Mixture Data for Training Cannot Ensure Out-of-distribution Generalization

• URL: http://arxiv.org/abs/2312.16243v4
• Date: Tue, 23 Apr 2024 07:43:10 GMT
• Title: Mixture Data for Training Cannot Ensure Out-of-distribution Generalization
• Authors: Songming Zhang, Yuxiao Luo, Qizhou Wang, Haoang Chi, Xiaofeng Chen, Bo Han, Jinyan Li,
• Abstract summary: We show that increasing the size of training data does not always lead to a reduction in the test generalization error. In this work, we quantitatively redefine OOD data as those situated outside the convex hull of mixed training data. Our proof of the new risk bound agrees that the efficacy of well-trained models can be guaranteed for unseen data.
• Score: 21.801115344132114
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks often face generalization problems to handle out-of-distribution (OOD) data, and there remains a notable theoretical gap between the contributing factors and their respective impacts. Literature evidence from in-distribution data has suggested that generalization error can shrink if the size of mixture data for training increases. However, when it comes to OOD samples, this conventional understanding does not hold anymore -- Increasing the size of training data does not always lead to a reduction in the test generalization error. In fact, diverse trends of the errors have been found across various shifting scenarios including those decreasing trends under a power-law pattern, initial declines followed by increases, or continuous stable patterns. Previous work has approached OOD data qualitatively, treating them merely as samples unseen during training, which are hard to explain the complicated non-monotonic trends. In this work, we quantitatively redefine OOD data as those situated outside the convex hull of mixed training data and establish novel generalization error bounds to comprehend the counterintuitive observations better. Our proof of the new risk bound agrees that the efficacy of well-trained models can be guaranteed for unseen data within the convex hull; More interestingly, but for OOD data beyond this coverage, the generalization cannot be ensured, which aligns with our observations. Furthermore, we attempted various OOD techniques to underscore that our results not only explain insightful observations in recent OOD generalization work, such as the significance of diverse data and the sensitivity to unseen shifts of existing algorithms, but it also inspires a novel and effective data selection strategy.

Related papers

• Out-of-Distribution Learning with Human Feedback [26.398598663165636]
  This paper presents a novel framework for OOD learning with human feedback. Our framework capitalizes on the freely available unlabeled data in the wild. By exploiting human feedback, we enhance the robustness and reliability of machine learning models.
  arXiv  Detail & Related papers  (2024-08-14T18:49:27Z)
• Rethinking Out-of-Distribution Detection on Imbalanced Data Distribution [38.844580833635725]
  We present a training-time regularization technique to mitigate the bias and boost imbalanced OOD detectors across architecture designs. Our method translates into consistent improvements on the representative CIFAR10-LT, CIFAR100-LT, and ImageNet-LT benchmarks.
  arXiv  Detail & Related papers  (2024-07-23T12:28:59Z)
• On the Benefits of Over-parameterization for Out-of-Distribution Generalization [28.961538657831788]
  We investigate the performance of a machine learning model in terms of Out-of-Distribution (OOD) loss under benign overfitting conditions. We show that further increasing the model's parameterization can significantly reduce the OOD loss. These insights explain the empirical phenomenon of enhanced OOD generalization through model ensembles.
  arXiv  Detail & Related papers  (2024-03-26T11:01:53Z)
• Early Period of Training Impacts Out-of-Distribution Generalization [56.283944756315066]
  We investigate the relationship between learning dynamics and OOD generalization during the early period of neural network training. We show that selecting the number of trainable parameters at different times during training has a minuscule impact on ID results. The absolute values of sharpness and trace of Fisher Information at the initial period of training are not indicative for OOD generalization.
  arXiv  Detail & Related papers  (2024-03-22T13:52:53Z)
• Causality and Independence Enhancement for Biased Node Classification [56.38828085943763]
  We propose a novel Causality and Independence Enhancement (CIE) framework, applicable to various graph neural networks (GNNs) Our approach estimates causal and spurious features at the node representation level and mitigates the influence of spurious correlations. Our approach CIE not only significantly enhances the performance of GNNs but outperforms state-of-the-art debiased node classification methods.
  arXiv  Detail & Related papers  (2023-10-14T13:56:24Z)
• LINe: Out-of-Distribution Detection by Leveraging Important Neurons [15.797257361788812]
  We introduce a new aspect for analyzing the difference in model outputs between in-distribution data and OOD data. We propose a novel method, Leveraging Important Neurons (LINe), for post-hoc Out of distribution detection.
  arXiv  Detail & Related papers  (2023-03-24T13:49:05Z)
• Agree to Disagree: Diversity through Disagreement for Better Transferability [54.308327969778155]
  We propose D-BAT (Diversity-By-disAgreement Training), which enforces agreement among the models on the training data. We show how D-BAT naturally emerges from the notion of generalized discrepancy.
  arXiv  Detail & Related papers  (2022-02-09T12:03:02Z)
• General Greedy De-bias Learning [163.65789778416172]
  We propose a General Greedy De-bias learning framework (GGD), which greedily trains the biased models and the base model like gradient descent in functional space. GGD can learn a more robust base model under the settings of both task-specific biased models with prior knowledge and self-ensemble biased model without prior knowledge.
  arXiv  Detail & Related papers  (2021-12-20T14:47:32Z)
• Learn what you can't learn: Regularized Ensembles for Transductive Out-of-distribution Detection [76.39067237772286]
  We show that current out-of-distribution (OOD) detection algorithms for neural networks produce unsatisfactory results in a variety of OOD detection scenarios. This paper studies how such "hard" OOD scenarios can benefit from adjusting the detection method after observing a batch of the test data. We propose a novel method that uses an artificial labeling scheme for the test data and regularization to obtain ensembles of models that produce contradictory predictions only on the OOD samples in a test batch.
  arXiv  Detail & Related papers  (2020-12-10T16:55:13Z)
• On the Benefits of Invariance in Neural Networks [56.362579457990094]
  We show that training with data augmentation leads to better estimates of risk and thereof gradients, and we provide a PAC-Bayes generalization bound for models trained with data augmentation. We also show that compared to data augmentation, feature averaging reduces generalization error when used with convex losses, and tightens PAC-Bayes bounds.
  arXiv  Detail & Related papers  (2020-05-01T02:08:58Z)

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.