A Neighbourhood-Aware Differential Privacy Mechanism for Static Word Embeddings


Bollegala, Danushka ORCID: 0000-0003-4476-7003, Otake, Shuichi, Machide, Tomoya and Kawarabayashi, Ken-ichi (2023) A Neighbourhood-Aware Differential Privacy Mechanism for Static Word Embeddings. In: Findings of the Association for Computational Linguistics: IJCNLP-AACL 2023 (Findings), 2023-11 - 2023-11, Bali, Indonesia.

[img] PDF
Diff_Privacy__IJCNLP_2023_.pdf - Author Accepted Manuscript
Download (1MB) | Preview

Abstract

We propose a Neighbourhood-Aware Differential Privacy (NADP) mechanism considering the neighbourhood of a word in a pretrained static word embedding space to determine the minimal amount of noise required to guarantee a specified privacy level. We first construct a nearest neighbour graph over the words using their embeddings, and factorise it into a set of connected components (i.e. neighbourhoods). We then separately apply different levels of Gaussian noise to the words in each neighbourhood, determined by the set of words in that neighbourhood. Experiments show that our proposed NADP mechanism consistently outperforms multiple previously proposed DP mechanisms such as Laplacian, Gaussian, and Mahalanobis in multiple downstream tasks, while guaranteeing higher levels of privacy.

Item Type: Conference or Workshop Item (Unspecified)
Divisions: Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science
Depositing User: Symplectic Admin
Date Deposited: 09 Nov 2023 09:17
Last Modified: 14 Apr 2024 22:01
DOI: 10.18653/v1/2023.findings-ijcnlp.7
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3176697
Dimensions
Altmetric
CORE (COnnecting REpositories)