"Amnesia" - A Selection of Machine Learning Models That Can Forget User Data Very Fast
Summary: Amnesia: efficient decremental update algorithms that remove a user’s contribution from trained ML models without re-accessing original training data, enabling fast compliance with right-to-be-forgotten. Rust implementations for four common ML methods show orders-of-magnitude speedups on nine real datasets and outline Differential Dataflow parallelization plus limitations. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
Incoming Citations (Sorted by Pagerank)
Showing 6 of 6 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 3,807 | HedgeCut: Maintaining Randomised Trees for Low-Latency Machine Unlearning | 2021 | SIGMOD | 6.7428898e-05 |
| 4,779 | LIMA: Fine-grained Lineage Tracing and Reuse in Machine Learning Systems | 2021 | SIGMOD | 5.9259373e-05 |
| 7,489 | DeltaBoost: Gradient Boosting Decision Trees with Efficient Machine Unlearning | 2023 | SIGMOD | 4.7135369e-05 |
| 7,702 | ExDRa: Exploratory Data Science on Federated Raw Data | 2021 | SIGMOD | 4.6689015e-05 |
| 11,099 | Snapcase – Regain Control over Your Predictions with Low-Latency Machine Unlearning | 2024 | VLDB | 4.1905499e-05 |
| 11,312 | Screening Native ML Pipelines with “ArgusEyes” | 2022 | CIDR | 4.1905499e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 3 of 3 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 34 | Similarity Search in High Dimensions via Hashing | 1999 | VLDB | 0.00076824554 |
| 524 | Differential dataflow | 2013 | CIDR | 0.00021093133 |
| 2,179 | Spinning Fast Iterative Data Flows | 2012 | VLDB | 9.3632007e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| Overall Rank | Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,842 | New Trends in Data Forgetting for Sustainable Data Management | 2025 | VLDB | 4.1905499e-05 |
| 10,684 | Meaningful Data Erasure in the Presence of Dependencies | 2025 | VLDB | 4.1905499e-05 |
| 3,807 | HedgeCut: Maintaining Randomised Trees for Low-Latency Machine Unlearning | 2021 | SIGMOD | 6.7428898e-05 |
| 11,099 | Snapcase – Regain Control over Your Predictions with Low-Latency Machine Unlearning | 2024 | VLDB | 4.1905499e-05 |
| 10,508 | Privacy and Accuracy-Aware AI/ML Model Deduplication | 2025 | SIGMOD | 4.1905499e-05 |
| 10,116 | Stochastic Submodular Data Forgetting | 2026 | SIGMOD | 4.1905499e-05 |
| 6,178 | A Database System with Amnesia | 2017 | CIDR | 5.1646168e-05 |
| 7,489 | DeltaBoost: Gradient Boosting Decision Trees with Efficient Machine Unlearning | 2023 | SIGMOD | 4.7135369e-05 |
| 9,841 | Machine Unlearning in Learned Databases: An Experimental Analysis | 2024 | SIGMOD | 4.2685233e-05 |
| 8,902 | On the Feasibility of Forgetting in Data Streams | 2024 | PODS | 4.4229886e-05 |