Why have a Unified Predictive Uncertainty? Disentangling it using Deep Split Ensembles

• URL: http://arxiv.org/abs/2009.12406v1
• Date: Fri, 25 Sep 2020 19:15:26 GMT
• Title: Why have a Unified Predictive Uncertainty? Disentangling it using Deep Split Ensembles
• Authors: Utkarsh Sarawgi, Wazeer Zulfikar, Rishab Khincha, Pattie Maes
• Abstract summary: Understanding and quantifying uncertainty in black box Neural Networks (NNs) is critical when deployed in real-world settings such as healthcare. We propose a conceptually simple non-Bayesian approach, deep split ensemble, to disentangle the predictive uncertainties.
• Score: 39.29536042476913
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Understanding and quantifying uncertainty in black box Neural Networks (NNs) is critical when deployed in real-world settings such as healthcare. Recent works using Bayesian and non-Bayesian methods have shown how a unified predictive uncertainty can be modelled for NNs. Decomposing this uncertainty to disentangle the granular sources of heteroscedasticity in data provides rich information about its underlying causes. We propose a conceptually simple non-Bayesian approach, deep split ensemble, to disentangle the predictive uncertainties using a multivariate Gaussian mixture model. The NNs are trained with clusters of input features, for uncertainty estimates per cluster. We evaluate our approach on a series of benchmark regression datasets, while also comparing with unified uncertainty methods. Extensive analyses using dataset shits and empirical rule highlight our inherently well-calibrated models. Our work further demonstrates its applicability in a multi-modal setting using a benchmark Alzheimer's dataset and also shows how deep split ensembles can highlight hidden modality-specific biases. The minimal changes required to NNs and the training procedure, and the high flexibility to group features into clusters makes it readily deployable and useful. The source code is available at https://github.com/wazeerzulfikar/deep-split-ensembles

Related papers

• Simplex Clustering via sBeta with Applications to Online Adjustment of Black-Box Predictions [16.876111500144667]
  We introduce a novel probabilistic clustering method, referred to as k-sBetas. We provide a general maximum a posteriori (MAP) perspective of clustering distributions. Our code and comparisons with the existing simplex-clustering approaches and our introduced softmax-prediction benchmarks are publicly available.
  arXiv  Detail & Related papers  (2022-07-30T18:29:11Z)
• Look beyond labels: Incorporating functional summary information in Bayesian neural networks [11.874130244353253]
  We present a simple approach to incorporate summary information about the predicted probability. The available summary information is incorporated as augmented data and modeled with a Dirichlet process. We show how the method can inform the model about task difficulty or class imbalance.
  arXiv  Detail & Related papers  (2022-07-04T07:06:45Z)
• How to Combine Variational Bayesian Networks in Federated Learning [0.0]
  Federated learning enables multiple data centers to train a central model collaboratively without exposing any confidential data. deterministic models are capable of performing high prediction accuracy, their lack of calibration and capability to quantify uncertainty is problematic for safety-critical applications. We study the effects of various aggregation schemes for variational Bayesian neural networks.
  arXiv  Detail & Related papers  (2022-06-22T07:53:12Z)
• Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning [78.83598532168256]
  Marginal-likelihood based model-selection is rarely used in deep learning due to estimation difficulties. Our work shows that marginal likelihoods can improve generalization and be useful when validation data is unavailable.
  arXiv  Detail & Related papers  (2021-04-11T09:50:24Z)
• Improving Uncertainty Calibration via Prior Augmented Data [56.88185136509654]
  Neural networks have proven successful at learning from complex data distributions by acting as universal function approximators. They are often overconfident in their predictions, which leads to inaccurate and miscalibrated probabilistic predictions. We propose a solution by seeking out regions of feature space where the model is unjustifiably overconfident, and conditionally raising the entropy of those predictions towards that of the prior distribution of the labels.
  arXiv  Detail & Related papers  (2021-02-22T07:02:37Z)
• Investigating maximum likelihood based training of infinite mixtures for uncertainty quantification [16.30200782698554]
  We investigate the effect of training an infinite mixture distribution with the maximum likelihood method instead of variational inference. We find that the proposed objective leads to adversarial networks with an increased predictive variance.
  arXiv  Detail & Related papers  (2020-08-07T14:55:53Z)
• Probabilistic Neighbourhood Component Analysis: Sample Efficient Uncertainty Estimation in Deep Learning [25.8227937350516]
  We show that uncertainty estimation capability of state-of-the-art BNNs and Deep Ensemble models degrades significantly when the amount of training data is small. We propose a probabilistic generalization of the popular sample-efficient non-parametric kNN approach. Our approach enables deep kNN to accurately quantify underlying uncertainties in its prediction.
  arXiv  Detail & Related papers  (2020-07-18T21:36:31Z)
• Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift [100.52588638477862]
  We develop an approximate Bayesian inference scheme based on posterior regularisation. We demonstrate the utility of our method in the context of transferring prognostic models of prostate cancer across globally diverse populations.
  arXiv  Detail & Related papers  (2020-06-26T13:50:19Z)
• Diversity inducing Information Bottleneck in Model Ensembles [73.80615604822435]
  In this paper, we target the problem of generating effective ensembles of neural networks by encouraging diversity in prediction. We explicitly optimize a diversity inducing adversarial loss for learning latent variables and thereby obtain diversity in the output predictions necessary for modeling multi-modal data. Compared to the most competitive baselines, we show significant improvements in classification accuracy, under a shift in the data distribution.
  arXiv  Detail & Related papers  (2020-03-10T03:10:41Z)
• Uncertainty Estimation Using a Single Deep Deterministic Neural Network [66.26231423824089]
  We propose a method for training a deterministic deep model that can find and reject out of distribution data points at test time with a single forward pass. We scale training in these with a novel loss function and centroid updating scheme and match the accuracy of softmax models.
  arXiv  Detail & Related papers  (2020-03-04T12:27:36Z)

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.