Elamur Research⌕
☰
home / papers / 2026 / Risk-Controlled Event-Driven Cascading Updates for Knowledge Graph Consistency Restoration

Risk-Controlled Event-Driven Cascading Updates for Knowledge Graph Consistency Restoration

Paper · 2026 · Bo Ni, Qinwen Ge, Haowei Fu et al.

Summary

When a knowledge graph receives a new fact, older facts that depended on the previous state of the world can become wrong. Fixing one of them may then reveal more outdated relations further along the graph. Existing dynamic-KG and KG-update methods mostly handle such changes as isolated or one-hop edits. The authors define this as event-driven cascading updating: a trigger event causes explicit changes, and each round of changes drives the next one until the graph is consistent again.

Their framework, CascadeKG, has two parts:

  • Risk control: Learn-Then-Test calibration bounds expected recall risk over the whole multi-hop cascade, which limits error accumulation without letting the set of predicted edges grow out of control. It works with any scoring model.
  • Scoring model: TAUS is a text-augmented GNN that uses LLM-generated descriptions of events to add world knowledge to the graph representations.

On two new benchmarks built from ICEWS and YAGO/Wiki data, TAUS outperforms embedding, GNN and LM-based baselines. The calibration meets the target coverage while producing the smallest prediction sets. This makes automated KG maintenance more reliable.

Key points

  • New benchmarks ICEWS14-Event and YAGO-Event model scenarios where one event requires coordinated multi-hop revisions. Code and data are released at github.com/Arstanley/cascadekg.
  • TAUS reaches an F1 of 0.880 and an accuracy of 0.866, ahead of TransE, R-GAT and SimKGC. Other compared backbones include DistMult, CompGCN and HittER.
  • The LTT-based calibration keeps valid coverage at every tested risk level α. It yields the smallest prediction sets, especially when paired with TAUS.
  • The task is framed as restoring consistency immediately after an event, not as forecasting future facts.
  • Limitations:
    • The guarantees assume calibration and test data come from the same distribution, so data that shifts over time may require re-calibration.
    • The experiments mainly test edge additions rather than deletions.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🏢Adobe SystemsSan Jose · United States35 works · 3,711 citations🎓Vanderbilt UniversityNashville · United States14 works · 1,413 citations🎓North Carolina State UniversityRaleigh · United States13 works · 406 citations

Also on the byline: HRL Laboratories.

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

🧭 Topics 1Research subjects and languages the work is about.Knowledge graphs & ontologies · 192 works

Cite

Cite as Bo Ni, Qinwen Ge, Haowei Fu, Ryan A. Rossi, Xiaorui Liu, Jiejun Xu and Tyler Derr. 2026. Risk-Controlled Event-Driven Cascading Updates for Knowledge Graph Consistency Restoration. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.2111

@inproceedings{ni2026risk,
  title = {{Risk-Controlled Event-Driven Cascading Updates for Knowledge Graph Consistency Restoration}},
  author = {Bo Ni, Qinwen Ge, Haowei Fu, Ryan A. Rossi, Xiaorui Liu, Jiejun Xu and Tyler Derr},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.2111},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.2111}
}

