Understanding Deep Generative Models with Generalized Empirical Likelihoods

• URL: http://arxiv.org/abs/2306.09780v2
• Date: Mon, 7 Aug 2023 09:25:55 GMT
• Title: Understanding Deep Generative Models with Generalized Empirical Likelihoods
• Authors: Suman Ravuri, M\'elanie Rey, Shakir Mohamed, Marc Deisenroth
• Abstract summary: We show how to combine techniques from Maximum Mean Discrepancy and Generalized Empirical Likelihood to create distribution tests that retain per-sample interpretability. We find that such tests predict the degree of mode dropping and mode imbalance up to 60% better than metrics such as improved precision/recall.
• Score: 3.7978679293562587
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Understanding how well a deep generative model captures a distribution of high-dimensional data remains an important open challenge. It is especially difficult for certain model classes, such as Generative Adversarial Networks and Diffusion Models, whose models do not admit exact likelihoods. In this work, we demonstrate that generalized empirical likelihood (GEL) methods offer a family of diagnostic tools that can identify many deficiencies of deep generative models (DGMs). We show, with appropriate specification of moment conditions, that the proposed method can identify which modes have been dropped, the degree to which DGMs are mode imbalanced, and whether DGMs sufficiently capture intra-class diversity. We show how to combine techniques from Maximum Mean Discrepancy and Generalized Empirical Likelihood to create not only distribution tests that retain per-sample interpretability, but also metrics that include label information. We find that such tests predict the degree of mode dropping and mode imbalance up to 60% better than metrics such as improved precision/recall. We provide an implementation at https://github.com/deepmind/understanding_deep_generative_models_with_generalized_empirical_likeliho od/.

Related papers

• Unsupervised Model Diagnosis [49.36194740479798]
  This paper proposes Unsupervised Model Diagnosis (UMO) to produce semantic counterfactual explanations without any user guidance. Our approach identifies and visualizes changes in semantics, and then matches these changes to attributes from wide-ranging text sources.
  arXiv  Detail & Related papers  (2024-10-08T17:59:03Z)
• Towards a Theoretical Understanding of Memorization in Diffusion Models [76.85077961718875]
  Diffusion probabilistic models (DPMs) are being employed as mainstream models for Generative Artificial Intelligence (GenAI) We provide a theoretical understanding of memorization in both conditional and unconditional DPMs under the assumption of model convergence. We propose a novel data extraction method named textbfSurrogate condItional Data Extraction (SIDE) that leverages a time-dependent classifier trained on the generated data as a surrogate condition to extract training data from unconditional DPMs.
  arXiv  Detail & Related papers  (2024-10-03T13:17:06Z)
• Double Gradient Reversal Network for Single-Source Domain Generalization in Multi-mode Fault Diagnosis [1.9389881806157316]
  Domain-invariant fault features from single-mode data for unseen mode fault diagnosis poses challenges. Existing methods utilize a generator module to simulate samples of unseen modes. Double gradient reversal network (DGRN) is proposed to achieve high classification accuracy on unseen modes.
  arXiv  Detail & Related papers  (2024-07-19T02:06:41Z)
• Deep Generative Models through the Lens of the Manifold Hypothesis: A Survey and New Connections [15.191007332508198]
  We show that numerical instability of likelihoods in high ambient dimensions is unavoidable when modelling data with low intrinsic dimension. We then show that DGMs on learned representations of autoencoders can be interpreted as approximately minimizing Wasserstein distance.
  arXiv  Detail & Related papers  (2024-04-03T18:00:00Z)
• Toward the Identifiability of Comparative Deep Generative Models [7.5479347719819865]
  We propose a theory of identifiability for comparative Deep Generative Models (DGMs) We show that, while these models lack identifiability across a general class of mixing functions, they surprisingly become identifiable when the mixing function is piece-wise affine. We also investigate the impact of model misspecification, and empirically show that previously proposed regularization techniques for fitting comparative DGMs help with identifiability when the number of latent variables is not known in advance.
  arXiv  Detail & Related papers  (2024-01-29T06:10:54Z)
• Learning Invariant Molecular Representation in Latent Discrete Space [52.13724532622099]
  We propose a new framework for learning molecular representations that exhibit invariance and robustness against distribution shifts. Our model achieves stronger generalization against state-of-the-art baselines in the presence of various distribution shifts.
  arXiv  Detail & Related papers  (2023-10-22T04:06:44Z)
• Open Set Recognition with Conditional Probabilistic Generative Models [51.40872765917125]
  We propose Conditional Probabilistic Generative Models (CPGM) for open set recognition. CPGM can detect unknown samples but also classify known classes by forcing different latent features to approximate conditional Gaussian distributions. Experiment results on multiple benchmark datasets reveal that the proposed method significantly outperforms the baselines.
  arXiv  Detail & Related papers  (2020-08-12T06:23:49Z)
• Evaluating the Disentanglement of Deep Generative Models through Manifold Topology [66.06153115971732]
  We present a method for quantifying disentanglement that only uses the generative model. We empirically evaluate several state-of-the-art models across multiple datasets.
  arXiv  Detail & Related papers  (2020-06-05T20:54:11Z)
• SUOD: Accelerating Large-Scale Unsupervised Heterogeneous Outlier Detection [63.253850875265115]
  Outlier detection (OD) is a key machine learning (ML) task for identifying abnormal objects from general samples. We propose a modular acceleration system, called SUOD, to address it.
  arXiv  Detail & Related papers  (2020-03-11T00:22:50Z)
• Towards Out-of-Distribution Detection with Divergence Guarantee in Deep Generative Models [22.697643259435115]
  Deep generative models may assign higher likelihood to out-of-distribution (OOD) data than in-distribution (ID) data. We prove theorems to investigate the divergences in flow-based model. We propose two group anomaly detection methods.
  arXiv  Detail & Related papers  (2020-02-09T09:54:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.