Memorization in deep learning: A survey
Deep Learning (DL) powered by Deep Neural Networks (DNNs) has revolutionized various domains, yet understanding the intricacies of DNN decision-making and learning processes remains a significant challenge. Recent investigations have uncovered an interesting memorization phenomenon in which DNNs tend to memorize specific details from examples rather than learning general patterns, affecting model generalization, security, and privacy. This raises critical questions about the nature of generalization in DNNs and their susceptibility to security breaches. In this survey, we present a systematic framework to organize memorization definitions based on the generalization and security/privacy domains and summarize memorization evaluation methods at both the example and model levels. Through a comprehensive literature review, we explore DNN memorization behaviors and their impacts on security and privacy. We also introduce privacy vulnerabilities caused by memorization and the phenomenon of forgetting and explore its connection with memorization. Furthermore, we spotlight various applications leveraging memorization and forgetting mechanisms, including noisy label learning, privacy preservation, and model enhancement. This survey offers the first-in-kind understanding of memorization in DNNs, providing insights into its challenges and opportunities for enhancing AI development while addressing critical ethical concerns.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingDeep LearningMemorizationSurveySimilar Papers 제목 키워드 기반
Trustworthy Machine Learning via Memorization and the Granular Long-Tail: A Survey on Interactions, Tradeoffs, and Beyond
The role of memorization in machine learning (ML) has garnered significant attention, particularly as modern models are empirically observed to memorize fragments of training data. Previous theoretical analyses, such as …
AttributeFairnessMemorizationUndesirable Memorization in Large Language Models: A Survey
While recent research increasingly showcases the remarkable capabilities of Large Language Models (LLMs), it's vital to confront their hidden pitfalls. Among these challenges, the issue of memorization stands out, posing…
MemorizationRetrieval-augmented GenerationSurveyForgetting Curve: A Reliable Method for Evaluating Memorization Capability for Long-context Models
Numerous recent works target to extend effective context length for language models and various methods, tasks and benchmarks exist to measure model's effective memorization length. However, through thorough investigatio…
MemorizationSurveying Generative AI's Economic Expectations
I introduce a survey of economic expectations formed by querying a large language model (LLM)'s expectations of various financial and macroeconomic variables based on a sample of news articles from the Wall Street Journa…
ArticlesLanguage ModelingLanguage ModellingLarge Language Model+3Plausible but Not Valid: A Psychometric Audit of LLMs as Synthetic Survey Respondents
Large language models (LLMs) are increasingly used as synthetic survey respondents, but existing evaluations ask whether answers look plausible at the individual level. We argue the right question is psychometric: do LLM…