Saved in:
Bibliographic Details
Main Authors: Iwamoto, Yuki, Kaneiwa, Ken
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.16902
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910495025397760
author Iwamoto, Yuki
Kaneiwa, Ken
author_facet Iwamoto, Yuki
Kaneiwa, Ken
contents Rule-induction models have demonstrated great power in the inductive setting of knowledge graph completion. In this setting, the models are tested on a knowledge graph entirely composed of unseen entities. These models learn relation patterns as rules by utilizing subgraphs. Providing the same inputs with different rules leads to differences in the model's predictions. In this paper, we focus on the behavior of such models. We propose a re-ranking-based model called ReDistLP (Re-ranking with a Distinct Model for Link Prediction). This model enhances the effectiveness of re-ranking by leveraging the difference in the predictions between the initial retriever and the re-ranker. ReDistLP outperforms the state-of-the-art methods in 2 out of 3 benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2405_16902
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Predicting from a Different Perspective: A Re-ranking Model for Inductive Knowledge Graph Completion
Iwamoto, Yuki
Kaneiwa, Ken
Machine Learning
Rule-induction models have demonstrated great power in the inductive setting of knowledge graph completion. In this setting, the models are tested on a knowledge graph entirely composed of unseen entities. These models learn relation patterns as rules by utilizing subgraphs. Providing the same inputs with different rules leads to differences in the model's predictions. In this paper, we focus on the behavior of such models. We propose a re-ranking-based model called ReDistLP (Re-ranking with a Distinct Model for Link Prediction). This model enhances the effectiveness of re-ranking by leveraging the difference in the predictions between the initial retriever and the re-ranker. ReDistLP outperforms the state-of-the-art methods in 2 out of 3 benchmarks.
title Predicting from a Different Perspective: A Re-ranking Model for Inductive Knowledge Graph Completion
topic Machine Learning
url https://arxiv.org/abs/2405.16902