HedgeCut: Maintaining Randomised Trees for Low-Latency Machine Unlearning
Summary: HedgeCut: an ensemble of randomized decision trees for low-latency machine unlearning. It supports removing data without retraining via vectorised tree operations, delivering ~100 microseconds unlearning latency and up to 36k predictions/sec, with training time and accuracy comparable to Random Forests. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Sebastian Schelter (University of Amsterdam)
- 2. Stefan Grafberger (University of Amsterdam)
- 3. Ted Dunning (Hewlett Packard Enterprise)
BibTeX Citation
@inproceedings{schelter_sigmod21,
title = {{HedgeCut: Maintaining Randomised Trees for Low-Latency Machine Unlearning}},
author = {Schelter, Sebastian and Grafberger, Stefan and Dunning, Ted},
series = {{SIGMOD} '21},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3448016.3457239},
url = {https://dl.acm.org/doi/10.1145/3448016.3457239},
year = {2021}
}Incoming Citations (Sorted by Pagerank)
Showing 7 of 7 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 1,951 | Interpretable Data-Based Explanations for Fairness Debugging | 2022 | SIGMOD | 9.4252389e-05 |
| 5,054 | Explainable AI: Foundations, Applications, Opportunities for Data Management Research | 2022 | SIGMOD | 6.3843089e-05 |
| 6,145 | Equitable Data Valuation Meets the Right to Be Forgotten in Model Markets | 2023 | VLDB | 5.9604471e-05 |
| 7,381 | DeltaBoost: Gradient Boosting Decision Trees with Efficient Machine Unlearning | 2023 | SIGMOD | 5.6288368e-05 |
| 7,661 | Machine Learning for Cloud Data Systems: the Progress so far and the Path Forward | 2021 | VLDB | 5.5736026e-05 |
| 9,881 | The Image Calculator: 10x Faster Image-AI Inference by Replacing JPEG with Self-designing Storage Format | 2024 | SIGMOD | 5.2040783e-05 |
| 11,302 | Snapcase – Regain Control over Your Predictions with Low-Latency Machine Unlearning | 2024 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 9 of 9 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 14 | MonetDB/X100: Hyper-Pipelining Query Execution | 2005 | CIDR | 0.0006312782 |
| 293 | Implementing Database Operations Using SIMD Instructions | 2002 | SIGMOD | 0.00022259273 |
| 455 | Differential dataflow | 2013 | CIDR | 0.00018133241 |
| 649 | Everything You Always Wanted to Know About Compiled and Vectorized Queries But Were Afraid to Ask | 2018 | VLDB | 0.00015320656 |
| 1,340 | Responsible Data Management | 2020 | VLDB | 0.00011111667 |
| 2,755 | Lethe: A Tunable Delete-Aware LSM Engine | 2020 | SIGMOD | 8.163097e-05 |
| 3,853 | Understanding and Benchmarking the Impact of GDPR on Database Systems | 2020 | VLDB | 7.0733274e-05 |
| 5,182 | Probabilistic Demand Forecasting at Scale | 2017 | VLDB | 6.3287692e-05 |
| 6,188 | "Amnesia" - A Selection of Machine Learning Models That Can Forget User Data Very Fast | 2020 | CIDR | 5.9483532e-05 |
Previous
Page 1 / 1
Next