Research Article
CERA-OSR: Counterfactual Evidence Routing forAuditable One-Shot Subgraph Reasoning inSmart-City Knowledge Graph Completion
@ARTICLE{10.4108/eetsc.13147, author={Van Ba Nguyen and Minh Y. Nguyen and Ha-Phuong Nguyen and Thuy-A Nguyen}, title={CERA-OSR: Counterfactual Evidence Routing forAuditable One-Shot Subgraph Reasoning inSmart-City Knowledge Graph Completion}, journal={EAI Endorsed Transactions on Smart Cities}, volume={8}, number={1}, publisher={EAI}, journal_a={SC}, year={2026}, month={11}, keywords={knowledge graph reasoning, smart cities, one-shot subgraph reasoning, evidence routing, counterfactual learning}, doi={10.4108/eetsc.13147} }- Van Ba Nguyen
Minh Y. Nguyen
Ha-Phuong Nguyen
Thuy-A Nguyen
Year: 2026
CERA-OSR: Counterfactual Evidence Routing forAuditable One-Shot Subgraph Reasoning inSmart-City Knowledge Graph Completion
SC
EAI
DOI: 10.4108/eetsc.13147
Abstract
Knowledge graph completion supports data integration, while compact subgraph retrieval can overlook relevant evidence. CERA-OSR integrates train-only multi-view evidence pooling, relation-dependency priors, query-conditioned soft routing, uncertainty-triggered recovery and counterfactual evidence training within a one-shot subgraph reasoning framework. On WN18RR, FB15k-237, NELL-995 and YAGO3-10, CERA-OSR achieves MRR values of 0.626, 0.468, 0.603 and 0.676, respectively. The unweighted mean MRR is 0.5933, compared with 0.5738 for MoKGR, an absolute improvement of 0.0195. Ablation and graph-perturbation analyses examine component contributions and prediction sensitivity to selected evidence. Efficiency measurements reveal a trade-off between ranking performance and the cost of conditional recovery. The framework is motivated by smart-city knowledge graphs and evaluated on general knowledge graph benchmarks.
Copyright © 2026 Van Ba Nguyen et al., licensed to EAI. This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.