paper-with-me

홈 › Papers

Forgetting by Pruning: Data Deletion in Join Cardinality Estimation

2025-11-25 · Chaowei He, Yuanjun Liu, Qingzhi Ma, Shenyuan Ren, Xizhao Luo, Lei Zhao, An Liu arxiv

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.

📄 PDF Abstract BibTeX arXiv:2511.20293

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

AdaptDel: Adaptable Deletion Rate Randomized Smoothing for Certified Robustness

2025-11-12 · Zhuoqun Huang, Neil G. Marchant, Olga Ohrimenko, Benjamin I. P. Rubinstein arxiv

We consider the problem of certified robustness for sequence classification against edit distance perturbations. Naturally occurring inputs of varying lengths (e.g., sentences in natural language processing tasks) presen…

Online Forgetting Process for Linear Regression Models

2020-12-03 · Yuantong Li, Chi-Hua Wang, Guang Cheng

Motivated by the EU's "Right To Be Forgotten" regulation, we initiate a study of statistical data deletion problems where users' data are accessible only for a limited period of time. This setting is formulated as an onl…

regression

FSFM: A Biologically-Inspired Framework for Selective Forgetting of Agent Memory

2026-04-22 · Yingjie Gu, Wenjian Xiong, Liqiang Wang, Pengcheng Ren 외 arxiv

For LLM agents, memory management critically impacts efficiency, quality, and security. While much research focuses on retention, selective forgetting--inspired by human cognitive processes (hippocampal indexing/consolid…

On the Complexity of Dynamic Submodular Maximization

2021-11-05 · Xi Chen, Binghui Peng

We study dynamic algorithms for the problem of maximizing a monotone submodular function over a stream of $n$ insertions and deletions. We show that any algorithm that maintains a $(0.5+\epsilon)$-approximate solution un…

Control-Plane Placement Shapes Forgetting: An Architectural Study of Agent Memory Across Thirteen System Configurations

2026-06-14 · Dongxu Yang arxiv

Where an LLM sits in an agent memory pipeline -- between the recall plane that retrieves stored facts (extensively benchmarked) and the control plane that mutates them via supersede, release, purge (largely untested) -- …