Learning Representations for Hyper-Relational Knowledge Graphs
- URL: http://arxiv.org/abs/2208.14322v1
- Date: Tue, 30 Aug 2022 15:02:14 GMT
- Title: Learning Representations for Hyper-Relational Knowledge Graphs
- Authors: Harry Shomer, Wei Jin, Juanhui Li, Yao Ma, Jiliang Tang
- Abstract summary: We design a framework to learn representations for hyper-relational facts using multiple aggregators.
Experiments demonstrate the effectiveness of our framework across multiple datasets.
We conduct an ablation study that validates the importance of the various components in our framework.
- Score: 35.380689788802776
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Knowledge graphs (KGs) have gained prominence for their ability to learn
representations for uni-relational facts. Recently, research has focused on
modeling hyper-relational facts, which move beyond the restriction of
uni-relational facts and allow us to represent more complex and real-world
information. However, existing approaches for learning representations on
hyper-relational KGs majorly focus on enhancing the communication from
qualifiers to base triples while overlooking the flow of information from base
triple to qualifiers. This can lead to suboptimal qualifier representations,
especially when a large amount of qualifiers are presented. It motivates us to
design a framework that utilizes multiple aggregators to learn representations
for hyper-relational facts: one from the perspective of the base triple and the
other one from the perspective of the qualifiers. Experiments demonstrate the
effectiveness of our framework for hyper-relational knowledge graph completion
across multiple datasets. Furthermore, we conduct an ablation study that
validates the importance of the various components in our framework. The code
to reproduce our results can be found at
\url{https://github.com/HarryShomer/QUAD}.
Related papers
- Inference over Unseen Entities, Relations and Literals on Knowledge Graphs [1.7474352892977463]
knowledge graph embedding models have been successfully applied in the transductive setting to tackle various challenging tasks.
We propose the attentive byte-pair encoding layer (BytE) to construct a triple embedding from a sequence of byte-pair encoded subword units of entities and relations.
BytE leads to massive feature reuse via weight tying, since it forces a knowledge graph embedding model to learn embeddings for subword units instead of entities and relations directly.
arXiv Detail & Related papers (2024-10-09T10:20:54Z) - HyperFormer: Enhancing Entity and Relation Interaction for
Hyper-Relational Knowledge Graph Completion [25.399684403558553]
Hyper-relational knowledge graphs (HKGs) extend standard knowledge graphs by associating attribute-value qualifiers to triples.
We propose HyperFormer, a model that considers local-level sequential information, which encodes the content of the entities, relations and qualifiers of a triple.
arXiv Detail & Related papers (2023-08-12T09:31:43Z) - Recognizing Unseen Objects via Multimodal Intensive Knowledge Graph
Propagation [68.13453771001522]
We propose a multimodal intensive ZSL framework that matches regions of images with corresponding semantic embeddings.
We conduct extensive experiments and evaluate our model on large-scale real-world data.
arXiv Detail & Related papers (2023-06-14T13:07:48Z) - Shrinking Embeddings for Hyper-Relational Knowledge Graphs [42.23862602535092]
We present emphShrinkE, a geometric hyper-relational KG embedding method aiming to explicitly model these patterns.
Experimental results demonstrate ShrinkE's superiority on three benchmarks of hyper-relational KGs.
arXiv Detail & Related papers (2023-06-03T21:14:59Z) - Representation Learning on Hyper-Relational and Numeric Knowledge Graphs with Transformers [14.240639250451736]
A hyper-relational knowledge graph has been recently studied where a triplet is associated with a set of qualifiers.
We propose a unified framework named HyNT that learns representations of a hyper-relational knowledge graph containing numeric literals in either triplets or qualifiers.
arXiv Detail & Related papers (2023-05-29T17:23:31Z) - A Dataset for Hyper-Relational Extraction and a Cube-Filling Approach [59.89749342550104]
We propose the task of hyper-relational extraction to extract more specific and complete facts from text.
Existing models cannot perform hyper-relational extraction as it requires a model to consider the interaction between three entities.
We propose CubeRE, a cube-filling model inspired by table-filling approaches and explicitly considers the interaction between relation triplets and qualifiers.
arXiv Detail & Related papers (2022-11-18T03:51:28Z) - All the World's a (Hyper)Graph: A Data Drama [55.144729234861316]
Hyperbard is a dataset of diverse data representations from Shakespeare's plays.
Our representations range from simple graphs capturing character co-occurrence in single scenes to hypergraphs encoding complex communication settings.
As an homage to our data source, and asserting that science can also be art, we present all our points in the form of a play.
arXiv Detail & Related papers (2022-06-16T14:51:28Z) - Relation-Guided Representation Learning [53.60351496449232]
We propose a new representation learning method that explicitly models and leverages sample relations.
Our framework well preserves the relations between samples.
By seeking to embed samples into subspace, we show that our method can address the large-scale and out-of-sample problem.
arXiv Detail & Related papers (2020-07-11T10:57:45Z) - ENT-DESC: Entity Description Generation by Exploring Knowledge Graph [53.03778194567752]
In practice, the input knowledge could be more than enough, since the output description may only cover the most significant knowledge.
We introduce a large-scale and challenging dataset to facilitate the study of such a practical scenario in KG-to-text.
We propose a multi-graph structure that is able to represent the original graph information more comprehensively.
arXiv Detail & Related papers (2020-04-30T14:16:19Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.