Kelpie: an Explainability Framework for Embedding-based Link Prediction Models
Summary: Kelpie is a model-agnostic explainability framework for embedding-based knowledge-graph link prediction. It generates necessary and sufficient explanations across diverse architectures and five benchmark datasets, addressing the interpretability–performance gap. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Andrea Rossi (Roma Tre University)
- 2. Donatella Firmani (Sapienza University)
- 3. Paolo Merialdo (Roma Tre University)
- 4. Tommaso Teofili (Roma Tre University)
BibTeX Citation
@article{rossi_vldb22,
title = {{Kelpie: an Explainability Framework for Embedding-based Link Prediction Models}},
author = {Rossi, Andrea and Firmani, Donatella and Merialdo, Paolo and Teofili, Tommaso},
journal = {PVLDB},
series = {{VLDB} '22},
volume = {15},
number = {12},
pages = {3566--3569},
doi = {10.14778/3554821.3554845},
url = {https://doi.org/10.14778/3554821.3554845},
year = {2022}
}Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,892 | eXpath: Explaining Knowledge Graph Link Prediction with Ontological Closed Path Rules | 2025 | VLDB | 5.093636e-05 |
| 11,202 | Online Detection of Anomalies in Temporal Knowledge Graphs with Interpretability | 2024 | SIGMOD | 5.093636e-05 |
Previous
Page 1 / 1
Next
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 |
|---|---|---|---|---|
| 6,295 | Explaining Link Prediction Systems based on Knowledge Graph Embeddings | 2022 | SIGMOD | 5.9231159e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,023 | A Universal Question-Answering Platform for Knowledge Graphs | 2023 | SIGMOD |
| 2 | 1,402 | Creating Embeddings of Heterogeneous Relational Datasets for Data Integration Tasks | 2020 | SIGMOD |
| 3 | 11,482 | Demonstration of SPARQL^ML: An Interfacing Language for Supporting Graph Machine Learning for RDF Graphs | 2023 | VLDB |
| 4 | 4,834 | KBPearl: A Knowledge Base Population System Supported by Joint Entity and Relation Linking | 2020 | VLDB |
| 5 | 10,557 | Database Views as Explanations for Relational Deep Learning | 2026 | VLDB |
| 6 | 4,372 | Schemaless and Structureless Graph Querying | 2014 | VLDB |
| 7 | 10,825 | Explaining Black-Box Clustering Pipelines With Cluster-Explorer | 2025 | VLDB |
| 8 | 2,781 | Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Study | 2020 | SIGMOD |
| 9 | 10,892 | eXpath: Explaining Knowledge Graph Link Prediction with Ontological Closed Path Rules | 2025 | VLDB |
| 10 | 6,295 | Explaining Link Prediction Systems based on Knowledge Graph Embeddings | 2022 | SIGMOD |