Machine unlearning, the process of removing specific data influences from Machine Learning models, is critical for complying with regulations like the GDPR's right to be forgotten and addressing copyright disputes in large models. Despite its rising importance, the field still lacks standardized tools, hindering reproducibility and evaluation. Here, we present, in an extensive way, ERASURE, a unified framework enabling reproducibility by implementing common unlearning techniques, evaluation metrics, and dedicated datasets. ERASURE advances research, ensures solution comparability, and facilitates reproducibility, addressing future legal and ethical challenges in data management.
How to Make Reproducible Research in Machine Unlearning with ERASURE / D'Angelo, Andrea; Savelli, Claudio; Tagliente, Gabriele; Giobergia, Flavio; Baralis, Elena Maria; Stilo, Giovanni. - (2025), pp. 11025-11029. (Intervento presentato al convegno Thirty-Fourth International Joint Conference on Artificial Intelligence tenutosi a Montreal (CA) nel 16-22 August 2025) [10.24963/ijcai.2025/1255].
How to Make Reproducible Research in Machine Unlearning with ERASURE
Savelli Claudio;Giobergia Flavio;Baralis Elena;
2025
Abstract
Machine unlearning, the process of removing specific data influences from Machine Learning models, is critical for complying with regulations like the GDPR's right to be forgotten and addressing copyright disputes in large models. Despite its rising importance, the field still lacks standardized tools, hindering reproducibility and evaluation. Here, we present, in an extensive way, ERASURE, a unified framework enabling reproducibility by implementing common unlearning techniques, evaluation metrics, and dedicated datasets. ERASURE advances research, ensures solution comparability, and facilitates reproducibility, addressing future legal and ethical challenges in data management.File | Dimensione | Formato | |
---|---|---|---|
1255.pdf
accesso aperto
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Pubblico - Tutti i diritti riservati
Dimensione
223 kB
Formato
Adobe PDF
|
223 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/3003568