A major factor contributing to the success of modern representation learning is the ease of performing various vector operations. Recently, objects with geometric structures (eg. distributions, complex or hyperbolic vectors, or regions such as cones, disks, or boxes) have been explored for their alternative inductive biases and additional representational capacities. In this work, we introduce Box Embeddings, a Python library that enables researchers to easily apply and extend probabilistic box embeddings.
@article{arxiv.2109.04997,
title = {Box Embeddings: An open-source library for representation learning using geometric structures},
author = {Tejas Chheda and Purujit Goyal and Trang Tran and Dhruvesh Patel and Michael Boratko and Shib Sankar Dasgupta and Andrew McCallum},
journal= {arXiv preprint arXiv:2109.04997},
year = {2021}
}
Comments
The source code and the usage and API documentation for the library is available at https://github.com/iesl/box-embeddings and https://www.iesl.cs.umass.edu/box-embeddings/main/index.html