Evaluating the Disentanglement of Deep Generative Models through Manifold Topology

• URL: http://arxiv.org/abs/2006.03680v5
• Date: Wed, 17 Mar 2021 21:46:59 GMT
• Title: Evaluating the Disentanglement of Deep Generative Models through Manifold Topology
• Authors: Sharon Zhou, Eric Zelikman, Fred Lu, Andrew Y. Ng, Gunnar Carlsson, Stefano Ermon
• Abstract summary: 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.
• Score: 66.06153115971732
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning disentangled representations is regarded as a fundamental task for improving the generalization, robustness, and interpretability of generative models. However, measuring disentanglement has been challenging and inconsistent, often dependent on an ad-hoc external model or specific to a certain dataset. To address this, we present a method for quantifying disentanglement that only uses the generative model, by measuring the topological similarity of conditional submanifolds in the learned representation. This method showcases both unsupervised and supervised variants. To illustrate the effectiveness and applicability of our method, we empirically evaluate several state-of-the-art models across multiple datasets. We find that our method ranks models similarly to existing methods. We make ourcode publicly available at https://github.com/stanfordmlgroup/disentanglement.

Related papers

• Embedding-based statistical inference on generative models [10.948308354932639]
  We extend results related to embedding-based representations of generative models to classical statistical inference settings. We demonstrate that using the perspective space as the basis of a notion of "similar" is effective for multiple model-level inference tasks.
  arXiv  Detail & Related papers  (2024-10-01T22:28:39Z)
• COSE: A Consistency-Sensitivity Metric for Saliency on Image Classification [21.3855970055692]
  We present a set of metrics that utilize vision priors to assess the performance of saliency methods on image classification tasks. We show that although saliency methods are thought to be architecture-independent, most methods could better explain transformer-based models over convolutional-based models.
  arXiv  Detail & Related papers  (2023-09-20T01:06:44Z)
• Comparing Foundation Models using Data Kernels [13.099029073152257]
  We present a methodology for directly comparing the embedding space geometry of foundation models. Our methodology is grounded in random graph theory and enables valid hypothesis testing of embedding similarity. We show how our framework can induce a manifold of models equipped with a distance function that correlates strongly with several downstream metrics.
  arXiv  Detail & Related papers  (2023-05-09T02:01:07Z)
• Bayesian Beta-Bernoulli Process Sparse Coding with Deep Neural Networks [11.937283219047984]
  Several approximate inference methods have been proposed for deep discrete latent variable models. We propose a non-parametric iterative algorithm for learning discrete latent representations in such deep models. We evaluate our method across datasets with varying characteristics and compare our results to current amortized approximate inference methods.
  arXiv  Detail & Related papers  (2023-03-14T20:50:12Z)
• Evaluating Disentanglement in Generative Models Without Knowledge of Latent Factors [71.79984112148865]
  We introduce a method for ranking generative models based on the training dynamics exhibited during learning. Inspired by recent theoretical characterizations of disentanglement, our method does not require supervision of the underlying latent factors.
  arXiv  Detail & Related papers  (2022-10-04T17:27:29Z)
• Model-free Subsampling Method Based on Uniform Designs [5.661822729320697]
  We develop a low-GEFD data-driven subsampling method based on the existing uniform designs. Our method keeps robust under diverse model specifications while other popular subsampling methods are under-performing.
  arXiv  Detail & Related papers  (2022-09-08T07:47:56Z)
• Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations [64.85696493596821]
  In computer vision applications, generative counterfactual methods indicate how to perturb a model's input to change its prediction. We propose a counterfactual method that learns a perturbation in a disentangled latent space that is constrained using a diversity-enforcing loss. Our model improves the success rate of producing high-quality valuable explanations when compared to previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-03-18T12:57:34Z)
• Distilling Interpretable Models into Human-Readable Code [71.11328360614479]
  Human-readability is an important and desirable standard for machine-learned model interpretability. We propose to train interpretable models using conventional methods, and then distill them into concise, human-readable code. We describe a piecewise-linear curve-fitting algorithm that produces high-quality results efficiently and reliably across a broad range of use cases.
  arXiv  Detail & Related papers  (2021-01-21T01:46:36Z)
• Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage Modeling [54.94763543386523]
  Current autoencoder-based disentangled representation learning methods achieve disentanglement by penalizing the ( aggregate) posterior to encourage statistical independence of the latent factors. We present a novel multi-stage modeling approach where the disentangled factors are first learned using a penalty-based disentangled representation learning method. Then, the low-quality reconstruction is improved with another deep generative model that is trained to model the missing correlated latent variables.
  arXiv  Detail & Related papers  (2020-10-25T18:51:15Z)
• Goal-directed Generation of Discrete Structures with Conditional Generative Models [85.51463588099556]
  We introduce a novel approach to directly optimize a reinforcement learning objective, maximizing an expected reward. We test our methodology on two tasks: generating molecules with user-defined properties and identifying short python expressions which evaluate to a given target value.
  arXiv  Detail & Related papers  (2020-10-05T20:03:13Z)

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.