A Large-scale Study on Training Sample Memorization in Generative Modeling
Many recent developments on generative models for natural images have relied on heuristically-motivated metrics that can be easily gamed by memorizing a small sample from the true distribution or training a model directly to improve the metric. In this work, we critically evaluate the gameability of the benchmarking procedure by running a competition which ultimately resulted in participants attempting to cheat. Our competition received over 11000 submitted models which allowed us to investigate memorization-aware metrics for measuring generative model performance. Specifically, we propose the Memorization-Informed Frechet Inception Distance (MiFID) and discuss ways to ensure that winning submissions were based on genuine improvements in perceptual quality. We evaluate the effectiveness of our benchmark by manually inspecting the code for the 1000 top-performing models and labeling different forms of memorization that were intentionally or unintentionally used. To facilitate future work on benchmarking generative models, we release generated images and our labels for these models as well as code to compute the MiFID metric.
Code (0)
등록된 구현이 없습니다.
Tasks
BenchmarkingMemorizationSimilar Papers 제목 키워드 기반
Counterfactual Influence as a Distributional Quantity
Machine learning models are known to memorize samples from their training data, raising concerns around privacy and generalization. Counterfactual self-influence is a popular metric to study memorization, quantifying how…
counterfactualimage-classificationImage ClassificationMemorization+1MemHunter: Automated and Verifiable Memorization Detection at Dataset-scale in LLMs
Large language models (LLMs) have been shown to memorize and reproduce content from their training data, raising significant privacy concerns, especially with web-scale datasets. Existing methods for detecting memorizati…
MemorizationBatch Normalization Amplifies Memorization and Privacy Risks
Batch Normalization (BN) is widely adopted to enable faster convergence and more stable training of deep neural networks. However, its impact on privacy and memorization has remained largely unexplored. In this work, we …
Generalizability of Memorization Neural Networks
The neural network memorization problem is to study the expressive power of neural networks to interpolate a finite dataset. Although memorization is widely believed to have a close relationship with the strong generaliz…
MemorizationFinding Memo: Extractive Memorization in Constrained Sequence Generation Tasks
Memorization presents a challenge for several constrained Natural Language Generation (NLG) tasks such as Neural Machine Translation (NMT), wherein the proclivity of neural models to memorize noisy and atypical samples r…
counterfactualMachine TranslationMemorizationNMT+1