Does confidence calibration improve conformal prediction?

• URL: http://arxiv.org/abs/2402.04344v3
• Date: Mon, 23 Dec 2024 06:46:59 GMT
• Title: Does confidence calibration improve conformal prediction?
• Authors: Huajun Xi, Jianguo Huang, Kangdao Liu, Lei Feng, Hongxin Wei,
• Abstract summary: We show that current confidence calibration methods lead to larger prediction sets in adaptive conformal prediction. By investigating the role of temperature value, we observe that high-confidence predictions can enhance the efficiency of adaptive conformal prediction. We propose Conformal Temperature Scaling (ConfTS), a variant of temperature scaling with a novel loss function designed to enhance the efficiency of prediction sets.
• Score: 10.340903334800787
• License:
• Abstract: Conformal prediction is an emerging technique for uncertainty quantification that constructs prediction sets guaranteed to contain the true label with a predefined probability. Previous works often employ temperature scaling to calibrate classifiers, assuming that confidence calibration benefits conformal prediction. However, the specific impact of confidence calibration on conformal prediction remains underexplored. In this work, we make two key discoveries about the impact of confidence calibration methods on adaptive conformal prediction. Firstly, we empirically show that current confidence calibration methods (e.g., temperature scaling) typically lead to larger prediction sets in adaptive conformal prediction. Secondly, by investigating the role of temperature value, we observe that high-confidence predictions can enhance the efficiency of adaptive conformal prediction. Theoretically, we prove that predictions with higher confidence result in smaller prediction sets on expectation. This finding implies that the rescaling parameters in these calibration methods, when optimized with cross-entropy loss, might counteract the goal of generating efficient prediction sets. To address this issue, we propose Conformal Temperature Scaling (ConfTS), a variant of temperature scaling with a novel loss function designed to enhance the efficiency of prediction sets. This approach can be extended to optimize the parameters of other post-hoc methods of confidence calibration. Extensive experiments demonstrate that our method improves existing adaptive conformal prediction methods in classification tasks, especially with LLMs.

Related papers

• Provably Reliable Conformal Prediction Sets in the Presence of Data Poisoning [53.42244686183879]
  Conformal prediction provides model-agnostic and distribution-free uncertainty quantification. Yet, conformal prediction is not reliable under poisoning attacks where adversaries manipulate both training and calibration data. We propose reliable prediction sets (RPS): the first efficient method for constructing conformal prediction sets with provable reliability guarantees under poisoning.
  arXiv  Detail & Related papers  (2024-10-13T15:37:11Z)
• Calibrating Language Models with Adaptive Temperature Scaling [58.056023173579625]
  We introduce Adaptive Temperature Scaling (ATS), a post-hoc calibration method that predicts a temperature scaling parameter for each token prediction. ATS improves calibration by over 10-50% across three downstream natural language evaluation benchmarks compared to prior calibration methods.
  arXiv  Detail & Related papers  (2024-09-29T22:54:31Z)
• Domain-adaptive and Subgroup-specific Cascaded Temperature Regression for Out-of-distribution Calibration [16.930766717110053]
  We propose a novel meta-set-based cascaded temperature regression method for post-hoc calibration. We partition each meta-set into subgroups based on predicted category and confidence level, capturing diverse uncertainties. A regression network is then trained to derive category-specific and confidence-level-specific scaling, achieving calibration across meta-sets.
  arXiv  Detail & Related papers  (2024-02-14T14:35:57Z)
• Self-Calibrating Conformal Prediction [16.606421967131524]
  We introduce Self-Calibrating Conformal Prediction to deliver calibrated point predictions alongside prediction intervals with finite-sample validity conditional on these predictions. We show that our method improves calibrated interval efficiency through model calibration and offers a practical alternative to feature-conditional validity.
  arXiv  Detail & Related papers  (2024-02-11T21:12:21Z)
• Predictive Inference with Feature Conformal Prediction [80.77443423828315]
  We propose feature conformal prediction, which extends the scope of conformal prediction to semantic feature spaces. From a theoretical perspective, we demonstrate that feature conformal prediction provably outperforms regular conformal prediction under mild assumptions. Our approach could be combined with not only vanilla conformal prediction, but also other adaptive conformal prediction methods.
  arXiv  Detail & Related papers  (2022-10-01T02:57:37Z)
• Sample-dependent Adaptive Temperature Scaling for Improved Calibration [95.7477042886242]
  Post-hoc approach to compensate for neural networks being wrong is to perform temperature scaling. We propose to predict a different temperature value for each input, allowing us to adjust the mismatch between confidence and accuracy. We test our method on the ResNet50 and WideResNet28-10 architectures using the CIFAR10/100 and Tiny-ImageNet datasets.
  arXiv  Detail & Related papers  (2022-07-13T14:13:49Z)
• Revisiting Calibration for Question Answering [16.54743762235555]
  We argue that the traditional evaluation of calibration does not reflect usefulness of the model confidence. We propose a new calibration metric, MacroCE, that better captures whether the model assigns low confidence to wrong predictions and high confidence to correct predictions.
  arXiv  Detail & Related papers  (2022-05-25T05:49:56Z)
• Optimized conformal classification using gradient descent approximation [0.2538209532048866]
  Conformal predictors allow predictions to be made with a user-defined confidence level. We consider an approach to train the conformal predictor directly with maximum predictive efficiency. We test the method on several real world data sets and find that the method is promising.
  arXiv  Detail & Related papers  (2021-05-24T13:14:41Z)
• Parameterized Temperature Scaling for Boosting the Expressive Power in Post-Hoc Uncertainty Calibration [57.568461777747515]
  We introduce a novel calibration method, Parametrized Temperature Scaling (PTS) We demonstrate that the performance of accuracy-preserving state-of-the-art post-hoc calibrators is limited by their intrinsic expressive power. We show with extensive experiments that our novel accuracy-preserving approach consistently outperforms existing algorithms across a large number of model architectures, datasets and metrics.
  arXiv  Detail & Related papers  (2021-02-24T10:18:30Z)
• Private Prediction Sets [72.75711776601973]
  Machine learning systems need reliable uncertainty quantification and protection of individuals' privacy. We present a framework that treats these two desiderata jointly. We evaluate the method on large-scale computer vision datasets.
  arXiv  Detail & Related papers  (2021-02-11T18:59:11Z)

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.