael, Pierre Ablin, Alexandre Gramfort, Joshua T. Vogelstein
JMLR 2021 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | mvlearn has been tested on Linux, Mac, and PC platforms, and adheres to strong code quality principles. Continuous integration ensures compatibility with past versions, PEP8 style guidelines keep the source code clean, and unit tests provide over 95% code coverage at the time of release. Additionally, mvlearn preprocessing tools can be used to generate multiple views from a single original data matrix, expanding the use-cases of multiview methods and potentially improving results over typical single-view methods with the same data. |
| Researcher Affiliation | Academia | 1 Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD 21218; 9 Department of Electrical Engineering, Columbia University, New York, NY 10027; 5 Universit e Paris-Saclay, Inria, Palaiseau, France; 6 Department of Statistics, University of Washington, Seattle, WA 98195; 7 CNRS and DMA, Ecole Normale Sup erieure, PSL University, Paris, France. |
| Pseudocode | No | No explicit pseudocode or algorithm blocks are present in the paper. The paper describes the algorithms conceptually and lists them in Table 1, but does not provide structured, step-by-step procedures in pseudocode format. |
| Open Source Code | Yes | mvlearn is a Python library which implements the leading multiview machine learning methods. ... The package can be installed from Python Package Index (Py PI) and the conda package manager and is released under the MIT open-source license. The documentation, detailed examples, and all releases are available at https://mvlearn.github.io/. |
| Open Datasets | Yes | A synthetic multiview data generator as well as dataloaders for the Multiple Features Data Set (Breukelen et al., 1998) in the UCI repository (Dua and Graff, 2017) and the genomics Nutrimouse data set (Martin et al., 2007) are included. |
| Dataset Splits | No | The paper introduces a software library and provides data loaders for existing datasets, but it does not describe specific training/test/validation dataset splits used for experiments within this paper. |
| Hardware Specification | No | The paper states 'mvlearn has been tested on Linux, Mac, and PC platforms', but does not provide any specific hardware details such as GPU/CPU models, processor types, or memory used for testing or development. |
| Software Dependencies | No | The paper mentions 'scikit-learn' for API design and 'matplotlib' and 'seaborn' for plotting, and installation via 'Python Package Index (Py PI)' and 'conda package manager', but does not specify version numbers for any software dependencies. |
| Experiment Setup | No | The paper describes a software library and its functionalities, but it does not detail specific experimental setup parameters such as hyperparameters, learning rates, batch sizes, or training configurations for a particular model. |