Mitigating covariate shift in non-colocated data with learned parameter priors

• URL: http://arxiv.org/abs/2411.06499v1
• Date: Sun, 10 Nov 2024 15:48:29 GMT
• Title: Mitigating covariate shift in non-colocated data with learned parameter priors
• Authors: Behraj Khan, Behroz Mirza, Nouman Durrani, Tahir Syed,
• Abstract summary: We present textitFragmentation-induced co-shift remediation ($FIcsR$), which minimizes an $f$-divergence between a fragment's covariate distribution and that of the standard cross-validation baseline. We run extensive classification experiments on multiple data classes, over $40$ datasets, and with data batched over multiple sequence lengths. The results are promising under all these conditions; with improved accuracy against batch and fold state-of-the-art by more than $5%$ and $10%$, respectively.
• Score: 0.0
• License:
• Abstract: When training data are distributed across{ time or space,} covariate shift across fragments of training data biases cross-validation, compromising model selection and assessment. We present \textit{Fragmentation-Induced covariate-shift Remediation} ($FIcsR$), which minimizes an $f$-divergence between a fragment's covariate distribution and that of the standard cross-validation baseline. We s{how} an equivalence with popular importance-weighting methods. {The method}'s numerical solution poses a computational challenge owing to the overparametrized nature of a neural network, and we derive a Fisher Information approximation. When accumulated over fragments, this provides a global estimate of the amount of shift remediation thus far needed, and we incorporate that as a prior via the minimization objective. In the paper, we run extensive classification experiments on multiple data classes, over $40$ datasets, and with data batched over multiple sequence lengths. We extend the study to the $k$-fold cross-validation setting through a similar set of experiments. An ablation study exposes the method to varying amounts of shift and demonstrates slower degradation with $FIcsR$ in place. The results are promising under all these conditions; with improved accuracy against batch and fold state-of-the-art by more than $5\%$ and $10\%$, respectively.

Related papers

• Pooling Image Datasets With Multiple Covariate Shift and Imbalance [22.53402104452306]
  We show how viewing this problem from the perspective of Category theory provides a simple and effective solution. We show the effectiveness of this approach via extensive experiments on real datasets.
  arXiv  Detail & Related papers  (2024-03-05T02:20:33Z)
• Dataset Distillation Meets Provable Subset Selection [14.158845925610438]
  dataset distillation is proposed to compress a large training dataset into a smaller synthetic one that retains its performance. We present a provable, sampling-based approach for initializing the distilled set by identifying important and removing redundant points in the data. We further merge the idea of data subset selection with dataset distillation, by training the distilled set on '' sampled points during the training procedure instead of randomly sampling the next batch.
  arXiv  Detail & Related papers  (2023-07-16T15:58:19Z)
• Intra-class Adaptive Augmentation with Neighbor Correction for Deep Metric Learning [99.14132861655223]
  We propose a novel intra-class adaptive augmentation (IAA) framework for deep metric learning. We reasonably estimate intra-class variations for every class and generate adaptive synthetic samples to support hard samples mining. Our method significantly improves and outperforms the state-of-the-art methods on retrieval performances by 3%-6%.
  arXiv  Detail & Related papers  (2022-11-29T14:52:38Z)
• ScoreMix: A Scalable Augmentation Strategy for Training GANs with Limited Data [93.06336507035486]
  Generative Adversarial Networks (GANs) typically suffer from overfitting when limited training data is available. We present ScoreMix, a novel and scalable data augmentation approach for various image synthesis tasks.
  arXiv  Detail & Related papers  (2022-10-27T02:55:15Z)
• Bias Mimicking: A Simple Sampling Approach for Bias Mitigation [57.17709477668213]
  We introduce a new class-conditioned sampling method: Bias Mimicking. Bias Mimicking improves underrepresented groups' accuracy of sampling methods by 3% over four benchmarks.
  arXiv  Detail & Related papers  (2022-09-30T17:33:00Z)
• Examining and Combating Spurious Features under Distribution Shift [94.31956965507085]
  We define and analyze robust and spurious representations using the information-theoretic concept of minimal sufficient statistics. We prove that even when there is only bias of the input distribution, models can still pick up spurious features from their training data. Inspired by our analysis, we demonstrate that group DRO can fail when groups do not directly account for various spurious correlations.
  arXiv  Detail & Related papers  (2021-06-14T05:39:09Z)
• Attentional-Biased Stochastic Gradient Descent [74.49926199036481]
  We present a provable method (named ABSGD) for addressing the data imbalance or label noise problem in deep learning. Our method is a simple modification to momentum SGD where we assign an individual importance weight to each sample in the mini-batch. ABSGD is flexible enough to combine with other robust losses without any additional cost.
  arXiv  Detail & Related papers  (2020-12-13T03:41:52Z)
• Multinomial Sampling for Hierarchical Change-Point Detection [0.0]
  We propose a multinomial sampling methodology that improves the detection rate and reduces the delay. Our experiments show results that outperform the baseline method and we also provide an example oriented to a human behavior study.
  arXiv  Detail & Related papers  (2020-07-24T09:18:17Z)
• Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift [81.74795324629712]
  We call prediction-time batch normalization, which significantly improves model accuracy and calibration under covariate shift. We show that prediction-time batch normalization provides complementary benefits to existing state-of-the-art approaches for improving robustness. The method has mixed results when used alongside pre-training, and does not seem to perform as well under more natural types of dataset shift.
  arXiv  Detail & Related papers  (2020-06-19T05:08:43Z)
• Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervision [5.352699766206807]
  Active learning (AL) aims to minimize labeling efforts for data-demanding deep neural networks (DNNs) We propose a low-complexity method for feature density matching using self-supervised Fisher kernel (FK) Our method outperforms state-of-the-art methods on MNIST, SVHN, and ImageNet classification while requiring only 1/10th of processing.
  arXiv  Detail & Related papers  (2020-03-01T03:56:32Z)

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.