Compact Walks: Taming Knowledge-Graph Embeddings With Domain- and Task-Specific Pathways
Summary: CompactWalks uses domain- and task-specific regular-expression pathways to define semantic subgraphs for KG neighborhoods. Mitigates promiscuity and runtime bottlenecks in large biomedical KGs; case studies on drug–disease links and scalable embeddings. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Pei-Yu Hou (North Carolina State University)
- 2. Daniel R. Korn (University of North Carolina)
- 3. Cleber C. Melo-Filho (University of North Carolina)
- 4. David R. Wright (North Carolina State University)
- 5. Alexander Tropsha (University of North Carolina)
- 6. Rada Chirkova (North Carolina State University)
BibTeX Citation
@inproceedings{hou_sigmod22,
title = {{Compact Walks: Taming Knowledge-Graph Embeddings With Domain- and Task-Specific Pathways}},
author = {Hou, Pei-Yu and Korn, Daniel R. and Melo-Filho, Cleber C. and Wright, David R. and Tropsha, Alexander and Chirkova, Rada},
series = {{SIGMOD} '22},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3514221.3517903},
url = {https://dl.acm.org/doi/10.1145/3514221.3517903},
year = {2022}
}Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 5,597 | Accelerating Sampling and Aggregation Operations in GNN Frameworks with GPU Initiated Direct Storage Accesses | 2024 | VLDB | 6.1547003e-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 |
|---|---|---|---|---|
| 2,781 | Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Study | 2020 | SIGMOD | 8.1281896e-05 |
| 4,905 | Medical Entity Disambiguation Using Graph Neural Networks | 2021 | SIGMOD | 6.4497268e-05 |
Previous
Page 1 / 1
Next