EUVIMEDEUVIMED entdecken
Crossref

Forgetting by Pruning: Data Deletion in Join Cardinality Estimation

Chaowei He, Yuanjun Liu, Qingzhi Ma, Shenyuan Ren, Xizhao Luo, Lei Zhao, An Liu

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (26) · 21602-21609

DOI: 10.1609/aaai.v40i26.39309 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Chaowei He und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Machine unlearning in learned cardinality estimation (CE) systems presents unique challenges due to the complex distributional dependencies in multi-table relational data. Specifically, data deletion, a core component of machine unlearning, faces three critical challenges in learned CE models: attribute-level sensitivity, inter-table propagation and domain disappearance leading to severe overestimation in multi-way joins. We propose Cardinality Estimation Pruning (CEP), the first unlearning framework specifically designed for multi-table learned CE systems. CEP introduces Distribution Sensitivity Pruning, which constructs semi-join deletion results and computes sensitivity scores to guide parameter pruning, and Domain Pruning, which removes support for value domains entirely eliminated by deletion. We evaluate CEP on state-of-the-art architectures NeuroCard and FACE across IMDb and TPC-H datasets. Results demonstrate CEP consistently achieves the lowest Q-error in multi-table scenarios, particularly under high deletion ratios, often outperforming full retraining. Furthermore, CEP significantly reduces convergence iterations, incurring negligible computational overhead of 0.3%-2.5% of fine-tuning time.

Zitieren

APA

He, C., Liu, Y., Ma, Q., Ren, S., Luo, X., Zhao, L., & Liu, A. (2026). Forgetting by Pruning: Data Deletion in Join Cardinality Estimation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(26), 21602-21609. https://doi.org/10.1609/aaai.v40i26.39309

Vancouver

He C, Liu Y, Ma Q, Ren S, Luo X, Zhao L, et al. Forgetting by Pruning: Data Deletion in Join Cardinality Estimation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(26):21602-21609. doi:10.1609/aaai.v40i26.39309

BibTeX
@article{He2026,
  author = {He, Chaowei and Liu, Yuanjun and Ma, Qingzhi and Ren, Shenyuan and Luo, Xizhao and Zhao, Lei and Liu, An},
  title = {Forgetting by Pruning: Data Deletion in Join Cardinality Estimation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {26},
  pages = {21602--21609},
  doi = {10.1609/aaai.v40i26.39309}
}
Kostenlos starten →