From Global Search to Local Lookup: Scalable Knowledge Base Completion via Differentiable Guarded Logic
Summary: GuardNet uses guarded first-order logic to turn global rule grounding into neighborhood lookups over existing KB edges, reducing sparse-data complexity from quadratic to linear. It scales to 377K concepts while improving prediction accuracy and ontological consistency. (summarized by gpt-6-luna on Oct 22 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Yizheng Zhao (Nanjing University)
BibTeX Citation
@inproceedings{zhao_sigmod27,
title = {{From Global Search to Local Lookup: Scalable Knowledge Base Completion via Differentiable Guarded Logic}},
author = {Zhao, Yizheng},
series = {{SIGMOD} '27},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3837113},
url = {https://dl.acm.org/doi/10.1145/3837113},
year = {2027}
}
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 9 of 9 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 3,488 | LEGO-GraphRAG: Modularizing Graph-based Retrieval-Augmented Generation for Design Space Exploration | 2025 | VLDB |
| 2 | 2,325 | Scalable and Efficient Full-Graph GNN Training for Large Graphs | 2023 | SIGMOD |
| 3 | 11,796 | Collective Grounding: Applying Database Techniques to Grounding Templated Models | 2023 | VLDB |
| 4 | 2,894 | Functional Dependencies for Graphs | 2016 | SIGMOD |
| 5 | 10,852 | QA-GraphRAG: Query-Adaptive Plug-and-Play Retrieval Integration for Graph-based Retrieval-Augmented Generation | 2026 | VLDB |
| 6 | 10,255 | A Universal Question-Answering Platform for Knowledge Graphs | 2023 | SIGMOD |
| 7 | 10,946 | ConRAD: Conformal Risk-Aware Neural Databases | 2026 | VLDB |
| 8 | 10,461 | Recursive Querying of Neural Networks via Weighted Structures | 2026 | PODS |
| 9 | 4,488 | Schemaless and Structureless Graph Querying | 2014 | VLDB |
| 10 | 6,485 | Cardinality Estimation over Knowledge Graphs with Embeddings and Graph Neural Networks | 2024 | SIGMOD |