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

09/10/2021
by   Tejas Chheda, et al.
9

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/28/2021

Word2Box: Learning Word Representation Using Box Embeddings

Learning vector representations for words is one of the most fundamental...
research
04/28/2023

NeuralKG-ind: A Python Library for Inductive Knowledge Graph Representation Learning

Since the dynamic characteristics of knowledge graphs, many inductive kn...
research
10/09/2020

Improving Local Identifiability in Probabilistic Box Embeddings

Geometric embeddings have recently received attention for their natural ...
research
02/25/2022

NeuralKG: An Open Source Library for Diverse Representation Learning of Knowledge Graphs

NeuralKG is an open-source Python-based library for diverse representati...
research
01/26/2023

Box^2EL: Concept and Role Box Embeddings for the Description Logic EL++

Representation learning in the form of semantic embeddings has been succ...
research
07/04/2023

Concept2Box: Joint Geometric Embeddings for Learning Two-View Knowledge Graphs

Knowledge graph embeddings (KGE) have been extensively studied to embed ...
research
03/06/2019

Fast Graph Representation Learning with PyTorch Geometric

We introduce PyTorch Geometric, a library for deep learning on irregular...

Please sign up or login with your details

Forgot password? Click here to reset