OoD-Bench: Benchmarking and Understanding Out-of-Distribution Generalization Datasets and Algorithms

• URL: http://arxiv.org/abs/2106.03721v1
• Date: Mon, 7 Jun 2021 15:34:36 GMT
• Title: OoD-Bench: Benchmarking and Understanding Out-of-Distribution Generalization Datasets and Algorithms
• Authors: Nanyang Ye, Kaican Li, Lanqing Hong, Haoyue Bai, Yiting Chen, Fengwei Zhou, Zhenguo Li
• Abstract summary: We show that existing OoD algorithms that outperform empirical risk minimization on one distribution shift usually have limitations on the other distribution shift. The new benchmark may serve as a strong foothold that can be resorted to by future OoD generalization research.
• Score: 28.37021464780398
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep learning has achieved tremendous success with independent and identically distributed (i.i.d.) data. However, the performance of neural networks often degenerates drastically when encountering out-of-distribution (OoD) data, i.e., training and test data are sampled from different distributions. While a plethora of algorithms has been proposed to deal with OoD generalization, our understanding of the data used to train and evaluate these algorithms remains stagnant. In this work, we position existing datasets and algorithms from various research areas (e.g., domain generalization, stable learning, invariant risk minimization) seemingly unconnected into the same coherent picture. First, we identify and measure two distinct kinds of distribution shifts that are ubiquitous in various datasets. Next, we compare various OoD generalization algorithms with a new benchmark dominated by the two distribution shifts. Through extensive experiments, we show that existing OoD algorithms that outperform empirical risk minimization on one distribution shift usually have limitations on the other distribution shift. The new benchmark may serve as a strong foothold that can be resorted to by future OoD generalization research.

Related papers

• Scalable Decentralized Algorithms for Online Personalized Mean Estimation [12.002609934938224]
  This study focuses on a simplified version of the overarching problem, where each agent collects samples from a real-valued distribution over time to estimate its mean. We introduce two collaborative mean estimation algorithms: one draws inspiration from belief propagation, while the other employs a consensus-based approach.
  arXiv  Detail & Related papers  (2024-02-20T08:30:46Z)
• Biquality Learning: a Framework to Design Algorithms Dealing with Closed-Set Distribution Shifts [0.0]
  We think the biquality data setup is a suitable framework for designing such algorithms. The trusted and untrusted datasets available at training time make designing algorithms dealing with any distribution shifts possible. We experiment with two novel methods to synthetically introduce concept drift and class-conditional shifts in real-world datasets.
  arXiv  Detail & Related papers  (2023-08-29T08:57:47Z)
• DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalization [58.704753031608625]
  Time series is one of the most challenging modalities in machine learning research. OOD detection and generalization on time series tend to suffer due to its non-stationary property. We propose DIVERSIFY, a framework for OOD detection and generalization on dynamic distributions of time series.
  arXiv  Detail & Related papers  (2023-08-04T12:27:11Z)
• Distribution Shift Inversion for Out-of-Distribution Prediction [57.22301285120695]
  We propose a portable Distribution Shift Inversion algorithm for Out-of-Distribution (OoD) prediction. We show that our method provides a general performance gain when plugged into a wide range of commonly used OoD algorithms.
  arXiv  Detail & Related papers  (2023-06-14T08:00:49Z)
• Anomaly Detection under Distribution Shift [24.094884041252044]
  Anomaly detection (AD) is a crucial machine learning task that aims to learn patterns from a set of normal training samples to identify abnormal samples in test data. Most existing AD studies assume that the training and test data are drawn from the same data distribution, but the test data can have large distribution shifts. We introduce a novel robust AD approach to diverse distribution shifts by minimizing the distribution gap between in-distribution and OOD normal samples in both the training and inference stages.
  arXiv  Detail & Related papers  (2023-03-24T07:39:08Z)
• Modeling the Data-Generating Process is Necessary for Out-of-Distribution Generalization [23.302060306322506]
  Real-world data often has multiple distribution shifts over different attributes. No state-of-the-art DG algorithm performs consistently well on all shifts. We develop Causally Adaptive Constraint Minimization (CACM), an algorithm that uses knowledge about the data-generating process to adaptively identify and apply the correct independence constraints for regularization.
  arXiv  Detail & Related papers  (2022-06-15T22:35:06Z)
• An Information-theoretical Approach to Semi-supervised Learning under Covariate-shift [24.061858945664856]
  A common assumption in semi-supervised learning is that the labeled, unlabeled, and test data are drawn from the same distribution. We propose an approach for semi-supervised learning algorithms that is capable of addressing this issue. Our framework also recovers some popular methods, including entropy minimization and pseudo-labeling.
  arXiv  Detail & Related papers  (2022-02-24T14:25:14Z)
• Decentralized Local Stochastic Extra-Gradient for Variational Inequalities [125.62877849447729]
  We consider distributed variational inequalities (VIs) on domains with the problem data that is heterogeneous (non-IID) and distributed across many devices. We make a very general assumption on the computational network that covers the settings of fully decentralized calculations. We theoretically analyze its convergence rate in the strongly-monotone, monotone, and non-monotone settings.
  arXiv  Detail & Related papers  (2021-06-15T17:45:51Z)
• Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data [77.88594632644347]
  Decentralized training of deep learning models is a key element for enabling data privacy and on-device learning over networks. In realistic learning scenarios, the presence of heterogeneity across different clients' local datasets poses an optimization challenge. We propose a novel momentum-based method to mitigate this decentralized training difficulty.
  arXiv  Detail & Related papers  (2021-02-09T11:27:14Z)
• 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)
• Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data [87.61504710345528]
  We propose two strategies for freeing a neural network from tuning with OoD data, while improving its OoD detection performance. We specifically propose to decompose confidence scoring as well as a modified input pre-processing method. Our further analysis on a larger scale image dataset shows that the two types of distribution shifts, specifically semantic shift and non-semantic shift, present a significant difference.
  arXiv  Detail & Related papers  (2020-02-26T04:18:25Z)

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.