On Disentangled Representations Learned From Correlated Data

• URL: http://arxiv.org/abs/2006.07886v3
• Date: Fri, 16 Jul 2021 09:28:05 GMT
• Title: On Disentangled Representations Learned From Correlated Data
• Authors: Frederik Tr\"auble, Elliot Creager, Niki Kilbertus, Francesco Locatello, Andrea Dittadi, Anirudh Goyal, Bernhard Sch\"olkopf, Stefan Bauer
• Abstract summary: We bridge the gap to real-world scenarios by analyzing the behavior of the most prominent disentanglement approaches on correlated data. We show that systematically induced correlations in the dataset are being learned and reflected in the latent representations. We also demonstrate how to resolve these latent correlations, either using weak supervision during training or by post-hoc correcting a pre-trained model with a small number of labels.
• Score: 59.41587388303554
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The focus of disentanglement approaches has been on identifying independent factors of variation in data. However, the causal variables underlying real-world observations are often not statistically independent. In this work, we bridge the gap to real-world scenarios by analyzing the behavior of the most prominent disentanglement approaches on correlated data in a large-scale empirical study (including 4260 models). We show and quantify that systematically induced correlations in the dataset are being learned and reflected in the latent representations, which has implications for downstream applications of disentanglement such as fairness. We also demonstrate how to resolve these latent correlations, either using weak supervision during training or by post-hoc correcting a pre-trained model with a small number of labels.

Related papers

• Trade-off Between Dependence and Complexity for Nonparametric Learning -- an Empirical Process Approach [10.27974860479791]
  In many applications where the data exhibit temporal dependencies, the corresponding empirical processes are much less understood. We present a general bound on the expected supremum of empirical processes under standard $beta/rho$-mixing assumptions. We show that even under long-range dependence, it is possible to attain the same rates as in the i.i.d. setting.
  arXiv  Detail & Related papers  (2024-01-17T05:08:37Z)
• Spurious Correlations and Where to Find Them [17.1264393170134]
  Spurious correlations occur when a model learns unreliable features from the data. We collect some of the commonly studied hypotheses behind the occurrence of spurious correlations. We investigate their influence on standard ERM baselines using synthetic datasets generated from causal graphs.
  arXiv  Detail & Related papers  (2023-08-21T21:06:36Z)
• A Causal Ordering Prior for Unsupervised Representation Learning [27.18951912984905]
  Causal representation learning argues that factors of variation in a dataset are, in fact, causally related. We propose a fully unsupervised representation learning method that considers a data generation process with a latent additive noise model.
  arXiv  Detail & Related papers  (2023-07-11T18:12:05Z)
• Stubborn Lexical Bias in Data and Models [50.79738900885665]
  We use a new statistical method to examine whether spurious patterns in data appear in models trained on the data. We apply an optimization approach to *reweight* the training data, reducing thousands of spurious correlations. Surprisingly, though this method can successfully reduce lexical biases in the training data, we still find strong evidence of corresponding bias in the trained models.
  arXiv  Detail & Related papers  (2023-06-03T20:12:27Z)
• Towards Causal Representation Learning and Deconfounding from Indefinite Data [17.793702165499298]
  Non-statistical data (e.g., images, text, etc.) encounters significant conflicts in terms of properties and methods with traditional causal data. We redefine causal data from two novel perspectives and then propose three data paradigms. We implement the above designs as a dynamic variational inference model, tailored to learn causal representation from indefinite data.
  arXiv  Detail & Related papers  (2023-05-04T08:20:37Z)
• Biases in Inverse Ising Estimates of Near-Critical Behaviour [0.0]
  Inverse inference allows pairwise interactions to be reconstructed from empirical correlations. We show that estimators used for this inference, such as Pseudo-likelihood (PLM), are biased. Data-driven methods are explored and applied to a functional magnetic resonance imaging (fMRI) dataset from neuroscience.
  arXiv  Detail & Related papers  (2023-01-13T14:01:43Z)
• OR-Net: Pointwise Relational Inference for Data Completion under Partial Observation [51.083573770706636]
  This work uses relational inference to fill in the incomplete data. We propose Omni-Relational Network (OR-Net) to model the pointwise relativity in two aspects.
  arXiv  Detail & Related papers  (2021-05-02T06:05:54Z)
• Efficient Causal Inference from Combined Observational and Interventional Data through Causal Reductions [68.6505592770171]
  Unobserved confounding is one of the main challenges when estimating causal effects. We propose a novel causal reduction method that replaces an arbitrary number of possibly high-dimensional latent confounders. We propose a learning algorithm to estimate the parameterized reduced model jointly from observational and interventional data.
  arXiv  Detail & Related papers  (2021-03-08T14:29:07Z)
• Accounting for Unobserved Confounding in Domain Generalization [107.0464488046289]
  This paper investigates the problem of learning robust, generalizable prediction models from a combination of datasets. Part of the challenge of learning robust models lies in the influence of unobserved confounders. We demonstrate the empirical performance of our approach on healthcare data from different modalities.
  arXiv  Detail & Related papers  (2020-07-21T08:18:06Z)
• An Investigation of Why Overparameterization Exacerbates Spurious Correlations [98.3066727301239]
  We identify two key properties of the training data that drive this behavior. We show how the inductive bias of models towards "memorizing" fewer examples can cause over parameterization to hurt.
  arXiv  Detail & Related papers  (2020-05-09T01:59:13Z)

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.