Research map / Learning theory and algorithms / Clustering

Making AI Forget You: Data Deletion in Machine Learning

NeurIPS 2019 · Learning theory and algorithms › Clustering · approach: Coresets and dynamic clustering · 69 citations (OpenAlex)

Read the paper Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changed	Where	Measured	Effect
Use quantized-centroid deletion instead of retraining from scratch	Q-k-means · Celltype	speedup: 163.286×	Helped
Use divide-and-conquer deletion instead of retraining from scratch	DC-k-means · Celltype	speedup: 15.6×	Helped
Use quantized-centroid deletion instead of retraining from scratch	Q-k-means · Covtype	speedup: 13.464×	Helped
Use divide-and-conquer deletion instead of retraining from scratch	DC-k-means · Covtype	speedup: 13.048×	Helped
Use quantized-centroid deletion instead of retraining from scratch	Q-k-means · MNIST	speedup: 2.213×	Helped
Use divide-and-conquer deletion instead of retraining from scratch	DC-k-means · MNIST	speedup: 25.381×	Helped
Use quantized-centroid deletion instead of retraining from scratch	Q-k-means · Postures	speedup: 64.441×	Helped
Use divide-and-conquer deletion instead of retraining from scratch	DC-k-means · Postures	speedup: 22.757×	Helped
Use quantized-centroid deletion instead of retraining from scratch	Q-k-means · Gaussian	speedup: 525.63×	Helped
Use divide-and-conquer deletion instead of retraining from scratch	DC-k-means · Gaussian	speedup: 34.483×	Helped
Use quantized-centroid deletion instead of retraining from scratch	Q-k-means · Botnet	speedup: 584.416×	Helped
Use divide-and-conquer deletion instead of retraining from scratch	DC-k-means · Botnet	speedup: 70.939×	Helped

Closest papers by meaning

What makes unlearning hard and what to do about it (NeurIPS 2024 · similarity 0.86)
Deletion-Anticipative Data Selection with a Limited Budget (ICML 2024 · similarity 0.86)
DeRDaVa: Deletion-Robust Data Valuation for Machine Learning (AAAI 2024 · similarity 0.85)
Towards Source-Free Machine Unlearning (CVPR 2025 · similarity 0.85)
Exact Unlearning via Quantized Sufficient Statistics (NeurIPS 2026 · similarity 0.84)
Machine Unlearning Fails to Remove Data Poisoning Attacks (ICLR 2025 · similarity 0.84)

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft