DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity

• URL: http://arxiv.org/abs/2410.23495v2
• Date: Fri, 01 Nov 2024 09:49:24 GMT
• Title: DASH: Warm-Starting Neural Network Training in Stationary Settings without Loss of Plasticity
• Authors: Baekrok Shin, Junsoo Oh, Hanseul Cho, Chulhee Yun,
• Abstract summary: We develop a framework emulating real-world neural network training and identify noise memorization as the primary cause of plasticity loss when warm-starting on stationary data. Motivated by this, we propose Direction-Aware SHrinking (DASH), a method aiming to mitigate plasticity loss by selectively forgetting noise while preserving learned features.
• Score: 11.624569521079426
• License:
• Abstract: Warm-starting neural network training by initializing networks with previously learned weights is appealing, as practical neural networks are often deployed under a continuous influx of new data. However, it often leads to loss of plasticity, where the network loses its ability to learn new information, resulting in worse generalization than training from scratch. This occurs even under stationary data distributions, and its underlying mechanism is poorly understood. We develop a framework emulating real-world neural network training and identify noise memorization as the primary cause of plasticity loss when warm-starting on stationary data. Motivated by this, we propose Direction-Aware SHrinking (DASH), a method aiming to mitigate plasticity loss by selectively forgetting memorized noise while preserving learned features. We validate our approach on vision tasks, demonstrating improvements in test accuracy and training efficiency.

Related papers

• A simple theory for training response of deep neural networks [0.0]
  Deep neural networks give us a powerful method to model the training dataset's relationship between input and output. We show the training response consists of some different factors based on training stages, activation functions, or training methods. In addition, we show feature space reduction as an effect of training dynamics, which can result in network fragility.
  arXiv  Detail & Related papers  (2024-05-07T07:20:15Z)
• Disentangling the Causes of Plasticity Loss in Neural Networks [55.23250269007988]
  We show that loss of plasticity can be decomposed into multiple independent mechanisms. We show that a combination of layer normalization and weight decay is highly effective at maintaining plasticity in a variety of synthetic nonstationary learning tasks.
  arXiv  Detail & Related papers  (2024-02-29T00:02:33Z)
• Simple and Effective Transfer Learning for Neuro-Symbolic Integration [50.592338727912946]
  A potential solution to this issue is Neuro-Symbolic Integration (NeSy), where neural approaches are combined with symbolic reasoning. Most of these methods exploit a neural network to map perceptions to symbols and a logical reasoner to predict the output of the downstream task. They suffer from several issues, including slow convergence, learning difficulties with complex perception tasks, and convergence to local minima. This paper proposes a simple yet effective method to ameliorate these problems.
  arXiv  Detail & Related papers  (2024-02-21T15:51:01Z)
• Set-Based Training for Neural Network Verification [8.97708612393722]
  Small input perturbations can significantly affect the outputs of a neural network. In safety-critical environments, the inputs often contain noisy sensor data. We employ an end-to-end set-based training procedure that trains robust neural networks for formal verification.
  arXiv  Detail & Related papers  (2024-01-26T15:52:41Z)
• Understanding plasticity in neural networks [41.79540750236036]
  Plasticity is the ability of a neural network to quickly change its predictions in response to new information. Deep neural networks are known to lose plasticity over the course of training even in relatively simple learning problems.
  arXiv  Detail & Related papers  (2023-03-02T18:47:51Z)
• 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)
• Critical Learning Periods for Multisensory Integration in Deep Networks [112.40005682521638]
  We show that the ability of a neural network to integrate information from diverse sources hinges critically on being exposed to properly correlated signals during the early phases of training. We show that critical periods arise from the complex and unstable early transient dynamics, which are decisive of final performance of the trained system and their learned representations.
  arXiv  Detail & Related papers  (2022-10-06T23:50:38Z)
• Reconstructing Training Data from Trained Neural Networks [42.60217236418818]
  We show in some cases a significant fraction of the training data can in fact be reconstructed from the parameters of a trained neural network classifier. We propose a novel reconstruction scheme that stems from recent theoretical results about the implicit bias in training neural networks with gradient-based methods.
  arXiv  Detail & Related papers  (2022-06-15T18:35:16Z)
• Explain to Not Forget: Defending Against Catastrophic Forgetting with XAI [10.374979214803805]
  Catastrophic forgetting describes the phenomenon when a neural network completely forgets previous knowledge when given new information. We propose a novel training algorithm called training by explaining in which we leverage Layer-wise Relevance propagation in order to retain the information a neural network has already learned in previous tasks when training on new data. Our method not only successfully retains the knowledge of old tasks within the neural networks but does so more resource-efficiently than other state-of-the-art solutions.
  arXiv  Detail & Related papers  (2022-05-04T08:00:49Z)
• Learning Fast and Slow for Online Time Series Forecasting [76.50127663309604]
  Fast and Slow learning Networks (FSNet) is a holistic framework for online time-series forecasting. FSNet balances fast adaptation to recent changes and retrieving similar old knowledge. Our code will be made publicly available.
  arXiv  Detail & Related papers  (2022-02-23T18:23:07Z)
• Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
  We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs. By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
  arXiv  Detail & Related papers  (2022-02-01T17:11:13Z)

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.