- name: PyKEEN github: pykeen/pykeen homepage: https://pykeen.github.io docs: https://pykeen.readthedocs.io language: python framework: PyTorch pypi: pykeen academic: true citation: title: "PyKEEN 1.0: A Python Library for Training and Evaluating Knowledge Graph Embeddings" year: 2021 venue: JMLR authors: Mehdi Ali, Max Berrendorf, Charles Tapley Hoyt, Laurent Vermue, Sahand Sharifzadeh, Volker Tresp, and Jens Lehmann url: https://jmlr.org/papers/v22/20-825.html arxiv: 2007.14175 installation: https://github.com/pykeen/pykeen/#installation-- ci: type: github link: https://github.com/pykeen/pykeen/actions/workflows/tests.yml description: PyKEEN is a PyTorch-based KGEM library for training and evaluation of knowledge graph embedding models. It is built with a modular architecture so the model, loss function, training loop, and other components can be used interchangably. - name: AmpliGraph github: Accenture/AmpliGraph docs: https://docs.ampligraph.org language: python framework: TensorFlow citation: null academic: false slack: https://join.slack.com/t/ampligraph/shared_invite/enQtNTc2NTI0MzUxMTM5LTRkODk0MjI2OWRlZjdjYmExY2Q3M2M3NGY0MGYyMmI4NWYyMWVhYTRjZDhkZjA1YTEyMzBkMGE4N2RmNTRiZDg installation: https://github.com/Accenture/AmpliGraph#installation pypi: ampligraph ci: type: CircleCI link: https://app.circleci.com/pipelines/github/Accenture/AmpliGraph description: AmpliGraph is a suite of neural machine learning models for relational Learning, a branch of machine learning that deals with supervised learning on knowledge graphs. - name: Pykg2vec github: Sujit-O/pykg2vec docs: https://pykg2vec.readthedocs.io license: MIT framework: PyTorch pypi: pykg2vec academic: true arxiv: 1906.04239 citation: authors: Shih-Yuan Yu, Sujit Rokka Chhetri, Arquimedes Canedo, Palash Goyal, and Mohammad Abdullah Al Faruque year: 2021 venue: JMLR title: "Pykg2vec: A Python Library for Knowledge Graph Embedding" url: https://jmlr.org/papers/v22/19-433.html ci: type: CircleCI link: https://app.circleci.com/pipelines/github/Sujit-O/pykg2vec installation: https://github.com/Sujit-O/pykg2vec#to-get-started description: Pykg2vec is a library for learning the representation of entities and relations in Knowledge Graphs built on top of PyTorch 1.5 (TF2 version is available in tf-master branch as well). It attempts to bring state-of-the-art knowledge graph embedding algorithms and the necessary building blocks in the pipeline of knowledge graph embedding task into a single library. - name: StellarGraph github: stellargraph/stellargraph citation: null academic: false docs: https://stellargraph.readthedocs.io ci: type: GitHub link: https://github.com/stellargraph/stellargraph/actions/workflows/ci.yml language: python pypi: stellargraph installation: https://github.com/stellargraph/stellargraph#installation description: The StellarGraph library offers state-of-the-art algorithms for graph machine learning, making it easy to discover patterns and answer questions about graph-structured data. - name: PyTorch-BigGraph github: facebookresearch/PyTorch-BigGraph academic: false citation: year: 2019 url: https://mlsys.org/Conferences/2019/doc/2019/71.pdf venue: Proceedings of the 2nd SysML Conference authors: Adam Lerer, Ledell Wu, Jiajun Shen, Timothee Lacroix, Luca Wehrstedt, Abhijit Bose, and Alex Peysakhovich title: "PyTorch-BigGraph: A Large-scale Graph Embedding Framework" docs: https://torchbiggraph.readthedocs.io ci: type: CircleCI link: https://app.circleci.com/pipelines/github/facebookresearch/PyTorch-BigGraph pypi: torchbiggraph installation: https://github.com/facebookresearch/PyTorch-BigGraph#installation description: PyTorch-BigGraph (PBG) is a distributed system for learning graph embeddings for large graphs, particularly big web interaction graphs with up to billions of entities and trillions of edges. - name: Deep Graph Library github: dmlc/dgl academic: false homepage: https://dgl.ai docs: https://docs.dgl.ai ci: type: Jenkins link: https://ci.dgl.ai/job/DGL/job/master pypi: dgl installation: https://github.com/dmlc/dgl#installation slack: https://join.slack.com/t/deep-graph-library/shared_invite/zt-eb4ict1g-xcg3PhZAFAB8p6dtKuP6xQ citation: title: "Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks" url: