knowledge-graph-completion-1

Inductive knowledge graph completion

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in knowledge-graph-completion-1

Trend

Dataset

Best Model

Actions

Wikidata5m-ind

WN18RR-ind

FB15k-237-ind

Libraries

i

Use these libraries to find knowledge-graph-completion-1 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Inductive Relation Prediction by Subgraph Reasoning

William L. Hamilton, Komal K. Teru, E. Denis•Fri Nov 15 2019

A graph neural network based relation prediction framework, GraIL, that reasons over local subgraph structures and has a strong inductive bias to learn entity-independent relational semantics is proposed.

468

Content

FB15k-237-ind

0

Paper Graph

Inductive Entity Representations from Text via Link Prediction

Michael Cochez, Paul Groth, Daniel Daza•Tue Oct 06 2020

This work proposes a holistic evaluation protocol for entity representations learned via a link prediction objective, and evaluates an architecture based on a pretrained language model, that exhibits strong generalization to entities not observed during training, and outperforms related state-of-the-art methods.

127 0

Paper Graph

DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs

D. Wang, A. Sadeghian, Mohammadreza Armandpour, P. Ding•Mon Sep 30 2019

DRUM is proposed, a scalable and differentiable approach for mining first-order logical rules from knowledge graphs that resolves the problem of learning probabilistic logical rules for inductive and interpretable link prediction.

379 0

Paper Graph

RuDaS: Synthetic Datasets for Rule Learning and Evaluation Tools

Veronika Thost, Cristina Cornelio•Sun Sep 15 2019

This work presents a tool for generating different kinds of datasets and for evaluating rule learning systems, including new performance measures.

0 0

Paper Graph

KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation

Zhiyuan Liu, Juan-Zi Li, Tianyu Gao, Xiaozhi Wang, Zhaocheng Zhu, Jian Tang•Tue Nov 12 2019

A unified model for Knowledge Embedding and Pre-trained LanguagERepresentation (KEPLER), which can not only better integrate factual knowledge into PLMs but also produce effective text-enhanced KE with the strong PLMs is proposed.

774 0

Paper Graph

Towards Learning Instantiated Logical Rules from Knowledge Graphs

Yulong Gu, Yushi Guan, P. Missier•Thu Mar 12 2020

This work presents GPFL, a probabilistic rule learner optimized to mine instantiated first-order logic rules from KGs, which discovers much more quality instantiated rules than existing works and improves the predictive performance of learned rules by removing overfitting rules via validation.

14 0

Paper Graph

Building Rule Hierarchies for Efficient Logical Rule Learning from Knowledge Graphs

Yulong Gu, Yushi Guan, P. Missier•Sun Jun 28 2020

This work builds a Rule Hierarchy Framework (RHF), which leverages a collection of subsumption frameworks to build a proper rule hierarchy from a set of learned rules, and adapts RHF to an existing rule learner where it design and implement two methods for Hierarchical Pruning (HPMs), which utilize the generated hierarchies to remove irrelevant and redundant rules.

1 0

Paper Graph

Relational Message Passing for Fully Inductive Knowledge Graph Completion

Mingyang Chen, Hua-zeng Chen, Jiaoyan Chen, Jeff Z. Pan, Wen Zhang, Yuxia Geng, Song Jiang•Fri Oct 07 2022

This study proposes a new method named RMPI which uses a novel Relational Message Passing network for fully Inductive KGC and passes messages directly between relations to make full use of the relation patterns for subgraph reasoning with new techniques on graph transformation, graph pruning, relation-aware neighborhood attention, addressing empty subgraphs, etc.

56 0

Paper Graph

InGram: Inductive Knowledge Graph Embedding via Relation Graphs

Jaejun Lee, Chanyoung Chung, Joyce Jiyoung Whang•Tue May 30 2023

An INductive knowledge GRAph eMbedding method, InGram, that can generate embeddings of new relations as well as new entities at inference time and outperforms 14 different state-of-the-art methods on varied inductive learning scenarios.

75 0

Paper Graph

Inductive Knowledge Graph Completion with GNNs and Rules: An Analysis

S. Schockaert, Akash Anil, Víctor Gutiérrez-Basulto, Yazmín Ibáñez-García•Sun Aug 13 2023

A number of variants of a rule-based approach which are specifically aimed at addressing the issues of underperformance and interpretability are studied, and it is found that the resulting models can achieve a performance which is close to that of NBFNet.

3 0

Paper Graph

Adding a benchmark result helps the community track progress.