Box Embeddings: An open-source library for representation learning using geometric structures

TL;DR

This paper introduces Box Embeddings, an open-source Python library that facilitates the use of geometric structured representations like boxes for enhanced inductive biases and capacities in machine learning.

Contribution

The paper presents a new library that simplifies the application and extension of probabilistic box embeddings for representation learning.

Findings

Enables easy application of geometric structured embeddings

Supports probabilistic box embeddings in Python

Facilitates research in alternative inductive biases

Abstract

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.