Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Study
Summary: Systematic re-evaluation of knowledge graph completion embeddings after removing leakage from standard benchmarks (FB15k/WN18) and problematic Cartesian-product/reverse relations. Results show substantially lower accuracy than reported, challenging the effectiveness of current embedding approaches and urging re-investigation of viable methods. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Farahnaz Akrami (University of Texas)
- 2. Mohammed Samiul Saeef (University of Texas)
- 3. Qingheng Zhang (Nanjing University)
- 4. Wei Hu (Nanjing University)
- 5. Chengkai Li (University of Texas)
BibTeX Citation
@inproceedings{akrami_sigmod20,
title = {{Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Study}},
author = {Akrami, Farahnaz and Saeef, Mohammed Samiul and Zhang, Qingheng and Hu, Wei and Li, Chengkai},
series = {{SIGMOD} '20},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3318464.3380599},
url = {https://dl.acm.org/doi/10.1145/3318464.3380599},
year = {2020}
}Incoming Citations (Sorted by Pagerank)
Showing 7 of 7 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 4,056 | A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs | 2020 | VLDB | 6.9344762e-05 |
| 5,305 | Parallel Training of Knowledge Graph Embedding Models: A Comparison of Techniques | 2022 | VLDB | 6.2732352e-05 |
| 6,295 | Explaining Link Prediction Systems based on Knowledge Graph Embeddings | 2022 | SIGMOD | 5.9231159e-05 |
| 8,895 | Compact Walks: Taming Knowledge-Graph Embeddings With Domain- and Task-Specific Pathways | 2022 | SIGMOD | 5.3500818e-05 |
| 9,061 | Mining Geospatial Relationships from Text | 2023 | SIGMOD | 5.3251649e-05 |
| 9,063 | Deep Active Alignment of Knowledge Graph Entities and Schemata | 2023 | SIGMOD | 5.3251649e-05 |
| 10,374 | GeoKGM: A Multimodal Large Language Model for Zero-Shot Knowledge Graph Completion in Geospatial Databases | 2026 | SIGMOD | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 2 of 2 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 | 0.00038697603 |
| 1,057 | YAGO3: A Knowledge Base from Multilingual Wikipedias | 2015 | CIDR | 0.00012387149 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 4,372 | Schemaless and Structureless Graph Querying | 2014 | VLDB |
| 2 | 6,581 | Efficient Knowledge Graph Accuracy Evaluation | 2019 | VLDB |
| 3 | 11,567 | PGE: Robust Product Graph Embedding Learning for Error Detection | 2022 | VLDB |
| 4 | 5,305 | Parallel Training of Knowledge Graph Embedding Models: A Comparison of Techniques | 2022 | VLDB |
| 5 | 9,063 | Deep Active Alignment of Knowledge Graph Entities and Schemata | 2023 | SIGMOD |
| 6 | 6,341 | Cardinality Estimation over Knowledge Graphs with Embeddings and Graph Neural Networks | 2024 | SIGMOD |
| 7 | 11,262 | Enriching Relations with Additional Attributes for ER | 2024 | VLDB |
| 8 | 1,402 | Creating Embeddings of Heterogeneous Relational Datasets for Data Integration Tasks | 2020 | SIGMOD |
| 9 | 6,295 | Explaining Link Prediction Systems based on Knowledge Graph Embeddings | 2022 | SIGMOD |
| 10 | 4,056 | A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs | 2020 | VLDB |