https://arxiv.org/abs/1909.01315 venue: arXiv authors: Minjie Wang, Da Zheng, Zihao Ye, Quan Gan, Mufei Li, Xiang Song, Jinjing Zhou, Chao Ma, Lingfan Yu, Yu Gai, Tianjun Xiao, Tong He, George Karypis, Jinyang Li, and Zheng Zhang year: 2020 description: DGL is an easy-to-use, high performance and scalable Python package for deep learning on graphs. DGL is framework agnostic, meaning if a deep graph model is a component of an end-to-end application, the rest of the logics can be implemented in any major frameworks, such as PyTorch, Apache MXNet or TensorFlow. - name: Paddle Graph Learning abbreviation: PGL github: PaddlePaddle/PGL academic: false framework: Custom installation: https://github.com/PaddlePaddle/PGL#installation docs: https://pgl.readthedocs.io pypi: pgl citation: null description: Paddle Graph Learning (PGL) is an efficient and flexible graph learning framework based on PaddlePaddle. - name: CogKGE github: jinzhuoran/CogKGE academic: true homepage: http://cognlp.com/cogkge framework: PyTorch installation: https://github.com/jinzhuoran/CogKGE#install pypi: cogkge citation: authors: Zhuoran Jin, Tianyi Men, Hongbang Yuan, Zhitao He, Dianbo Sui, Chenhao Wang, Zhipeng Xue, Yubo Chen, Jun Zhao year: 2022 url: https://aclanthology.org/2022.acl-demo.16/ title: "CogKGE: A Knowledge Graph Embedding Toolkit and Benchmark for Representing Multi-source and Heterogeneous Knowledge" venue: ACL description: A Knowledge Graph Embedding Toolkit and Benckmark for Representing Multi-source and Heterogeneous Knowledge - name: Marius github: marius-team/marius homepage: https://marius-project.org arxiv: 2101.08358 license: Apache-2.0 framework: Custom installation: https://github.com/marius-team/marius#build-and-install language: - python - c++ academic: true ci: type: github link: https://github.com/marius-team/marius/actions/workflows/build_and_test.yml citation: title: "Marius: Learning Massive Graph Embeddings on a Single Machine" year: 2021 authors: Jason Mohoney, Roger Waleffe, Henry Xu, Theodoros Rekatsinas, and Shivaram Venkataraman url: https://www.usenix.org/conference/osdi21/presentation/mohoney venue: OSDI description: Marius is a system for large-scale graph learning that supports large-scale link prediction training, and preprocessing and training of datasets. - name: GraphVite github: DeepGraphLearning/graphvite academic: true homepage: https://graphvite.io installation: https://github.com/DeepGraphLearning/graphvite#installation arxiv: 1903.00757 language: - python - c++ citation: url: https://arxiv.org/abs/1903.00757 authors: Zhaocheng Zhu, Shizhen Xu, Meng Qu, and Jian Tang year: 2019 title: "GraphVite: A High-Performance CPU-GPU Hybrid System for Node Embedding" venue: arXiv description: GraphVite is a general and high-performance graph embedding system for various applications, designed for CPU-GPU hybrid architecture. - name: LibKGE github: uma-pi1/kge academic: true installation: https://github.com/uma-pi1/kge#quick-start citation: year: 2020 title: "LibKGE - A knowledge graph embedding library for reproducible research" authors: Samuel Broscheit, Daniel Ruffinelli, Adrian Kochsiek, Patrick Betz, and Rainer Gemulla url: https://www.aclweb.org/anthology/2020.emnlp-demos.22 venue: EMNLP description: LibKGE is a PyTorch-based library for efficient training, evaluation, and hyperparameter optimization of knowledge graph embeddings. - name: OpenKE github: thunlp/OpenKE academic: true homepage: http://openke.thunlp.org framework: TensorFlow installation: https://github.com/thunlp/OpenKE#installation citation: authors: Xu Han, Shulin Cao, Xin Lv, Yankai Lin, Zhiyuan Liu, Maosong Sun, and Juanzi Li year: 2018 url: https://www.aclweb.org/anthology/D18-2024/ title: "OpenKE: An Open Toolkit for Knowledge Embedding" venue: EMNLP description: OpenKE is an open-source framework for knowledge embedding organized by THUNLP based on the TensorFlow toolkit. - name: μKG github: nju-websoft/muKG academic: true language: python framework: - PyTorch - TensorFlow installation: https://github.com/nju-websoft/muKG#getting-started- citation: authors: Xindi Luo, Zequn Sun, Wei Hu year: 2022 venue: ISWC title: "μKG: A Library for Multi-source Knowledge Graph Embeddings and Applications"