Kge

Visit Tool

kge, or LibKGE, is a PyTorch-based library for efficient training, evaluation, and hyperparameter optimization of knowledge graph embeddings (KGE). It fosters reproducible research and offers highly configurable, extensible KGE models.

Claim this tool

1View

At a glance

Pricing

Open Source

Free tier

Yes

API

Skill level

Technical

About

What is kge?

LibKGE is a PyTorch-based library designed for the efficient training, evaluation, and hyperparameter optimization of knowledge graph embeddings (KGE). Its primary goal is to foster reproducible research and facilitate meaningful comparisons between KGE models and training methods. The library is highly configurable, easy to use, and extensible, providing clean implementations of various training strategies, hyperparameter optimization techniques, and evaluation metrics. It supports common KGE models like RESCAL, TransE, DistMult, ComplEx, and ConvE, with explicit exposure of all parameters via well-documented configuration files. LibKGE also includes GraSH for efficient multi-fidelity hyperparameter optimization on large-scale KGE models.

Best used for

Ideal for developers and data scientists who need to implement and experiment with knowledge graph embedding models, compare different training strategies, and optimize hyperparameters. Especially valuable for academic researchers and practitioners focused on reproducible results and efficient handling of large-scale knowledge graphs.

Common actions

train KGE models

evaluate KGE models

optimize hyperparameters

conduct reproducible research

face swapping"AI Agents"automated workflowcollaborationworkflowsdeepfakelow-code/no-codeopen-sourcegithub copilot

Capabilities

Key features

Knowledge graph embedding library
Efficient training
Hyperparameter optimization
Reproducible research
Configurable KGE models
Extensive logging
Automatic memory management

Target Audience

developerdata scientist

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What KGE models does LibKGE support?

LibKGE supports a variety of common knowledge graph embedding models including RESCAL, TransE, TransH, DistMult, ComplEx, ConvE, RelationalTucker3/TuckER, CP, SimplE, RotatE, and a Transformer-based model. New models can also be easily added due to its extensible design.

How does LibKGE ensure reproducible research?

LibKGE ensures reproducibility by providing clean implementations of training, hyperparameter optimization, and evaluation strategies. All potential parameters and heuristics are explicitly exposed via well-documented configuration files, allowing for precise control and replication of experimental setups.

Can LibKGE handle large knowledge graphs?

Yes, LibKGE is designed to handle large knowledge graphs. It features automatic memory management to support large batch sizes and includes GraSH, an efficient multi-fidelity hyperparameter optimization algorithm specifically for large-scale KGE models, as demonstrated with datasets like Wikidata5M and Freebase.

Trending

Subcategories trending in AI Agents & Automation

AI Frameworks & Infra Chatbots & Conversational AI Workflow Agents Personal Assistants RAG & Document AI Voice Agents

Trending

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce