Evaluating Disentanglement in Generative Models Without Knowledge of
Latent Factors
- URL: http://arxiv.org/abs/2210.01760v1
- Date: Tue, 4 Oct 2022 17:27:29 GMT
- Title: Evaluating Disentanglement in Generative Models Without Knowledge of
Latent Factors
- Authors: Chester Holtz, Gal Mishne, and Alexander Cloninger
- Abstract summary: 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.
- Score: 71.79984112148865
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Probabilistic generative models provide a flexible and systematic framework
for learning the underlying geometry of data. However, model selection in this
setting is challenging, particularly when selecting for ill-defined qualities
such as disentanglement or interpretability. In this work, we address this gap
by introducing 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. We evaluate our approach by demonstrating the
need for disentanglement metrics which do not require labels\textemdash the
underlying generative factors. We additionally demonstrate that our approach
correlates with baseline supervised methods for evaluating disentanglement.
Finally, we show that our method can be used as an unsupervised indicator for
downstream performance on reinforcement learning and fairness-classification
problems.
Related papers
- Fairness and Sparsity within Rashomon sets: Enumeration-Free Exploration and Characterization [4.554831326324025]
We introduce an enumeration-free method based on mathematical programming to characterize various properties such as fairness or sparsity.
We apply our approach to two hypothesis classes: scoring systems and decision diagrams.
arXiv Detail & Related papers (2025-02-07T19:43:34Z) - Benchmarks as Microscopes: A Call for Model Metrology [76.64402390208576]
Modern language models (LMs) pose a new challenge in capability assessment.
To be confident in our metrics, we need a new discipline of model metrology.
arXiv Detail & Related papers (2024-07-22T17:52:12Z) - Time-series Generation by Contrastive Imitation [87.51882102248395]
We study a generative framework that seeks to combine the strengths of both: Motivated by a moment-matching objective to mitigate compounding error, we optimize a local (but forward-looking) transition policy.
At inference, the learned policy serves as the generator for iterative sampling, and the learned energy serves as a trajectory-level measure for evaluating sample quality.
arXiv Detail & Related papers (2023-11-02T16:45:25Z) - Class-Incremental Mixture of Gaussians for Deep Continual Learning [15.49323098362628]
We propose end-to-end incorporation of the mixture of Gaussians model into the continual learning framework.
We show that our model can effectively learn in memory-free scenarios with fixed extractors.
arXiv Detail & Related papers (2023-07-09T04:33:19Z) - Poisson Reweighted Laplacian Uncertainty Sampling for Graph-based Active
Learning [1.6752182911522522]
We show that uncertainty sampling is sufficient to achieve exploration versus exploitation in graph-based active learning.
In particular, we use a recently developed algorithm, Poisson ReWeighted Laplace Learning (PWLL) for the classifier.
We present experimental results on a number of graph-based image classification problems.
arXiv Detail & Related papers (2022-10-27T22:07:53Z) - Multicriteria interpretability driven Deep Learning [0.0]
Deep Learning methods are renowned for their performances, yet their lack of interpretability prevents them from high-stakes contexts.
Recent model methods address this problem by providing post-hoc interpretability methods by reverse-engineering the model's inner workings.
We propose a Multicriteria agnostic technique that allows to control the feature effects on the model's outcome by injecting knowledge in the objective function.
arXiv Detail & Related papers (2021-11-28T09:41:13Z) - Learning from others' mistakes: Avoiding dataset biases without modeling
them [111.17078939377313]
State-of-the-art natural language processing (NLP) models often learn to model dataset biases and surface form correlations instead of features that target the intended task.
Previous work has demonstrated effective methods to circumvent these issues when knowledge of the bias is available.
We show a method for training models that learn to ignore these problematic correlations.
arXiv Detail & Related papers (2020-12-02T16:10:54Z) - A Sober Look at the Unsupervised Learning of Disentangled
Representations and their Evaluation [63.042651834453544]
We show that the unsupervised learning of disentangled representations is impossible without inductive biases on both the models and the data.
We observe that while the different methods successfully enforce properties "encouraged" by the corresponding losses, well-disentangled models seemingly cannot be identified without supervision.
Our results suggest that future work on disentanglement learning should be explicit about the role of inductive biases and (implicit) supervision.
arXiv Detail & Related papers (2020-10-27T10:17:15Z) - 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)
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.