Võrdle meetodeid
Vaata valitud meetodeid kõrvuti; erinevad read on esile tõstetud.
| Diferentsiaalne privaatsus× | Teadmise destilleerimine× | |
|---|---|---|
| Valdkond≠ | Privaatsus | Süvaõpe |
| Perekond | Machine learning | Machine learning |
| Tekkeaasta≠ | 2006 | 2015 |
| Looja≠ | Cynthia Dwork | Hinton, G., Vinyals, O. & Dean, J. |
| Tüüp≠ | Privacy-preserving randomized mechanism | Neural network compression (teacher–student) |
| Algallikas≠ | Dwork, C. (2006). Differential privacy. International Colloquium on Automata, Languages and Programming (ICALP), 1–12. DOI ↗ | Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop. link ↗ |
| Rööpnimetused | DP, epsilon-differential privacy, randomized privacy, Diferansiyel Gizlilik | Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation |
| Seotud≠ | 3 | 5 |
| Kokkuvõte≠ | Differential privacy is a mathematical framework for releasing statistical information about a dataset while providing rigorous guarantees that individual records cannot be identified or inferred. Introduced by Cynthia Dwork in 2006, it formalizes privacy as a probabilistic bound: any single individual's presence or absence in the dataset changes the output distribution by at most a multiplicative factor of e^ε, where ε is the privacy budget controlling the privacy–utility tradeoff. | Knowledge Distillation is a model-compression technique, introduced by Geoffrey Hinton and colleagues in 2015, that trains a small student model using the soft-label outputs of a large teacher model. Distilled models such as DistilBERT and TinyBERT reach roughly 97% of the larger model's performance while running far faster. |
| ScholarGateAndmestik ↗ |
|
|