Keeping Deep Learning Models in Check: A History-Based Approach to Mitigate Overfitting

• URL: http://arxiv.org/abs/2401.10359v1
• Date: Thu, 18 Jan 2024 19:56:27 GMT
• Title: Keeping Deep Learning Models in Check: A History-Based Approach to Mitigate Overfitting
• Authors: Hao Li, Gopi Krishnan Rajbahadur, Dayi Lin, Cor-Paul Bezemer, and Zhen Ming (Jack) Jiang
• Abstract summary: Overfitting affects the quality, reliability, and trustworthiness of software systems that utilize deep learning models. We propose a simple, yet powerful approach that can both detect and prevent overfitting based on the training history. Our approach achieves an F1 score of 0.91 which is at least 5% higher than the current best-performing non-intrusive overfitting detection approach.
• Score: 18.952459066212523
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In software engineering, deep learning models are increasingly deployed for critical tasks such as bug detection and code review. However, overfitting remains a challenge that affects the quality, reliability, and trustworthiness of software systems that utilize deep learning models. Overfitting can be (1) prevented (e.g., using dropout or early stopping) or (2) detected in a trained model (e.g., using correlation-based approaches). Both overfitting detection and prevention approaches that are currently used have constraints (e.g., requiring modification of the model structure, and high computing resources). In this paper, we propose a simple, yet powerful approach that can both detect and prevent overfitting based on the training history (i.e., validation losses). Our approach first trains a time series classifier on training histories of overfit models. This classifier is then used to detect if a trained model is overfit. In addition, our trained classifier can be used to prevent overfitting by identifying the optimal point to stop a model's training. We evaluate our approach on its ability to identify and prevent overfitting in real-world samples. We compare our approach against correlation-based detection approaches and the most commonly used prevention approach (i.e., early stopping). Our approach achieves an F1 score of 0.91 which is at least 5% higher than the current best-performing non-intrusive overfitting detection approach. Furthermore, our approach can stop training to avoid overfitting at least 32% of the times earlier than early stopping and has the same or a better rate of returning the best model.

Related papers

• Prior2Posterior: Model Prior Correction for Long-Tailed Learning [0.41248472494152805]
  We propose a novel approach to accurately model the effective prior of a trained model using textita posteriori probabilities. We show that the proposed approach achieves new state-of-the-art (SOTA) on several benchmark datasets from the long-tail literature.
  arXiv  Detail & Related papers  (2024-12-21T08:49:02Z)
• Source-Free Test-Time Adaptation For Online Surface-Defect Detection [29.69030283193086]
  We propose a novel test-time adaptation surface-defect detection approach. It adapts pre-trained models to new domains and classes during inference. Experiments demonstrate it outperforms state-of-the-art techniques.
  arXiv  Detail & Related papers  (2024-08-18T14:24:05Z)
• Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple Logits Retargeting Approach [102.0769560460338]
  We develop a simple logits approach (LORT) without the requirement of prior knowledge of the number of samples per class. Our method achieves state-of-the-art performance on various imbalanced datasets, including CIFAR100-LT, ImageNet-LT, and iNaturalist 2018.
  arXiv  Detail & Related papers  (2024-03-01T03:27:08Z)
• StochCA: A Novel Approach for Exploiting Pretrained Models with Cross-Attention [2.66269503676104]
  We introduce a novel fine-tuning method, called cross-attention (StochCA), specific to Transformer architectures. This method modifies the Transformer's self-attention mechanism to selectively utilize knowledge from pretrained models during fine-tuning. Our experimental results show the superiority of StochCA over state-of-the-art approaches in both areas.
  arXiv  Detail & Related papers  (2024-02-25T13:53:49Z)
• Selective Learning: Towards Robust Calibration with Dynamic Regularization [79.92633587914659]
  Miscalibration in deep learning refers to there is a discrepancy between the predicted confidence and performance. We introduce Dynamic Regularization (DReg) which aims to learn what should be learned during training thereby circumventing the confidence adjusting trade-off.
  arXiv  Detail & Related papers  (2024-02-13T11:25:20Z)
• LARA: A Light and Anti-overfitting Retraining Approach for Unsupervised Time Series Anomaly Detection [49.52429991848581]
  We propose a Light and Anti-overfitting Retraining Approach (LARA) for deep variational auto-encoder based time series anomaly detection methods (VAEs) This work aims to make three novel contributions: 1) the retraining process is formulated as a convex problem and can converge at a fast rate as well as prevent overfitting; 2) designing a ruminate block, which leverages the historical data without the need to store them; and 3) mathematically proving that when fine-tuning the latent vector and reconstructed data, the linear formations can achieve the least adjusting errors between the ground truths and the fine-tuned ones.
  arXiv  Detail & Related papers  (2023-10-09T12:36:16Z)
• RanPAC: Random Projections and Pre-trained Models for Continual Learning [59.07316955610658]
  Continual learning (CL) aims to learn different tasks (such as classification) in a non-stationary data stream without forgetting old ones. We propose a concise and effective approach for CL with pre-trained models.
  arXiv  Detail & Related papers  (2023-07-05T12:49:02Z)
• TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization [89.54947228958494]
  This paper focuses on the fine-tuning of an adversarially pre-trained model in various classification tasks. We propose a novel statistics-based approach, Two-WIng NormliSation (TWINS) fine-tuning framework. TWINS is shown to be effective on a wide range of image classification datasets in terms of both generalization and robustness.
  arXiv  Detail & Related papers  (2023-03-20T14:12:55Z)
• Uncertainty Estimation for Language Reward Models [5.33024001730262]
  Language models can learn a range of capabilities from unsupervised training on text corpora. It is often easier for humans to choose between options than to provide labeled data, and prior work has achieved state-of-the-art performance by training a reward model from such preference comparisons. We seek to address these problems via uncertainty estimation, which can improve sample efficiency and robustness using active learning and risk-averse reinforcement learning.
  arXiv  Detail & Related papers  (2022-03-14T20:13:21Z)
• Being Patient and Persistent: Optimizing An Early Stopping Strategy for Deep Learning in Profiled Attacks [2.7748013252318504]
  We propose an early stopping algorithm that reliably recognizes the model's optimal state during training. We formalize two conditions, persistence and patience, for a deep learning model to be optimal.
  arXiv  Detail & Related papers  (2021-11-29T09:54:45Z)
• Reinforcement Based Learning on Classification Task Could Yield Better Generalization and Adversarial Accuracy [0.0]
  We propose a novel method to train deep learning models on an image classification task. We use a reward-based optimization function, similar to the vanilla policy gradient method used in reinforcement learning.
  arXiv  Detail & Related papers  (2020-12-08T11:03:17Z)
• Overfitting in adversarially robust deep learning [86.11788847990783]
  We show that overfitting to the training set does in fact harm robust performance to a very large degree in adversarially robust training. We also show that effects such as the double descent curve do still occur in adversarially trained models, yet fail to explain the observed overfitting.
  arXiv  Detail & Related papers  (2020-02-26T15:40:50Z)

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.