References

35 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Anastasios N. Angelopoulos and Stephen Bates. 2022. A gentle introduction to conformal prediction and distribution-free uncertainty quantification. Preprint, arXiv:2107.07511. find
  2. Anastasios N. Angelopoulos, Stephen Bates, Emmanuel J. Candès, Michael I. Jordan, and Lihua Lei. 2022. Learn then test: Calibrating predictive algorithms to achieve risk control. Preprint, arXiv:2110.01052. — [arXiv:2110.01052](https://arxiv.org/abs/2110.01052) find
  3. Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, and Oksana Yakhnenko. 2013. Translating embeddings for modeling multi-relational data. In Advances in Neural Information Processing Systems (NeurIPS), pages 2787–2795.
  4. Elizabeth Boschee, Jennifer Lautenschlager, Sean O’Brien, Steve Shellman, James Starz, and Michael Ward. 2015. ICEWS Coded Event Data. find
  5. Dan Busbridge, Dane Sherburn, Pietro Cavallo, and Nils Y Hammerla. 2019. Relational graph attention networks. arXiv preprint arXiv:1904.05811. — [arXiv:1904.05811](https://arxiv.org/abs/1904.05811) find
  6. Li Cai, Xin Mao, Yuhao Zhou, Zhaoguang Long, Changxu Wu, and Man Lan. 2024. A survey on temporal knowledge graph: Representation learning and applications. Preprint, arXiv:2403.04782. — [arXiv:2403.04782](https://arxiv.org/abs/2403.04782) find
  7. Sanxing Chen, Xiaodong Liu, Jianfeng Gao, Jian Jiao, Ruofei Zhang, and Yangfeng Ji. 2021. HittER: Hierarchical transformers for knowledge graph embeddings. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 10395–10407, Online and Punta Cana, Dominican R… find
  8. Zhe Chen, Yuehan Wang, Bin Zhao, Jing Cheng, Xin Zhao, and Zongtao Duan. 2020. Knowledge graph completion: A review. IEEE Access, 8:192435– 192456. find
  9. Shib Sankar Dasgupta, Swayambhu Nath Ray, and Partha Talukdar. 2018. Hyte: Hyperplane-based temporally aware knowledge graph embedding. In Proceedings of the 2018 conference on empirical methods in natural language processing, pages 2001– 2011. find
  10. Wenchong He, Zhe Jiang, Tingsong Xiao, Zelin Xu, and Yukun Li. 2025. A survey on uncertainty quantification methods for deep learning. Preprint, arXiv:2302.13425. — [arXiv:2302.13425](https://arxiv.org/abs/2302.13425) find
  11. Shaoxiong Ji, Shirui Pan, Erik Cambria, Pekka Marttinen, and Philip S. Yu. 2022. A survey on knowledge graphs: Representation, acquisition, and applications. IEEE Transactions on Neural Networks and Learning Systems, 33(2):494–514. find
  12. Xuhui Jiang, Chengjin Xu, Yinghan Shen, Xun Sun, Lumingyuan Tang, Saizhuo Wang, Zhongwu Chen, Yuanzhuo Wang, and Jian Guo. 2025. On the evolution of knowledge graphs: A survey and perspective. Preprint, arXiv:2310.04835. — [arXiv:2310.04835](https://arxiv.org/abs/2310.04835) find
  13. Adrian Kochsiek, Apoorv Saxena, Inderjeet Nair, and Rainer Gemulla. 2023. Friendly neighbors: Contextualized sequence-to-sequence link prediction. arXiv preprint arXiv:2305.13059. find
  14. Jiaqing Liang, Sheng Zhang, and Yanghua Xiao. 2017. How to keep a knowledge base synchronized with its encyclopedia source. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management (CIKM), pages 1917–1926. ACM. find
  15. Lihui Liu, Boxin Du, Heng Ji, and Hanghang Tong. 2020. Kompare: A knowledge graph comparative reasoning system. Preprint, arXiv:2011.03189. — [arXiv:2011.03189](https://arxiv.org/abs/2011.03189) find
  16. Mohamed Morsey, Jens Lehmann, Sören Auer, Claus Stadler, and Sebastian Hellmann. 2012. Dbpedia and the live extraction of structured data from wikipedia. Program, 46(2):157–181. find
  17. Bo Ni, Zheyuan Liu, Leyao Wang, Yongjia Lei, Yuying Zhao, Xueqi Cheng, Qingkai Zeng, Luna Dong, Yinglong Xia, Krishnaram Kenthapadi, Ryan Rossi, Franck Dernoncourt, Md Mehrab Tanjim, Nesreen Ahmed, Xiaorui Liu, Wenqi Fan, Erik Blasch, Yu Wang, Meng Jiang, and Tyler Derr. 2025a. Towards trustworthy r… — [arXiv:2502.06872](https://arxiv.org/abs/2502.06872) find
