Confident Sinkhorn Allocation for Pseudo-Labeling

• URL: http://arxiv.org/abs/2206.05880v5
• Date: Tue, 5 Mar 2024 07:18:44 GMT
• Title: Confident Sinkhorn Allocation for Pseudo-Labeling
• Authors: Vu Nguyen and Hisham Husain and Sachin Farfade and Anton van den Hengel
• Abstract summary: Semi-supervised learning is a critical tool in reducing machine learning's dependence on labeled data. This paper studies theoretically the role of uncertainty to pseudo-labeling and proposes Confident Sinkhorn Allocation (CSA) CSA identifies the best pseudo-label allocation via optimal transport to only samples with high confidence scores.
• Score: 40.883130133661304
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Semi-supervised learning is a critical tool in reducing machine learning's dependence on labeled data. It has been successfully applied to structured data, such as images and natural language, by exploiting the inherent spatial and semantic structure therein with pretrained models or data augmentation. These methods are not applicable, however, when the data does not have the appropriate structure, or invariances. Due to their simplicity, pseudo-labeling (PL) methods can be widely used without any domain assumptions. However, the greedy mechanism in PL is sensitive to a threshold and can perform poorly if wrong assignments are made due to overconfidence. This paper studies theoretically the role of uncertainty to pseudo-labeling and proposes Confident Sinkhorn Allocation (CSA), which identifies the best pseudo-label allocation via optimal transport to only samples with high confidence scores. CSA outperforms the current state-of-the-art in this practically important area of semi-supervised learning. Additionally, we propose to use the Integral Probability Metrics to extend and improve the existing PACBayes bound which relies on the Kullback-Leibler (KL) divergence, for ensemble models. Our code is publicly available at https://github.com/amzn/confident-sinkhorn-allocation.

Related papers

• CAST: Cluster-Aware Self-Training for Tabular Data via Reliable Confidence [0.4999814847776098]
  Self-training is vulnerable to noisy pseudo-labels caused by erroneous confidence. Cluster-Aware Self-Training (CAST) enhances existing self-training algorithms at a negligible cost.
  arXiv  Detail & Related papers  (2023-10-10T07:46:54Z)
• An Uncertainty-Aware Pseudo-Label Selection Framework using Regularized Conformal Prediction [0.0]
  Pseudo-labeling (PL) is a general and domain-agnostic SSL approach. PL underperforms due to the erroneous high-confidence predictions from poorly calibrated models. This paper proposes an uncertainty-aware pseudo-label selection framework.
  arXiv  Detail & Related papers  (2023-08-30T17:13:30Z)
• All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentation [67.30502812804271]
  Pseudo-labels are widely employed in weakly supervised 3D segmentation tasks where only sparse ground-truth labels are available for learning. We propose a novel learning strategy to regularize the generated pseudo-labels and effectively narrow the gaps between pseudo-labels and model predictions.
  arXiv  Detail & Related papers  (2023-05-25T08:19:31Z)
• ProtoCon: Pseudo-label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-supervised Learning [60.57998388590556]
  ProtoCon is a novel method for confidence-based pseudo-labeling. Online nature of ProtoCon allows it to utilise the label history of the entire dataset in one training cycle. It delivers significant gains and faster convergence over state-of-the-art datasets.
  arXiv  Detail & Related papers  (2023-03-22T23:51:54Z)
• Uncertainty-aware Self-training for Low-resource Neural Sequence Labeling [29.744621356187764]
  This paper presents SeqUST, a novel uncertain-aware self-training framework for Neural sequence labeling (NSL) We incorporate Monte Carlo (MC) dropout in Bayesian neural network (BNN) to perform uncertainty estimation at the token level and then select reliable language tokens from unlabeled data. A well-designed masked sequence labeling task with a noise-robust loss supports robust training, which aims to suppress the problem of noisy pseudo labels.
  arXiv  Detail & Related papers  (2023-02-17T02:40:04Z)
• Cycle Self-Training for Domain Adaptation [85.14659717421533]
  Cycle Self-Training (CST) is a principled self-training algorithm that enforces pseudo-labels to generalize across domains. CST recovers target ground truth, while both invariant feature learning and vanilla self-training fail. Empirical results indicate that CST significantly improves over prior state-of-the-arts in standard UDA benchmarks.
  arXiv  Detail & Related papers  (2021-03-05T10:04:25Z)
• Self-Tuning for Data-Efficient Deep Learning [75.34320911480008]
  Self-Tuning is a novel approach to enable data-efficient deep learning. It unifies the exploration of labeled and unlabeled data and the transfer of a pre-trained model. It outperforms its SSL and TL counterparts on five tasks by sharp margins.
  arXiv  Detail & Related papers  (2021-02-25T14:56:19Z)
• Sinkhorn Label Allocation: Semi-Supervised Classification via Annealed Self-Training [38.81973113564937]
  Self-training is a standard approach to semi-supervised learning where the learner's own predictions on unlabeled data are used as supervision during training. In this paper, we reinterpret this label assignment problem as an optimal transportation problem between examples and classes. We demonstrate the effectiveness of our algorithm on the CIFAR-10, CIFAR-100, and SVHN datasets in comparison with FixMatch, a state-of-the-art self-training algorithm.
  arXiv  Detail & Related papers  (2021-02-17T08:23:15Z)
• In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning [53.1047775185362]
  Pseudo-labeling (PL) is a general SSL approach that does not have this constraint but performs relatively poorly in its original formulation. We argue that PL underperforms due to the erroneous high confidence predictions from poorly calibrated models. We propose an uncertainty-aware pseudo-label selection (UPS) framework which improves pseudo labeling accuracy by drastically reducing the amount of noise encountered in the training process.
  arXiv  Detail & Related papers  (2021-01-15T23:29:57Z)

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.