CERA-OSR: Counterfactual Evidence Routing forAuditable One-Shot Subgraph Reasoning inSmart-City Knowledge Graph Completion
DOI:
https://doi.org/10.4108/eetsc.13147Keywords:
knowledge graph reasoning, smart cities, one-shot subgraph reasoning, evidence routing, counterfactual learningAbstract
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.
Downloads
References
[1] Dettmers T, Minervini P, Stenetorp P, Riedel S. Convolutional 2D Knowledge Graph Embeddings. In: Proceedings of the 32nd AAAI Conference on Artificial Intelligence. AAAI Press; 2018. p. 1811–1818. doi:10.1609/aaai.v32i1.11573.
[2] Sun Z, Deng ZH, Nie JY, Tang J. RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space. In: International Conference on Learning Repre-sentations. 2019. Available from: https://openreview .net/forum?id=HkgEQnRqYQ.
[3] Zhang S, Tay Y, Yao L, Liu Q. Quaternion Knowledge Graph Embeddings. In: Advances in Neural Information Processing Systems. Vol. 32. Curran Associates; 2019. Available from: https: //proceedings.neurips.cc/paper/2019/hash/d961e 9f236177d65d21100592edb0769-Abstract.html.
[4] Das R, Dhuliawala S, Zaheer M, Vilnis L, Durugkar I, Krishnamurthy A, Smola A, McCallum A. Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning. In: International Conference on Learning Representations. 2018. Available from: https://openreview.net/forum ?id=Syg-YfWCW.
[5] Sadeghian A, Armandpour M, Ding P, Wang DZ. DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs. In: Advances in Neural Information Processing Systems. Vol. 32. Curran Associates; 2019. Available from: https: //proceedings.neurips.cc/paper/2019/hash/0c72c b7ee1512f800abe27823a792d03-Abstract.html.
[6] Vashishth S, Sanyal S, Nitin V, Talukdar P. Composition-based Multi-Relational Graph Convolutional Networks. In: International Conference on Learning Representa-tions. 2020. Available from: https://openreview.net /forum?id=BylA_C4tPr.
[7] Zhu Z, Zhang Z, Xhonneux LP, Tang J. Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction. In: Advances in Neural Information Processing Systems. Vol. 34. Curran Associates; 2021. p. 29476–29490. Available from: https://proceedings.neurips.cc/paper/2021/hash/f6a673f09493afcd8b129a0bcf1cd5bc-Abstract.html.
[8] Zhang Y, Yao Q. Knowledge Graph Reasoning with Relational Digraph. In: Proceedings of the ACM Web Conference 2022. ACM; 2022. p. 912–924. doi:10.1145/3485447.3512008.
[9] Zhang Y, Zhou Z, Yao Q, Chu X, Han B. AdaProp: Learn-ing Adaptive Propagation for Graph Neural Network based Knowledge Graph Reasoning. In: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Dis-covery and Data Mining. ACM; 2023. p. 3446–3457. doi:10.1145/3580305.3599404.
[10] Zhu Z, Yuan X, Galkin M, Xhonneux LP, Zhang M, Gazeau M, Tang J. A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphs. In: Advances in Neural Information Processing Systems. Vol. 36. Curran Associates; 2023. p. 59323–59336. doi:10.52202/075280-2591.
[11] Zhou Z, Zhang Y, Yao J, Yao Q, Han B. Less is More: One-shot Subgraph Reasoning on Large-scale Knowledge Graphs. In: International Conference on Learning Representations. 2024. Available from: https://proceedings.iclr.cc/paper_files/paper/2024/hash/c3eb94d149aea08c28505d1e5234a21a-Abstract-Conference.html.
[12] Du E, Liu S, Zhang Y. Mixture of Length and Pruning Experts for Knowledge Graphs Reasoning. In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics; 2025. p. 432–453. doi:10.18653/v1/2025.emnlp-main.23.
[13] Ning Y, Liu H, Wang H, Zeng Z, Xiong H. UUKG: Unified Urban Knowledge Graph Dataset for Urban Spatiotemporal Prediction. In: Advances in Neural Information Processing Systems. Vol. 36, Datasets and Benchmarks Track. Curran Associates; 2023. p. 62442–62456. doi:10.52202/075280-2727.
[14] Meilicke C, Chekol MW, Ruffinelli D, Stuckenschmidt H. Anytime Bottom-Up Rule Learning for Knowledge Graph Completion. In: Proceedings of the 28th Interna-tional Joint Conference on Artificial Intelligence. IJCAI; 2019. p. 3137–3143. doi:10.24963/ijcai.2019/435.
[15] Zhang S, Zhang J, Song X, Adeshina S, Zheng D, Falout-sos C, Sun Y. PaGE-Link: Path-based Graph Neural Net-work Explanation for Heterogeneous Link Prediction. In: Proceedings of the ACM Web Conference 2023. ACM; 2023. p. 3784–3793. doi:10.1145/3543507.3583511.
[16] Amara K, Ying Z, Zhang Z, Han Z, Zhao Y, Shan Y, Brandes U, Schemm S, Zhang C. GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networks. In: Proceedings of the First Learning on Graphs Conference. Proceedings of Machine Learning Research. Vol. 198. PMLR; 2022. p. 44:1–44:23. Available from: https://proceedings.mlr.pres s/v198/amara22a.html.
[17] Ning Y, Liu H. UrbanKGent: A Unified Large Language Model Agent Framework for Urban Knowledge Graph Construction. In: Advances in Neural Information Processing Systems. Vol. 37. Curran Associates; 2024. p. 123127–123154. doi:10.52202/079017-3913.
[18] Tabassi E. Artificial Intelligence Risk Management Framework (AI RMF 1.0). Gaithersburg (MD): National Institute of Standards and Technology; 2023. Report No.: NIST AI 100-1. doi:10.6028/NIST.AI.100-1.
[19] Toutanova K, Chen D. Observed versus latent fea-tures for knowledge base and text inference. In: Pro-ceedings of the 3rd Workshop on Continuous Vec-tor Space Models and their Compositionality. Associ-ation for Computational Linguistics; 2015. p. 57–66. doi:10.18653/v1/W15-4007.
[20] Mahdisoltani F, Biega J, Suchanek FM. YAGO3: A Knowledge Base from Multilingual Wikipedias. In: Proceedings of the 7th Biennial Conference on Inno-vative Data Systems Research (CIDR). 2015. Avail-able from: https://www.cidrdb.org/cidr2015/Papers /CIDR15_Paper1.pdf.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Van Ba Nguyen, Minh Y. Nguyen, Ha-Phuong Nguyen, Thuy-A Nguyen
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
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.
