Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
A Unified View of Differentially Private Deep Generative Modeling
Authors: Dingfan Chen, Raouf Kerkouche, Mario Fritz
TMLR 2024 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | In this paper, we present a novel unified view that systematizes these approaches. Our view provides a joint design space for systematically deriving methods that cater to different use cases. We then discuss the strengths, limitations, and inherent correlations between different approaches, aiming to shed light on crucial aspects and inspire future research. We conclude by presenting potential paths forward for the field of DP data generation, with the aim of steering the community toward making the next important steps in advancing privacy-preserving learning. |
| Researcher Affiliation | Academia | Dingfan Chen EMAIL CISPA Helmholtz Center for Information Security Raouf Kerkouche EMAIL CISPA Helmholtz Center for Information Security Mario Fritz EMAIL CISPA Helmholtz Center for Information Security |
| Pseudocode | No | The paper describes various mechanisms and algorithms conceptually, such as the steps for DP-SGD in Section 2.1.1 or the PATE framework in Section 2.1.2, but it does not present these or any other procedures in a structured pseudocode or algorithm block format. |
| Open Source Code | No | The paper is a survey and does not propose a new methodology or model for which source code would be released. While it lists GitHub links for *other* reviewed works in Table 1, it does not provide code for its own contribution (the unified view and taxonomy). |
| Open Datasets | No | The paper is a survey and theoretical work; it does not conduct its own experiments or evaluate models on specific datasets. Therefore, it does not provide access information for any datasets used by the authors. |
| Dataset Splits | No | The paper is a survey and theoretical work; it does not conduct its own experiments or evaluate models on specific datasets. Therefore, it does not describe dataset splits for experimental reproduction. |
| Hardware Specification | No | The paper is a survey and theoretical work; it does not conduct its own experiments. Therefore, it does not provide any hardware specifications used for running experiments. |
| Software Dependencies | No | The paper is a survey and theoretical work; it does not conduct its own experiments. Therefore, it does not list specific software dependencies with version numbers for experimental reproduction. |
| Experiment Setup | No | The paper is a survey and theoretical work; it does not conduct its own experiments. Therefore, it does not provide specific experimental setup details, hyperparameters, or training configurations. |