paper-with-me

Papers

On Memorization in Probabilistic Deep Generative Models

2021-12-01 · NeurIPS 2021 12 · Gerrit van den Burg, Chris Williams

Recent advances in deep generative models have led to impressive results in a variety of application domains. Motivated by the possibility that deep learning models might memorize part of the input data, there have been increased efforts to understand how memorization arises. In this work, we extend a recently proposed measure of memorization for supervised learning (Feldman, 2019) to the unsupervised density estimation problem and adapt it to be more computationally efficient. Next, we present a study that demonstrates how memorization can occur in probabilistic deep generative models such as variational autoencoders. This reveals that the form of memorization to which these models are susceptible differs fundamentally from mode collapse and overfitting. Furthermore, we show that the proposed memorization score measures a phenomenon that is not captured by commonly-used nearest neighbor tests. Finally, we discuss several strategies that can be used to limit memorization in practice. Our work thus provides a framework for understanding problematic memorization in probabilistic generative models.

📄 PDF Abstract BibTeX

Code (1)

alan-turing-institute/memorization 공식 구현 pytorch

Tasks

Density EstimationMemorization

Similar Papers 제목 키워드 기반

On Memorization in Probabilistic Deep Generative Models

2021-06-06 · Gerrit J. J. van den Burg, Christopher K. I. Williams

Recent advances in deep generative models have led to impressive results in a variety of application domains. Motivated by the possibility that deep learning models might memorize part of the input data, there have been …

Density EstimationMemorization

A Probabilistic Fluctuation based Membership Inference Attack for Diffusion Models

2023-08-23 · Wenjie Fu, Huandong Wang, Liyuan Zhang, Chen Gao 외

Membership Inference Attack (MIA) identifies whether a record exists in a machine learning model's training set by querying the model. MIAs on the classic classification models have been well-studied, and recent works ha…

Inference AttackMembership Inference AttackMemorization

Measuring memorization through probabilistic discoverable extraction

2024-10-25 · Jamie Hayes, Marika Swanberg, Harsh Chaudhari, Itay Yona 외

Large language models (LLMs) are susceptible to memorizing training data, raising concerns due to the potential extraction of sensitive information. Current methods to measure memorization rates of LLMs, primarily discov…

Memorization

Bigger Isn't Always Memorizing: Early Stopping Overparameterized Diffusion Models

2025-05-22 · Alessandro Favero, Antonio Sclocchi, Matthieu Wyart

Diffusion probabilistic models have become a cornerstone of modern generative AI, yet the mechanisms underlying their generalization remain poorly understood. In fact, if these models were perfectly minimizing their trai…

Memorization

Extracting Training Data from Unconditional Diffusion Models

2024-06-18 · Yunhao Chen, Xingjun Ma, Difan Zou, Yu-Gang Jiang

As diffusion probabilistic models (DPMs) are being employed as mainstream models for generative artificial intelligence (AI), the study of their memorization of the raw training data has attracted growing attention. Exis…

Memorization