Transferring Learning Trajectories of Neural Networks

• URL: http://arxiv.org/abs/2305.14122v2
• Date: Tue, 3 Oct 2023 12:03:05 GMT
• Title: Transferring Learning Trajectories of Neural Networks
• Authors: Daiki Chijiwa
• Abstract summary: Training deep neural networks (DNNs) is computationally expensive. We formulate the problem of "transferring" a given learning trajectory from one initial parameter to another one. We empirically show that the transferred parameters achieve non-trivial accuracy before any direct training, and can be trained significantly faster than training from scratch.
• Score: 2.2299983745857896
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Training deep neural networks (DNNs) is computationally expensive, which is problematic especially when performing duplicated or similar training runs in model ensemble or fine-tuning pre-trained models, for example. Once we have trained one DNN on some dataset, we have its learning trajectory (i.e., a sequence of intermediate parameters during training) which may potentially contain useful information for learning the dataset. However, there has been no attempt to utilize such information of a given learning trajectory for another training. In this paper, we formulate the problem of "transferring" a given learning trajectory from one initial parameter to another one (learning transfer problem) and derive the first algorithm to approximately solve it by matching gradients successively along the trajectory via permutation symmetry. We empirically show that the transferred parameters achieve non-trivial accuracy before any direct training, and can be trained significantly faster than training from scratch.

Related papers

• DeepONet as a Multi-Operator Extrapolation Model: Distributed Pretraining with Physics-Informed Fine-Tuning [6.635683993472882]
  We propose a novel fine-tuning method to achieve multi-operator learning. Our approach combines distributed learning to integrate data from various operators in pre-training, while physics-informed methods enable zero-shot fine-tuning.
  arXiv  Detail & Related papers  (2024-11-11T18:58:46Z)
• Learn, Unlearn and Relearn: An Online Learning Paradigm for Deep Neural Networks [12.525959293825318]
  We introduce Learn, Unlearn, and Relearn (LURE) an online learning paradigm for deep neural networks (DNNs) LURE interchanges between the unlearning phase, which selectively forgets the undesirable information in the model, and the relearning phase, which emphasizes learning on generalizable features. We show that our training paradigm provides consistent performance gains across datasets in both classification and few-shot settings.
  arXiv  Detail & Related papers  (2023-03-18T16:45:54Z)
• Learning to Learn with Generative Models of Neural Network Checkpoints [71.06722933442956]
  We construct a dataset of neural network checkpoints and train a generative model on the parameters. We find that our approach successfully generates parameters for a wide range of loss prompts. We apply our method to different neural network architectures and tasks in supervised and reinforcement learning.
  arXiv  Detail & Related papers  (2022-09-26T17:59:58Z)
• Transfer Learning via Test-Time Neural Networks Aggregation [11.42582922543676]
  It has been demonstrated that deep neural networks outperform traditional machine learning. Deep networks lack generalisability, that is, they will not perform as good as in a new (testing) set drawn from a different distribution.
  arXiv  Detail & Related papers  (2022-06-27T15:46:05Z)
• 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)
• Task-Customized Self-Supervised Pre-training with Scalable Dynamic Routing [76.78772372631623]
  A common practice for self-supervised pre-training is to use as much data as possible. For a specific downstream task, however, involving irrelevant data in pre-training may degenerate the downstream performance. It is burdensome and infeasible to use different downstream-task-customized datasets in pre-training for different tasks.
  arXiv  Detail & Related papers  (2022-05-26T10:49:43Z)
• A Meta-Learned Neuron model for Continual Learning [0.0]
  Continual learning is the ability to acquire new knowledge without forgetting the previously learned one. In this work, we replace the standard neuron by a meta-learned neuron model. Our approach can memorize dataset-length sequences of training samples, and its learning capabilities generalize to any domain.
  arXiv  Detail & Related papers  (2021-11-03T23:39:14Z)
• What training reveals about neural network complexity [80.87515604428346]
  This work explores the hypothesis that the complexity of the function a deep neural network (NN) is learning can be deduced by how fast its weights change during training. Our results support the hypothesis that good training behavior can be a useful bias towards good generalization.
  arXiv  Detail & Related papers  (2021-06-08T08:58:00Z)
• Learning Neural Network Subspaces [74.44457651546728]
  Recent observations have advanced our understanding of the neural network optimization landscape. With a similar computational cost as training one model, we learn lines, curves, and simplexes of high-accuracy neural networks. With a similar computational cost as training one model, we learn lines, curves, and simplexes of high-accuracy neural networks.
  arXiv  Detail & Related papers  (2021-02-20T23:26:58Z)
• Predicting Training Time Without Training [120.92623395389255]
  We tackle the problem of predicting the number of optimization steps that a pre-trained deep network needs to converge to a given value of the loss function. We leverage the fact that the training dynamics of a deep network during fine-tuning are well approximated by those of a linearized model. We are able to predict the time it takes to fine-tune a model to a given loss without having to perform any training.
  arXiv  Detail & Related papers  (2020-08-28T04:29:54Z)
• Side-Tuning: A Baseline for Network Adaptation via Additive Side Networks [95.51368472949308]
  Adaptation can be useful in cases when training data is scarce, or when one wishes to encode priors in the network. In this paper, we propose a straightforward alternative: side-tuning.
  arXiv  Detail & Related papers  (2019-12-31T18:52:32Z)

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.