Something for (almost) nothing: Improving deep ensemble calibration using unlabeled data

• URL: http://arxiv.org/abs/2310.02885v1
• Date: Wed, 4 Oct 2023 15:21:54 GMT
• Title: Something for (almost) nothing: Improving deep ensemble calibration using unlabeled data
• Authors: Konstantinos Pitas, Julyan Arbel
• Abstract summary: We present a method to improve the calibration of deep ensembles in the small training data regime in the presence of unlabeled data. Our approach is extremely simple to implement: given an unlabeled set, for each unlabeled data point, we simply fit a different randomly selected label with each ensemble member.
• Score: 4.503508912578133
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a method to improve the calibration of deep ensembles in the small training data regime in the presence of unlabeled data. Our approach is extremely simple to implement: given an unlabeled set, for each unlabeled data point, we simply fit a different randomly selected label with each ensemble member. We provide a theoretical analysis based on a PAC-Bayes bound which guarantees that if we fit such a labeling on unlabeled data, and the true labels on the training data, we obtain low negative log-likelihood and high ensemble diversity on testing samples. Empirically, through detailed experiments, we find that for low to moderately-sized training sets, our ensembles are more diverse and provide better calibration than standard ensembles, sometimes significantly.

Related papers

• AllMatch: Exploiting All Unlabeled Data for Semi-Supervised Learning [5.0823084858349485]
  We present a novel SSL algorithm named AllMatch, which achieves improved pseudo-label accuracy and a 100% utilization ratio for the unlabeled data. The results demonstrate that AllMatch consistently outperforms existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-06-22T06:59:52Z)
• You can't handle the (dirty) truth: Data-centric insights improve pseudo-labeling [60.27812493442062]
  We show the importance of investigating labeled data quality to improve any pseudo-labeling method. Specifically, we introduce a novel data characterization and selection framework called DIPS to extend pseudo-labeling. We demonstrate the applicability and impact of DIPS for various pseudo-labeling methods across an extensive range of real-world datasets.
  arXiv  Detail & Related papers  (2024-06-19T17:58:40Z)
• Multi-Label Adaptive Batch Selection by Highlighting Hard and Imbalanced Samples [9.360376286221943]
  We introduce an adaptive batch selection algorithm tailored to multi-label deep learning models. Our method converges faster and performs better than random batch selection.
  arXiv  Detail & Related papers  (2024-03-27T02:00:18Z)
• Soft Curriculum for Learning Conditional GANs with Noisy-Labeled and Uncurated Unlabeled Data [70.25049762295193]
  We introduce a novel conditional image generation framework that accepts noisy-labeled and uncurated data during training. We propose soft curriculum learning, which assigns instance-wise weights for adversarial training while assigning new labels for unlabeled data. Our experiments show that our approach outperforms existing semi-supervised and label-noise robust methods in terms of both quantitative and qualitative performance.
  arXiv  Detail & Related papers  (2023-07-17T08:31:59Z)
• How many labelers do you have? A closer look at gold-standard labels [10.637125300701795]
  We show how access to non-aggregated label information can make training well-calibrated models more feasible than it is with gold-standard labels. We make several predictions for real-world datasets, including when non-aggregate labels should improve learning performance.
  arXiv  Detail & Related papers  (2022-06-24T02:33:50Z)
• An analysis of over-sampling labeled data in semi-supervised learning with FixMatch [66.34968300128631]
  Most semi-supervised learning methods over-sample labeled data when constructing training mini-batches. This paper studies whether this common practice improves learning and how. We compare it to an alternative setting where each mini-batch is uniformly sampled from all the training data, labeled or not.
  arXiv  Detail & Related papers  (2022-01-03T12:22:26Z)
• Dash: Semi-Supervised Learning with Dynamic Thresholding [72.74339790209531]
  We propose a semi-supervised learning (SSL) approach that uses unlabeled examples to train models. Our proposed approach, Dash, enjoys its adaptivity in terms of unlabeled data selection.
  arXiv  Detail & Related papers  (2021-09-01T23:52:29Z)
• Disentangling Sampling and Labeling Bias for Learning in Large-Output Spaces [64.23172847182109]
  We show that different negative sampling schemes implicitly trade-off performance on dominant versus rare labels. We provide a unified means to explicitly tackle both sampling bias, arising from working with a subset of all labels, and labeling bias, which is inherent to the data due to label imbalance.
  arXiv  Detail & Related papers  (2021-05-12T15:40:13Z)
• Gradient Descent in RKHS with Importance Labeling [58.79085525115987]
  We study importance labeling problem, in which we are given many unlabeled data. We propose a new importance labeling scheme that can effectively select an informative subset of unlabeled data.
  arXiv  Detail & Related papers  (2020-06-19T01:55:00Z)

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.