The Earth Mover's Pinball Loss: Quantiles for Histogram-Valued Regression

• URL: http://arxiv.org/abs/2106.02051v1
• Date: Thu, 3 Jun 2021 18:00:04 GMT
• Title: The Earth Mover's Pinball Loss: Quantiles for Histogram-Valued Regression
• Authors: Florian List
• Abstract summary: We present a dedicated method for Deep Learning-based histogram regression, which incorporates cross-bin information and yields over possible histograms. We validate our method with an illustrative toy example, a football-related task, and an astrophysical computer vision problem.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Although ubiquitous in the sciences, histogram data have not received much attention by the Deep Learning community. Whilst regression and classification tasks for scalar and vector data are routinely solved by neural networks, a principled approach for estimating histogram labels as a function of an input vector or image is lacking in the literature. We present a dedicated method for Deep Learning-based histogram regression, which incorporates cross-bin information and yields distributions over possible histograms, expressed by $\tau$-quantiles of the cumulative histogram in each bin. The crux of our approach is a new loss function obtained by applying the pinball loss to the cumulative histogram, which for 1D histograms reduces to the Earth Mover's distance (EMD) in the special case of the median ($\tau = 0.5$), and generalizes it to arbitrary quantiles. We validate our method with an illustrative toy example, a football-related task, and an astrophysical computer vision problem. We show that with our loss function, the accuracy of the predicted median histograms is very similar to the standard EMD case (and higher than for per-bin loss functions such as cross-entropy), while the predictions become much more informative at almost no additional computational cost.

Related papers

• Investigating the Histogram Loss in Regression [16.83443393563771]
  Histogram Loss is a regression approach to learning the conditional distribution of a target variable. We show that the benefits of learning distributions in this setup come from improvements in optimization rather than modelling extra information.
  arXiv  Detail & Related papers  (2024-02-20T23:29:41Z)
• Deep Manifold Graph Auto-Encoder for Attributed Graph Embedding [51.75091298017941]
  This paper proposes a novel Deep Manifold (Variational) Graph Auto-Encoder (DMVGAE/DMGAE) for attributed graph data. The proposed method surpasses state-of-the-art baseline algorithms by a significant margin on different downstream tasks across popular datasets.
  arXiv  Detail & Related papers  (2024-01-12T17:57:07Z)
• ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detection [84.0718034981805]
  We introduce a novel framework called Anomaly-Denoised Autoencoders for Graph Anomaly Detection (ADA-GAD) In the first stage, we design a learning-free anomaly-denoised augmentation method to generate graphs with reduced anomaly levels. In the next stage, the decoders are retrained for detection on the original graph.
  arXiv  Detail & Related papers  (2023-12-22T09:02:01Z)
• Two-level histograms for dealing with outliers and heavy tail distributions [0.0]
  We focus on the G-Enum histogram method, which exploits the Minimum Description Length (MDL) principle to build histograms without any user parameter. We investigate on the limits of this method in the case of outliers or heavy-tailed distributions. The first level exploits a logarithmic transformation of the data to split the data set into a list of data subsets with a controlled range of values. The second level builds a sub-histogram for each data subset and aggregates them to obtain a complete histogram.
  arXiv  Detail & Related papers  (2023-06-09T09:57:18Z)
• A fast topological approach for predicting anomalies in time-varying graphs [0.0]
  A persistence diagram (PD) from topological data analysis (TDA) has become a popular descriptor of shape of data with a well-defined distance between points. This paper introduces a computationally efficient framework to extract shape information from graph data. In a real data application, our approach provides up to 22% gain in anomalous price prediction for the cryptocurrency transaction networks.
  arXiv  Detail & Related papers  (2023-05-11T01:54:45Z)
• Training trajectories, mini-batch losses and the curious role of the learning rate [13.848916053916618]
  We show that validated gradient descent plays a fundamental role in nearly all applications of deep learning. We propose a simple model and a geometric interpretation that allows to analyze the relationship between the gradients of mini-batches and the full batch. In particular, a very low loss value can be reached just one step of descent with large enough learning rate.
  arXiv  Detail & Related papers  (2023-01-05T21:58:46Z)
• Deep Autoregressive Regression [5.257719744958367]
  We show that a major limitation of regression using a mean-squared error loss is its sensitivity to the scale of its targets. We propose a novel approach to training deep learning models on real-valued regression targets, autoregressive regression.
  arXiv  Detail & Related papers  (2022-11-14T15:22:20Z)
• Distributionally Robust Semi-Supervised Learning Over Graphs [68.29280230284712]
  Semi-supervised learning (SSL) over graph-structured data emerges in many network science applications. To efficiently manage learning over graphs, variants of graph neural networks (GNNs) have been developed recently. Despite their success in practice, most of existing methods are unable to handle graphs with uncertain nodal attributes. Challenges also arise due to distributional uncertainties associated with data acquired by noisy measurements. A distributionally robust learning framework is developed, where the objective is to train models that exhibit quantifiable robustness against perturbations.
  arXiv  Detail & Related papers  (2021-10-20T14:23:54Z)
• Imputation-Free Learning from Incomplete Observations [73.15386629370111]
  We introduce the importance of guided gradient descent (IGSGD) method to train inference from inputs containing missing values without imputation. We employ reinforcement learning (RL) to adjust the gradients used to train the models via back-propagation. Our imputation-free predictions outperform the traditional two-step imputation-based predictions using state-of-the-art imputation methods.
  arXiv  Detail & Related papers  (2021-07-05T12:44:39Z)
• Distributed Training of Graph Convolutional Networks using Subgraph Approximation [72.89940126490715]
  We propose a training strategy that mitigates the lost information across multiple partitions of a graph through a subgraph approximation scheme. The subgraph approximation approach helps the distributed training system converge at single-machine accuracy.
  arXiv  Detail & Related papers  (2020-12-09T09:23:49Z)
• Semiparametric Nonlinear Bipartite Graph Representation Learning with Provable Guarantees [106.91654068632882]
  We consider the bipartite graph and formalize its representation learning problem as a statistical estimation problem of parameters in a semiparametric exponential family distribution. We show that the proposed objective is strongly convex in a neighborhood around the ground truth, so that a gradient descent-based method achieves linear convergence rate. Our estimator is robust to any model misspecification within the exponential family, which is validated in extensive experiments.
  arXiv  Detail & Related papers  (2020-03-02T16:40:36Z)

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.