Leveraging Unlabeled Data to Track Memorization

• URL: http://arxiv.org/abs/2212.04461v1
• Date: Thu, 8 Dec 2022 18:36:41 GMT
• Title: Leveraging Unlabeled Data to Track Memorization
• Authors: Mahsa Forouzesh and Hanie Sedghi and Patrick Thiran
• Abstract summary: We propose a metric, called susceptibility, to gauge memorization for neural networks. We empirically show the effectiveness of our metric in tracking memorization on various architectures and datasets.
• Score: 15.4909376515404
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep neural networks may easily memorize noisy labels present in real-world data, which degrades their ability to generalize. It is therefore important to track and evaluate the robustness of models against noisy label memorization. We propose a metric, called susceptibility, to gauge such memorization for neural networks. Susceptibility is simple and easy to compute during training. Moreover, it does not require access to ground-truth labels and it only uses unlabeled data. We empirically show the effectiveness of our metric in tracking memorization on various architectures and datasets and provide theoretical insights into the design of the susceptibility metric. Finally, we show through extensive experiments on datasets with synthetic and real-world label noise that one can utilize susceptibility and the overall training accuracy to distinguish models that maintain a low memorization on the training set and generalize well to unseen clean data.

Related papers

• Maximizing Data Efficiency for Cross-Lingual TTS Adaptation by Self-Supervised Representation Mixing and Embedding Initialization [57.38123229553157]
  This paper presents an effective transfer learning framework for language adaptation in text-to-speech systems. We focus on achieving language adaptation using minimal labeled and unlabeled data. Experimental results show that our framework is able to synthesize intelligible speech in unseen languages with only 4 utterances of labeled data and 15 minutes of unlabeled data.
  arXiv  Detail & Related papers  (2024-01-23T21:55:34Z)
• 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)
• MILD: Modeling the Instance Learning Dynamics for Learning with Noisy Labels [19.650299232829546]
  We propose an iterative selection approach based on the Weibull mixture model to identify clean data. In particular, we measure the difficulty of memorization and memorize for each instance via the transition times between being misclassified and being memorized. Our strategy outperforms existing noisy-label learning methods.
  arXiv  Detail & Related papers  (2023-06-20T14:26:53Z)
• Mitigating Label Noise through Data Ambiguation [9.51828574518325]
  Large models with high expressive power are prone to memorizing incorrect labels, thereby harming generalization performance. In this paper, we suggest to address the shortcomings of both methodologies by "ambiguating" the target information. More precisely, we leverage the framework of so-called superset learning to construct set-valued targets based on a confidence threshold.
  arXiv  Detail & Related papers  (2023-05-23T07:29:08Z)
• Debiased Pseudo Labeling in Self-Training [77.83549261035277]
  Deep neural networks achieve remarkable performances on a wide range of tasks with the aid of large-scale labeled datasets. To mitigate the requirement for labeled data, self-training is widely used in both academia and industry by pseudo labeling on readily-available unlabeled data. We propose Debiased, in which the generation and utilization of pseudo labels are decoupled by two independent heads.
  arXiv  Detail & Related papers  (2022-02-15T02:14:33Z)
• Understanding Memorization from the Perspective of Optimization via Efficient Influence Estimation [54.899751055620904]
  We study the phenomenon of memorization with turn-over dropout, an efficient method to estimate influence and memorization, for data with true labels (real data) and data with random labels (random data) Our main findings are: (i) For both real data and random data, the optimization of easy examples (e.g., real data) and difficult examples (e.g., random data) are conducted by the network simultaneously, with easy ones at a higher speed; (ii) For real data, a correct difficult example in the training dataset is more informative than an easy one.
  arXiv  Detail & Related papers  (2021-12-16T11:34:23Z)
• Learning from Noisy Labels for Entity-Centric Information Extraction [17.50856935207308]
  We propose a simple co-regularization framework for entity-centric information extraction. These models are jointly optimized with task-specific loss, and are regularized to generate similar predictions. In the end, we can take any of the trained models for inference.
  arXiv  Detail & Related papers  (2021-04-17T22:49:12Z)
• Noisy Labels Can Induce Good Representations [53.47668632785373]
  We study how architecture affects learning with noisy labels. We show that training with noisy labels can induce useful hidden representations, even when the model generalizes poorly. This finding leads to a simple method to improve models trained on noisy labels.
  arXiv  Detail & Related papers  (2020-12-23T18:58:05Z)
• Iterative Label Improvement: Robust Training by Confidence Based Filtering and Dataset Partitioning [5.1293809610257775]
  State-of-the-art, high capacity deep neural networks require large amounts of labelled training data. They are also highly susceptible to label errors in this data. We propose a novel meta training and labelling scheme that is able to use inexpensive unlabelled data.
  arXiv  Detail & Related papers  (2020-02-07T10:42:26Z)
• Exploratory Machine Learning with Unknown Unknowns [60.78953456742171]
  We study a new problem setting in which there are unknown classes in the training data misperceived as other labels. We propose the exploratory machine learning, which examines and investigates training data by actively augmenting the feature space to discover potentially hidden classes.
  arXiv  Detail & Related papers  (2020-02-05T02:06:56Z)

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.