  18. Bo Ni, Yu Wang, Lu Cheng, Erik Blasch, and Tyler Derr. 2025b. Towards trustworthy knowledge graph reasoning: An uncertainty aware perspective. In Proceedings of the AAAI conference on artificial intelligence, volume 39, pages 12417–12425. find
  19. Ankur Padia, Francis Ferraro, and Tim Finin. 2024. Enhancing knowledge graph consistency through open large language models: A case study. Proceedings of the AAAI Symposium Series, 3(1):203–208. find
  20. Ethan Perez, Florian Strub, Harm de Vries, Vincent Dumoulin, and Aaron Courville. 2017. Film: Visual reasoning with a general conditioning layer. Preprint, arXiv:1709.07871.
  21. Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. Preprint, arXiv:1908.10084.
  22. Yu Rong, Tingyang Xu, Junzhou Huang, Wenbing Huang, Hong Cheng, Yao Ma, Yiqi Wang, Tyler Derr, Lingfei Wu, and Tengfei Ma. 2020. Deep graph learning: Foundations, advances and applications. In Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining, pages 355… find
  23. Apoorv Saxena, Adrian Kochsiek, and Rainer Gemulla. 2022. Sequence-to-sequence knowledge graph completion and question answering. arXiv preprint arXiv:2203.10321. find
  24. Michael Schlichtkrull, Thomas N Kipf, Peter Bloem, Rianne Van Den Berg, Ivan Titov, and Max Welling. 2018. Modeling relational data with graph convolutional networks. In The Semantic Web (ESWC), pages 593–607. Springer. find
  25. Fabian M. Suchanek, Gjergji Kasneci, and Gerhard Weikum. 2007. Yago: a core of semantic knowledge. In Proceedings of the 16th International Conference on World Wide Web, WWW ’07, page 697–706, New York, NY, USA. Association for Computing Machinery. find
  26. Jizhi Tang, Yansong Feng, and Dongyan Zhao. 2019. Learning to update knowledge graphs by reading news. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 2632–2641,… find
  27. Rakshit Trivedi, Hanjun Dai, Yichen Wang, and Le Song. 2017. Know-evolve: Deep temporal reasoning for dynamic knowledge graphs. In international conference on machine learning, pages 3462–3471. PMLR. find
  28. Shikhar Vashishth, Soumya Sanyal, Vikram Nitin, and Partha Talukdar. 2019. Composition-based multi-relational graph convolutional networks. arXiv preprint arXiv:1911.03082. find
  29. Vladimir Vovk, Alexander Gammerman, and Glenn Shafer. 2005. Algorithmic Learning in a Random World. Springer. find
  30. Liang Wang, Wei Zhao, Zhuoyu Wei, and Jingming Liu. 2022. Simkgc: Simple contrastive knowledge graph completion with pre-trained language models. arXiv preprint arXiv:2203.02167. find
  31. Quan Wang, Zhendong Mao, Bin Wang, and Li Guo. 2017. Knowledge graph embedding: A survey of approaches and applications. IEEE transactions on knowledge and data engineering, 29(12):2724–2743. find
  32. Xiangyu Wang, Lyuzhou Chen, Taiyu Ban, Muhammad Usman, Yifeng Guan, Shikang Liu, Tianhao Wu, and Huanhuan Chen. 2021. Knowledge graph quality control: A survey. Fundamental Research, 1(5):607– 626. find
  33. Yu Wang, Amin Javari, Janani Balaji, Walid Shalaby, Tyler Derr, and Xiquan Cui. 2024. Knowledge graph-based session recommendation with session-adaptive propagation. In Companion Proceedings of the ACM Web Conference 2024, pages 264–273. find
  34. Bishan Yang, Wen-tau Yih, Xiaodong He, Jianfeng Gao, and Li Deng. 2015. Embedding entities and relations for learning and inference in knowledge bases. In International Conference on Learning Representations (ICLR).
  35. Zhaocheng Zhu, Zuobai Zhang, Louis-Pascal Xhonneux, and Jian Tang. 2021. Neural bellman-ford networks: A general graph neural network framework for link prediction. Advances in neural information processing systems, 34:29476–29490. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/ni-2026-risk-controlled-event-driven-cascading/