Why Fine-grained Labels in Pretraining Benefit Generalization?

• URL: http://arxiv.org/abs/2410.23129v1
• Date: Wed, 30 Oct 2024 15:41:30 GMT
• Title: Why Fine-grained Labels in Pretraining Benefit Generalization?
• Authors: Guan Zhe Hong, Yin Cui, Ariel Fuxman, Stanely Chan, Enming Luo,
• Abstract summary: Recent studies show that pretraining a deep neural network with fine-grained labeled data, followed by fine-tuning on coarse-labeled data, often yields better generalization than pretraining with coarse-labeled data. This paper addresses this gap by introducing a "hierarchical multi-view" structure to confine the input data distribution. Under this framework, we prove that: 1) coarse-grained pretraining only allows a neural network to learn the common features well, while 2) fine-grained pretraining helps the network learn the rare features in addition to the common ones, leading to improved accuracy on hard downstream test samples.
• Score: 12.171634061370616
• License:
• Abstract: Recent studies show that pretraining a deep neural network with fine-grained labeled data, followed by fine-tuning on coarse-labeled data for downstream tasks, often yields better generalization than pretraining with coarse-labeled data. While there is ample empirical evidence supporting this, the theoretical justification remains an open problem. This paper addresses this gap by introducing a "hierarchical multi-view" structure to confine the input data distribution. Under this framework, we prove that: 1) coarse-grained pretraining only allows a neural network to learn the common features well, while 2) fine-grained pretraining helps the network learn the rare features in addition to the common ones, leading to improved accuracy on hard downstream test samples.

Related papers

• Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data [42.870635753205185]
  Neural networks trained by gradient descent (GD) have exhibited a number of surprising generalization behaviors. We show that both of these phenomena provably occur in two-layer ReLU networks trained by GD on XOR cluster data. At a later training step, the network achieves near-optimal test accuracy while still fitting the random labels in the training data, exhibiting a "grokking" phenomenon.
  arXiv  Detail & Related papers  (2023-10-04T02:50:34Z)
• Towards Understanding the Effect of Pretraining Label Granularity [23.61736162174686]
  We focus on the "fine-to-coarse" transfer learning setting, where the pretraining label space is more fine-grained than that of the target problem. We show that pretraining on the leaf labels of ImageNet21k produces better transfer results on ImageNet1k than pretraining on other coarser granularity levels.
  arXiv  Detail & Related papers  (2023-03-29T17:56:36Z)
• Neural networks trained with SGD learn distributions of increasing complexity [78.30235086565388]
  We show that neural networks trained using gradient descent initially classify their inputs using lower-order input statistics. We then exploit higher-order statistics only later during training. We discuss the relation of DSB to other simplicity biases and consider its implications for the principle of universality in learning.
  arXiv  Detail & Related papers  (2022-11-21T15:27:22Z)
• Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data [44.431266188350655]
  We consider the generalization error of two-layer neural networks trained to generalize by gradient descent. We show that neural networks exhibit benign overfitting: they can be driven to zero training error, perfectly fitting any noisy training labels, and simultaneously achieve minimax optimal test error. In contrast to previous work on benign overfitting that require linear or kernel-based predictors, our analysis holds in a setting where both the model and learning dynamics are fundamentally nonlinear.
  arXiv  Detail & Related papers  (2022-02-11T23:04:00Z)
• How does unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis [93.37576644429578]
  This work establishes the first theoretical analysis for the known iterative self-training paradigm. We prove the benefits of unlabeled data in both training convergence and generalization ability. Experiments from shallow neural networks to deep neural networks are also provided to justify the correctness of our established theoretical insights on self-training.
  arXiv  Detail & Related papers  (2022-01-21T02:16:52Z)
• RATT: Leveraging Unlabeled Data to Guarantee Generalization [96.08979093738024]
  We introduce a method that leverages unlabeled data to produce generalization bounds. We prove that our bound is valid for 0-1 empirical risk minimization. This work provides practitioners with an option for certifying the generalization of deep nets even when unseen labeled data is unavailable.
  arXiv  Detail & Related papers  (2021-05-01T17:05:29Z)
• A Theoretical Analysis of Learning with Noisily Labeled Data [62.946840431501855]
  We first show that in the first epoch training, the examples with clean labels will be learned first. We then show that after the learning from clean data stage, continuously training model can achieve further improvement in testing error.
  arXiv  Detail & Related papers  (2021-04-08T23:40:02Z)
• Temporal Calibrated Regularization for Robust Noisy Label Learning [60.90967240168525]
  Deep neural networks (DNNs) exhibit great success on many tasks with the help of large-scale well annotated datasets. However, labeling large-scale data can be very costly and error-prone so that it is difficult to guarantee the annotation quality. We propose a Temporal Calibrated Regularization (TCR) in which we utilize the original labels and the predictions in the previous epoch together.
  arXiv  Detail & Related papers  (2020-07-01T04:48:49Z)
• Text Classification with Few Examples using Controlled Generalization [58.971750512415134]
  Current practice relies on pre-trained word embeddings to map words unseen in training to similar seen ones. Our alternative begins with sparse pre-trained representations derived from unlabeled parsed corpora. We show that a feed-forward network over these vectors is especially effective in low-data scenarios.
  arXiv  Detail & Related papers  (2020-05-18T06:04:58Z)

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.