Query2Particles: Knowledge Graph Reasoning with Particle Embeddings

@article{Bai2022Query2ParticlesKG,
  title={Query2Particles: Knowledge Graph Reasoning with Particle Embeddings},
  author={Jiaxin Bai and Zihao Wang and Hongming Zhang and Yangqiu Song},
  journal={ArXiv},
  year={2022},
  volume={abs/2204.12847}
}
Answering complex logical queries on incomplete knowledge graphs (KGs) with missing edges is a fundamental and important task for knowledge graph reasoning. The query embedding method is proposed to answer these queries by jointly encoding queries and entities to the same embedding space. Then the answer entities are selected according to the similarities between the entity embeddings and the query embedding. As the answers to a complex query are obtained from a combination of logical… 

References

SHOWING 1-10 OF 29 REFERENCES
Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings
Answering complex logical queries on large-scale incomplete knowledge graphs (KGs) is a fundamental yet challenging task. Recently, a promising approach to this problem has been to embed KG entities
Embedding Logical Queries on Knowledge Graphs
TLDR
This work introduces a framework to efficiently make predictions about conjunctive logical queries -- a flexible but tractable subset of first-order logic -- on incomplete knowledge graphs and demonstrates the utility of this framework in two application studies on real-world datasets with millions of relations.
Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs
TLDR
BetaE is the first method that can handle a complete set of first-order logical operations: conjunction, disjunction, and negation, and a key insight of BetaE is to use probabilistic distributions with bounded support, specifically the Beta distribution, and embed queries/entities as distributions, which as a consequence allows us to also faithfully model uncertainty.
Complex Query Answering with Neural Link Predictors
TLDR
This work translates each query into an end-to-end differentiable objective, where the truth value of each atom is computed by a pre-trained neural link predictor, and analyses two solutions to the optimisation problem, including gradient-based and combinatorial search.
Faithful Embeddings for Knowledge Base Queries
TLDR
A novel QE method is addressed that is more faithful to deductive reasoning, and this leads to better performance on complex queries to incomplete KBs and inserting this new QE module into a neural question-answering system leads to substantial improvements over the state-of-the-art.
Jointly Embedding Knowledge Graphs and Logical Rules
TLDR
Experimental results show that joint embedding brings significant and consistent improvements over state of theart methods and enhances the prediction of new facts which cannot even be directly inferred by pure logical inference, demonstrating the capability of the method to learn more predictive embeddings.
Embedding Uncertain Knowledge Graphs
TLDR
This paper proposes a novel uncertain KG embedding model UKGE, which aims to preserve both structural and uncertainty information of relation facts in the embedding space and introduces probabilistic soft logic to infer confidence scores for unseen relation facts during training.
RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
TLDR
Experimental results show that the proposed RotatE model is not only scalable, but also able to infer and model various relation patterns and significantly outperform existing state-of-the-art models for link prediction.
Knowledge Graph Embedding with Iterative Guidance from Soft Rules
TLDR
Experimental results show that with rule knowledge injected iteratively, RUGE achieves significant and consistent improvements over state-of-the-art baselines; and despite their uncertainties, automatically extracted soft rules are highly beneficial to KG embedding, even those with moderate confidence levels.
Knowledge base completion via search-based question answering
TLDR
A way to leverage existing Web-search-based question-answering technology to fill in the gaps in knowledge bases in a targeted way by learning the best set of queries to ask, such that the answer snippets returned by the search engine are most likely to contain the correct value for that attribute.
...
...