Kelpie: an Explainability Framework for Embedding-based Link Prediction Models

Summary: Kelpie offers explainability for embedding-based link prediction models, addressing opacity in knowledge-graph completion. Model-agnostic, it provides necessary and sufficient explanations and demonstrates effectiveness across architectures on five major datasets. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: 12832
Venue: VLDB
Year: 2022
Pagerank: 4.7529612e-05
Overall Rank: 7,355 | 48.84%
DOI: 10.14778/3554821.3554845

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 2 of 2 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
10,640	eXpath: Explaining Knowledge Graph Link Prediction with Ontological Closed Path Rules	2025	VLDB	4.1945683e-05
10,991	Online Detection of Anomalies in Temporal Knowledge Graphs with Interpretability	2024	SIGMOD	4.1945683e-05

Outgoing Citations (Sorted by Pagerank)

Showing 1 of 1 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
6,408	Explaining Link Prediction Systems based on Knowledge Graph Embeddings	2022	SIGMOD	5.0763482e-05

Semantically Similar Papers

Overall Rank	Paper	Year	Venue	Pagerank
1,914	Creating Embeddings of Heterogeneous Relational Datasets for Data Integration Tasks	2020	SIGMOD	0.00010109102
9,875	A Universal Question-Answering Platform for Knowledge Graphs	2023	SIGMOD	4.2667743e-05
11,283	Demonstration of SPARQLML: An Interfacing Language for Supporting Graph Machine Learning for RDF Graphs	2023	VLDB	4.1945683e-05
5,041	KBPearl: A Knowledge Base Population System Supported by Joint Entity and Relation Linking	2020	VLDB	5.741618e-05
10,269	Database Views as Explanations for Relational Deep Learning	2026	VLDB	4.1945683e-05
3,320	Schemaless and Structureless Graph Querying	2014	VLDB	7.2249102e-05
10,557	Explaining Black-Box Clustering Pipelines With Cluster-Explorer	2025	VLDB	4.1945683e-05
1,966	Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Study	2020	SIGMOD	9.9175408e-05
10,640	eXpath: Explaining Knowledge Graph Link Prediction with Ontological Closed Path Rules	2025	VLDB	4.1945683e-05
6,408	Explaining Link Prediction Systems based on Knowledge Graph Embeddings	2022	SIGMOD	5.0763482e-05