Skip to content
@NeSymGraphs

NeSymGraphs

Neurosymbolic AI for Reasoning over Knowledge Graphs: The GitHub Organization

This is the Github organization where we fork all the GitHub repositories featured in our survey paper,

L. N. DeLong, R. F. Mir and J. D. Fleuriot, "Neurosymbolic AI for Reasoning Over Knowledge Graphs: A Survey," in IEEE Transactions on Neural Networks and Learning Systems, doi: 10.1109/TNNLS.2024.3420218..

To cite this work, please use the following:

@ARTICLE{10603423,
  author={DeLong, Lauren Nicole and Mir, Ramon Fernández and Fleuriot, Jacques D.},
  journal={IEEE Transactions on Neural Networks and Learning Systems}, 
  title={Neurosymbolic AI for Reasoning Over Knowledge Graphs: A Survey}, 
  year={2024},
  volume={},
  number={},
  pages={1-21},
  keywords={Cognition;Artificial intelligence;Artificial neural networks;Surveys;Taxonomy;Knowledge graphs;Semantics;Graph neural networks (GNNs);hybrid artificial intelligence (AI);knowledge graphs (KGs);neurosymbolic AI;representation learning},
  doi={10.1109/TNNLS.2024.3420218}}

News 📰

🔍 Our blog post, summarizing this paper with a crime scene analogy, is now on AIHub.

🧬 An abridged, biomedical version of this survey was presented as a (non-archival) workshop paper at ICML 2023's Workshop on Knowledge and Logical Reasoning in the Era of Data-driven Learning.

Summary:

🤔 In this paper, we survey the methods which combine symbolic methods with deep learning to accomplish reasoning tasks over graph structures. This hybrid style is called neurosymbolic AI 🤖 , a relatively new type of AI.

We break these methods down into the following hierarchy:

hierarchy

Logically-Informed Embedding Approaches are the most straightforward: they augment a graph with logical inference, and then feed the augmented graph into a Knowledge Graph embedding method to learn patterns and make predictions:

cat1

The methods under Learning with Logical Constraints essentially restrict the training of some sort of graph embedding method with logic. They typically accomplish this by imposing some sort of regularizing transformation on the embedding space or by imposing a penalty term onto the loss function whenever logical rules are violated:

cat2

Finally, methods which Learn Rules for Graph Reasoning often learn rule confidences, or weights, using an iterative, back-and-forth method. In many of these cases, the model interchangeably trains a graph embedding method and performs logical inference. The results of the embedding method are used to update the weights of the rule base, and the results of logical inference are used to guide the embedding method. Some of these methods even alter the pool of rules so that each iteration has a different rule set:

cat3

To read more, our paper is currently on arxiv.

Contact

Feel free to contact us for the following maintenance:

➕ If you would like us to add GitHub repository containing a published method for neurosymbolic reasoning on graph structures

🔄 If you'd like us to fork a more recent version of your repository than we have here

Contact Information:

👩‍💻 Lauren Nicole DeLong

📬 [email protected]

Popular repositories Loading

  1. kg-deductive-reasoner kg-deductive-reasoner Public

    Forked from Monireh2/kg-deductive-reasoner

    knowledge graph deductive reasoning using memory networks

    Python 2 1

  2. NS-KGC-AUG NS-KGC-AUG Public

    Forked from dair-iitd/NS-KGC-AUG

    Python 2 1

  3. RNNLogic RNNLogic Public

    Forked from DeepGraphLearning/RNNLogic

    C++ 1 1

  4. reonto-relation-extraction reonto-relation-extraction Public

    Forked from kracr/reonto-relation-extraction

    ReOnto is a neuro-symbolic approach where we use ontologies and GNNs to extract relations from sentences.

    Python 1

  5. walking-rdf-and-owl walking-rdf-and-owl Public

    Forked from bio-ontology-research-group/walking-rdf-and-owl

    Feature learning over RDF data and OWL ontologies

    Python

  6. ExpressGNN ExpressGNN Public

    Forked from expressGNN/ExpressGNN

    Python

Repositories

Showing 10 of 30 repositories
  • .github Public
    NeSymGraphs/.github’s past year of commit activity
    0 MIT 0 0 0 Updated Jul 24, 2024
  • gekcs Public Forked from april-tools/gekcs

    How to Turn Your Knowledge Graph Embeddings into Generative Models

    NeSymGraphs/gekcs’s past year of commit activity
    Python 0 5 0 0 Updated Nov 27, 2023
  • TFLEX Public template Forked from LinXueyuanStdio/TFLEX

    [NeurIPS 2023] TFLEX: Temporal Feature-Logic Embedding Framework for Complex Reasoning over Temporal Knowledge Graph

    NeSymGraphs/TFLEX’s past year of commit activity
    Jupyter Notebook 0 Apache-2.0 3 0 0 Updated Oct 24, 2023
  • reonto-relation-extraction Public Forked from kracr/reonto-relation-extraction

    ReOnto is a neuro-symbolic approach where we use ontologies and GNNs to extract relations from sentences.

    NeSymGraphs/reonto-relation-extraction’s past year of commit activity
    Python 1 Apache-2.0 1 0 0 Updated Jun 16, 2023
  • NS-KGC-AUG Public Forked from dair-iitd/NS-KGC-AUG
    NeSymGraphs/NS-KGC-AUG’s past year of commit activity
    Python 2 4 0 0 Updated Jun 2, 2023
  • LPRules Public Forked from IBM/LPRules

    Rule Induction in Knowledge Graphs Using Linear Programming

    NeSymGraphs/LPRules’s past year of commit activity
    C++ 0 EPL-2.0 2 0 0 Updated Feb 21, 2023
  • cqd Public Forked from uclnlp/cqd

    Continuous Query Decomposition for Complex Query Answering in Incomplete Knowledge Graphs

    NeSymGraphs/cqd’s past year of commit activity
    Python 0 MIT 12 0 0 Updated Nov 20, 2022
  • NeSymGraphs/RNNLogic’s past year of commit activity
    C++ 1 25 0 0 Updated Oct 25, 2022
  • RuLES Public Forked from hovinhthinh/RuLES

    Rule Learning with Embedding Support

    NeSymGraphs/RuLES’s past year of commit activity
    C++ 0 4 0 0 Updated Aug 18, 2022
  • walking-rdf-and-owl Public Forked from bio-ontology-research-group/walking-rdf-and-owl

    Feature learning over RDF data and OWL ontologies

    NeSymGraphs/walking-rdf-and-owl’s past year of commit activity
    Python 0 BSD-3-Clause 8 0 0 Updated Aug 17, 2022

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…