knowledge-graph-completion-1

Inductive Relation Prediction

3260 papers • 126 benchmarks • 313 datasets

Inductive setting of the knowledge graph completion task. This requires a model to perform link prediction on an entirely new test graph with new set of entities.

(Image credit: Papersgraph)

Benchmarks

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

Trend

Dataset

Best Model

Actions

No benchmarks available.

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

0

Paper Graph

Inductive Relation Prediction by BERT

Zhiyu Chen, Xifeng Yan, H. Zha•Thu Mar 11 2021

This work proposes an all-in-one solution, called BERTRL (BERT-based Relational Learning), which leverages pre-trained language model and fine-tunes it by taking relation instances and their possible reasoning paths as training samples.

66 0

Paper Graph

Communicative Message Passing for Inductive Relation Reasoning

Haifeng Hu, Yuedong Yang, Shuangjia Zheng, Sijie Mai•Tue Dec 15 2020

A Communicative Message Passing neural network for Inductive reLation rEasoning, CoMPILE, that reasons over local directed subgraph structures and has a vigorous inductive bias to process entity-independent semantic relations and can naturally handle asymmetric/anti-symmetric relations.

127 0

Paper Graph

Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction

Zhaocheng Zhu, Jian Tang, Zuobai Zhang, Louis-Pascal Xhonneux•Sat Jun 12 2021

The Neural Bellman-Ford Network (NBFNet) is proposed, a general graph neural network framework that solves the path formulation with learned operators in the generalized Bell man-Ford algorithm, and outperforms existing methods by a large margin in both transductive and inductive settings.

440 0

Paper Graph

Cycle Representation Learning for Inductive Relation Prediction

Liangcai Gao, Zuoyu Yan, Tengfei Ma, Zhi Tang, Chao Chen•Tue Oct 05 2021

This paper considers rules as cycles and shows that the space of cycles has a unique structure based on the mathematics of algebraic topology, and builds a novel GNN framework on the collected cycles to learn the representations of cycles, and to predict the existence/non-existence of a relation.

28 0

Paper Graph

Meta-Knowledge Transfer for Inductive Knowledge Graph Embedding

Mingyang Chen, Hua-zeng Chen, Wen Zhang, Zonggang Yuan, Yushan Zhu, Hongting Zhou, Changliang Xu•Tue Oct 26 2021

A model MorsE is proposed, which does not learn embeddings for entities but learns transferable meta-knowledge that can be used to produce entity embeddINGS that significantly outperforms corresponding baselines for in-KGs and out-of-KG tasks in inductive settings.

75 0

Paper Graph

Multi-Aspect Explainable Inductive Relation Prediction by Sentence Transformer

Chun Miao, Di Wang, Zhixiang Su, Li-zhen Cui•Tue Jan 03 2023

The concepts of relation path coverage and relation path confidence are introduced to filter out unreliable paths prior to model training to elevate the model performance.

14 0

Paper Graph

Inductive Relation Prediction from Relational Paths and Context with Hierarchical Transformers

Quan Wang, Zhendong Mao, Jiaang Li•Fri Mar 31 2023

A novel method that captures both connections between entities and the intrinsic nature of entities, by simultaneously aggregating RElational Paths and cOntext with a unified hieRarchical Transformer framework, namely REPORT is proposed.

13 0

Paper Graph

Inductive Link Prediction on N-ary Relational Facts via Semantic Hypergraph Reasoning

Gong Yin, Hongli Zhang, Yuchen Yang, Yi Luo•Tue Mar 25 2025

An n-ary subgraph reasoning framework for fully inductive link prediction (ILP) on n-ary relational facts is proposed and a novel graph structure, the n-ary semantic hypergraph, is introduced to facilitate subgraph extraction.

2 0

Paper Graph

Anchoring Path for Inductive Relation Prediction in Knowledge Graphs

C. Miao, Di Wang, Zhixiang Su, Li-zhen Cui•Wed Dec 20 2023

This work proposes Anchoring Path Sentence Transformer (APST), a search-based description retrieval method to enrich entity descriptions and an assessment mechanism to evaluate the rationality of APs, enabling comprehensive predictions and high-quality explanations.

7 0

Paper Graph

Adding a benchmark result helps the community track progress.