Positive Unlabeled Learning Selected Not At Random (PULSNAR): class proportion estimation when the SCAR assumption does not hold

• URL: http://arxiv.org/abs/2303.08269v3
• Date: Fri, 3 May 2024 21:41:20 GMT
• Title: Positive Unlabeled Learning Selected Not At Random (PULSNAR): class proportion estimation when the SCAR assumption does not hold
• Authors: Praveen Kumar, Christophe G. Lambert,
• Abstract summary: Positive and Unlabeled (PU) learning is a type of semi-supervised binary classification. PU learning has broad applications in settings where confirmed negatives are unavailable or difficult to obtain. We propose two PU learning algorithms to estimate $alpha$, calculate probabilities for PU instances, and improve classification metrics.
• Score: 2.76815720120527
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Positive and Unlabeled (PU) learning is a type of semi-supervised binary classification where the machine learning algorithm differentiates between a set of positive instances (labeled) and a set of both positive and negative instances (unlabeled). PU learning has broad applications in settings where confirmed negatives are unavailable or difficult to obtain, and there is value in discovering positives among the unlabeled (e.g., viable drugs among untested compounds). Most PU learning algorithms make the \emph{selected completely at random} (SCAR) assumption, namely that positives are selected independently of their features. However, in many real-world applications, such as healthcare, positives are not SCAR (e.g., severe cases are more likely to be diagnosed), leading to a poor estimate of the proportion, $\alpha$, of positives among unlabeled examples and poor model calibration, resulting in an uncertain decision threshold for selecting positives. PU learning algorithms vary; some estimate only the proportion, $\alpha$, of positives in the unlabeled set, while others calculate the probability that each specific unlabeled instance is positive, and some can do both. We propose two PU learning algorithms to estimate $\alpha$, calculate calibrated probabilities for PU instances, and improve classification metrics: i) PULSCAR (positive unlabeled learning selected completely at random), and ii) PULSNAR (positive unlabeled learning selected not at random). PULSNAR employs a divide-and-conquer approach to cluster SNAR positives into subtypes and estimates $\alpha$ for each subtype by applying PULSCAR to positives from each cluster and all unlabeled. In our experiments, PULSNAR outperformed state-of-the-art approaches on both synthetic and real-world benchmark datasets.

Related papers

• Verifying the Selected Completely at Random Assumption in Positive-Unlabeled Learning [0.7646713951724013]
  We propose a relatively simple and computationally fast test that can be used to determine whether the observed data meet the SCAR assumption. Our test is based on generating artificial labels conforming to the SCAR case, which in turn allows to mimic the distribution of the test statistic under the null hypothesis of SCAR.
  arXiv  Detail & Related papers  (2024-03-29T20:36:58Z)
• Contrastive Learning with Negative Sampling Correction [52.990001829393506]
  We propose a novel contrastive learning method named Positive-Unlabeled Contrastive Learning (PUCL) PUCL treats the generated negative samples as unlabeled samples and uses information from positive samples to correct bias in contrastive loss. PUCL can be applied to general contrastive learning problems and outperforms state-of-the-art methods on various image and graph classification tasks.
  arXiv  Detail & Related papers  (2024-01-13T11:18:18Z)
• Joint empirical risk minimization for instance-dependent positive-unlabeled data [4.112909937203119]
  Learning from positive and unlabeled data (PU learning) is actively researched machine learning task. The goal is to train a binary classification model based on a dataset containing part on positives which are labeled, and unlabeled instances. Unlabeled set includes remaining part positives and all negative observations.
  arXiv  Detail & Related papers  (2023-12-27T12:45:12Z)
• Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical [66.57396042747706]
  Complementary-label learning is a weakly supervised learning problem. We propose a consistent approach that does not rely on the uniform distribution assumption. We find that complementary-label learning can be expressed as a set of negative-unlabeled binary classification problems.
  arXiv  Detail & Related papers  (2023-11-27T02:59:17Z)
• Robust Positive-Unlabeled Learning via Noise Negative Sample Self-correction [48.929877651182885]
  Learning from positive and unlabeled data is known as positive-unlabeled (PU) learning in literature. We propose a new robust PU learning method with a training strategy motivated by the nature of human learning.
  arXiv  Detail & Related papers  (2023-08-01T04:34:52Z)
• Dist-PU: Positive-Unlabeled Learning from a Label Distribution Perspective [89.5370481649529]
  We propose a label distribution perspective for PU learning in this paper. Motivated by this, we propose to pursue the label distribution consistency between predicted and ground-truth label distributions. Experiments on three benchmark datasets validate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2022-12-06T07:38:29Z)
• Learning with Proper Partial Labels [87.65718705642819]
  Partial-label learning is a kind of weakly-supervised learning with inexact labels. We show that this proper partial-label learning framework includes many previous partial-label learning settings. We then derive a unified unbiased estimator of the classification risk.
  arXiv  Detail & Related papers  (2021-12-23T01:37:03Z)
• Adaptive Positive-Unlabelled Learning via Markov Diffusion [0.0]
  Positive-Unlabelled (PU) learning is the machine learning setting in which only a set of positive instances are labelled. The principal aim of the algorithm is to identify a set of instances which are likely to contain positive instances that were originally unlabelled.
  arXiv  Detail & Related papers  (2021-08-13T10:25:47Z)
• Improving Positive Unlabeled Learning: Practical AUL Estimation and New Training Method for Extremely Imbalanced Data Sets [10.870831090350402]
  We improve Positive Unlabeled (PU) learning over state-of-the-art from two aspects. First, we propose an unbiased practical AUL estimation method, which makes use of raw PU data without prior knowledge of unlabeled samples. Secondly, we propose ProbTagging, a new training method for extremely imbalanced data sets.
  arXiv  Detail & Related papers  (2020-04-21T08:32:57Z)
• Learning from Positive and Unlabeled Data with Arbitrary Positive Shift [11.663072799764542]
  This paper shows that PU learning is possible even with arbitrarily non-representative positive data given unlabeled data. We integrate this into two statistically consistent methods to address arbitrary positive bias. Experimental results demonstrate our methods' effectiveness across numerous real-world datasets.
  arXiv  Detail & Related papers  (2020-02-24T13:53:22Z)
• On Positive-Unlabeled Classification in GAN [130.43248168149432]
  This paper defines a positive and unlabeled classification problem for standard GANs. It then leads to a novel technique to stabilize the training of the discriminator in GANs.
  arXiv  Detail & Related papers  (2020-02-04T05:59:37Z)

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.