Midpoint Regularization: from High Uncertainty Training to Conservative Classification

• URL: http://arxiv.org/abs/2106.13913v1
• Date: Sat, 26 Jun 2021 00:31:46 GMT
• Title: Midpoint Regularization: from High Uncertainty Training to Conservative Classification
• Authors: Hongyu Guo
• Abstract summary: Label Smoothing (LS) improves model generalization through penalizing models from generating overconfident output distributions. We extend this technique by considering example pairs, coined PLS. PLS first creates midpoint samples by averaging random sample pairs and then learns a smoothing distribution during training for each of these midpoint samples, resulting in midpoints with high uncertainty labels for training.
• Score: 19.252319300590653
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Label Smoothing (LS) improves model generalization through penalizing models from generating overconfident output distributions. For each training sample the LS strategy smooths the one-hot encoded training signal by distributing its distribution mass over the non-ground truth classes. We extend this technique by considering example pairs, coined PLS. PLS first creates midpoint samples by averaging random sample pairs and then learns a smoothing distribution during training for each of these midpoint samples, resulting in midpoints with high uncertainty labels for training. We empirically show that PLS significantly outperforms LS, achieving up to 30% of relative classification error reduction. We also visualize that PLS produces very low winning softmax scores for both in and out of distribution samples.

Related papers

• Distribution-Aware Robust Learning from Long-Tailed Data with Noisy Labels [8.14255560923536]
  Real-world data often exhibit long-tailed distributions and label noise, significantly degrading generalization performance. Recent studies have focused on noisy sample selection methods that estimate the centroid of each class based on high-confidence samples within each target class. We present Distribution-aware Sample Selection and Contrastive Learning (DaSC) to generate enhanced class centroids.
  arXiv  Detail & Related papers  (2024-07-23T19:06:15Z)
• Distributional Preference Alignment of LLMs via Optimal Transport [36.95053112313244]
  We propose a novel method for distributional preference alignment of LLMs called Alignment via Optimal Transport (AOT) AOT aligns LLMs on unpaired preference data by making the reward distribution of the positive samplesally dominant in the first order on the distribution of negative samples. We show that AOT leads to state-of-the-art models in the 7B family of models when evaluated with Open LLM Benchmarks and AlpacaEval.
  arXiv  Detail & Related papers  (2024-06-09T18:41:05Z)
• A Channel-ensemble Approach: Unbiased and Low-variance Pseudo-labels is Critical for Semi-supervised Classification [61.473485511491795]
  Semi-supervised learning (SSL) is a practical challenge in computer vision. Pseudo-label (PL) methods, e.g., FixMatch and FreeMatch, obtain the State Of The Art (SOTA) performances in SSL. We propose a lightweight channel-based ensemble method to consolidate multiple inferior PLs into the theoretically guaranteed unbiased and low-variance one.
  arXiv  Detail & Related papers  (2024-03-27T09:49:37Z)
• Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization [165.98557106089777]
  A key challenge is to enhance the capabilities of large language models (LLMs) amid a looming shortage of high-quality training data. Our study starts from an empirical strategy for the light continual training of LLMs using their original pre-training data sets. We then formalize this strategy into a principled framework of Instance-Reweighted Distributionally Robust Optimization.
  arXiv  Detail & Related papers  (2024-02-22T04:10:57Z)
• Twice Class Bias Correction for Imbalanced Semi-Supervised Learning [59.90429949214134]
  We introduce a novel approach called textbfTwice textbfClass textbfBias textbfCorrection (textbfTCBC) We estimate the class bias of the model parameters during the training process. We apply a secondary correction to the model's pseudo-labels for unlabeled samples.
  arXiv  Detail & Related papers  (2023-12-27T15:06:36Z)
• Learning in Imperfect Environment: Multi-Label Classification with Long-Tailed Distribution and Partial Labels [53.68653940062605]
  We introduce a novel task, Partial labeling and Long-Tailed Multi-Label Classification (PLT-MLC) We find that most LT-MLC and PL-MLC approaches fail to solve the degradation-MLC. We propose an end-to-end learning framework: textbfCOrrection $rightarrow$ textbfModificattextbfIon $rightarrow$ balantextbfCe.
  arXiv  Detail & Related papers  (2023-04-20T20:05:08Z)
• InPL: Pseudo-labeling the Inliers First for Imbalanced Semi-supervised Learning [34.062061310242385]
  We present a new perspective of pseudo-labeling for imbalanced semi-supervised learning (SSL) We measure whether an unlabeled sample is likely to be in-distribution'' or out-of-distribution'' Experiments demonstrate that our energy-based pseudo-labeling method, textbfInPL, significantly outperforms confidence-based methods on imbalanced SSL benchmarks.
  arXiv  Detail & Related papers  (2023-03-13T16:45:41Z)
• Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
  Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios. We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
  arXiv  Detail & Related papers  (2022-04-13T12:43:12Z)
• Two-stage Training for Learning from Label Proportions [18.78148397471913]
  Learning from label proportions (LLP) aims at learning an instance-level classifier with label proportions in grouped training data. We introduce the mixup strategy and symmetric crossentropy to further reduce the label noise. Our framework is model-agnostic, and demonstrates compelling performance improvement in extensive experiments.
  arXiv  Detail & Related papers  (2021-05-22T03:55:35Z)
• Regularization via Adaptive Pairwise Label Smoothing [19.252319300590653]
  This paper introduces a novel label smoothing technique called Pairwise Label Smoothing (PLS) Unlike current LS methods, which typically require to find a global smoothing distribution mass through cross-validation search, PLS automatically learns the distribution mass for each input pair during training. We empirically show that PLS significantly outperforms LS and the baseline models, achieving up to 30% of relative classification error reduction.
  arXiv  Detail & Related papers  (2020-12-02T22:08:10Z)
• Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning [126.31716228319902]
  We develop Distribution Aligning Refinery of Pseudo-label (DARP) algorithm. We show that DARP is provably and efficiently compatible with state-of-the-art SSL schemes.
  arXiv  Detail & Related papers  (2020-07-17T09:16:05Z)

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.