Explaining Link Prediction Systems based on Knowledge Graph Embeddings
Summary: Introduces Kelpie, a model-agnostic explainability framework for embedding-based link prediction in knowledge graphs. It extracts necessary and sufficient explanations by tracing training facts, enabling interpretable predictions across LP models and outperforming baselines in experiments. (summarized by gpt-5-nano on Feb 09 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
@inproceedings{rossi_sigmod22,
title = {{Explaining Link Prediction Systems based on Knowledge Graph Embeddings}},
author = {Rossi, Andrea and Firmani, Donatella and Merialdo, Paolo and Teofili, Tommaso},
series = {{SIGMOD} '22},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3514221.3517887},
url = {https://dl.acm.org/doi/10.1145/3514221.3517887},
year = {2022}
}
Incoming Citations (Sorted by Pagerank)
Showing 7 of 7 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 4,848 | Accelerating Sampling and Aggregation Operations in GNN Frameworks with GPU Initiated Direct Storage Accesses | 2024 | VLDB | 6.3691963e-05 |
| 6,727 | eXpath: Explaining Knowledge Graph Link Prediction with Ontological Closed Path Rules | 2025 | VLDB | 5.6820665e-05 |
| 7,335 | Kelpie: an Explainability Framework for Embedding-based Link Prediction Models | 2022 | VLDB | 5.5339171e-05 |
| 10,398 | From Global Search to Local Lookup: Scalable Knowledge Base Completion via Differentiable Guarded Logic | 2027 | SIGMOD | 4.9605343e-05 |
| 10,832 | Multimodal Knowledge Graph Completion via Relation-Aware Negative Sampling with Diffusion-Based Interpolation | 2026 | VLDB | 4.9605343e-05 |
| 10,906 | Sankofa: Online Query-adaptive Dynamic Graph Summaries | 2026 | VLDB | 4.9605343e-05 |
| 11,516 | Efficient Graph Embedding Generation and Update for Large-Scale Temporal Graph | 2025 | VLDB | 4.9605343e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 5 of 5 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 65 | Freebase: A Collaboratively Created Graph Database For Structuring Human Knowledge | 2008 | SIGMOD | 0.0003826876 |
| 132 | Deep Entity Matching with Pre-Trained Language Models | 2021 | VLDB | 0.00030213215 |
| 158 | Deep Learning for Entity Matching: A Design Space Exploration | 2018 | SIGMOD | 0.00028049555 |
| 1,036 | YAGO3: A Knowledge Base from Multilingual Wikipedias | 2015 | CIDR | 0.00012357949 |
| 2,580 | Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Study | 2020 | SIGMOD | 8.2533242e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 4,530 | KBPearl: A Knowledge Base Population System Supported by Joint Entity and Relation Linking | 2020 | VLDB |
| 2 | 4,163 | A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs | 2020 | VLDB |
| 3 | 1,348 | Creating Embeddings of Heterogeneous Relational Datasets for Data Integration Tasks | 2020 | SIGMOD |
| 4 | 10,255 | A Universal Question-Answering Platform for Knowledge Graphs | 2023 | SIGMOD |
| 5 | 11,297 | Explaining Black-Box Clustering Pipelines With Cluster-Explorer | 2025 | VLDB |
| 6 | 4,488 | Schemaless and Structureless Graph Querying | 2014 | VLDB |
| 7 | 10,810 | Database Views as Explanations for Relational Deep Learning | 2026 | VLDB |
| 8 | 2,580 | Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Study | 2020 | SIGMOD |
| 9 | 6,727 | eXpath: Explaining Knowledge Graph Link Prediction with Ontological Closed Path Rules | 2025 | VLDB |
| 10 | 7,335 | Kelpie: an Explainability Framework for Embedding-based Link Prediction Models | 2022 | VLDB |