Boosted Dynamic Neural Networks
- URL: http://arxiv.org/abs/2211.16726v1
- Date: Wed, 30 Nov 2022 04:23:12 GMT
- Title: Boosted Dynamic Neural Networks
- Authors: Haichao Yu, Haoxiang Li, Gang Hua, Gao Huang, Humphrey Shi
- Abstract summary: A typical EDNN has multiple prediction heads at different layers of the network backbone.
To optimize the model, these prediction heads together with the network backbone are trained on every batch of training data.
Treating training and testing inputs differently at the two phases will cause the mismatch between training and testing data distributions.
We formulate an EDNN as an additive model inspired by gradient boosting, and propose multiple training techniques to optimize the model effectively.
- Score: 53.559833501288146
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Early-exiting dynamic neural networks (EDNN), as one type of dynamic neural
networks, has been widely studied recently. A typical EDNN has multiple
prediction heads at different layers of the network backbone. During inference,
the model will exit at either the last prediction head or an intermediate
prediction head where the prediction confidence is higher than a predefined
threshold. To optimize the model, these prediction heads together with the
network backbone are trained on every batch of training data. This brings a
train-test mismatch problem that all the prediction heads are optimized on all
types of data in training phase while the deeper heads will only see difficult
inputs in testing phase. Treating training and testing inputs differently at
the two phases will cause the mismatch between training and testing data
distributions. To mitigate this problem, we formulate an EDNN as an additive
model inspired by gradient boosting, and propose multiple training techniques
to optimize the model effectively. We name our method BoostNet. Our experiments
show it achieves the state-of-the-art performance on CIFAR100 and ImageNet
datasets in both anytime and budgeted-batch prediction modes. Our code is
released at https://github.com/SHI-Labs/Boosted-Dynamic-Networks.
Related papers
- When do Convolutional Neural Networks Stop Learning? [0.0]
Convolutional Neural Networks (CNNs) have demonstrated outstanding performance in computer vision tasks.
Current practice is to stop training when the training loss decreases and the gap between training and validation error increases.
This research work introduces a hypothesis that analyzes the data variation across all the layers of a CNN variant to anticipate its near-optimal learning capacity.
arXiv Detail & Related papers (2024-03-04T20:35:09Z) - A Dynamical Model of Neural Scaling Laws [79.59705237659547]
We analyze a random feature model trained with gradient descent as a solvable model of network training and generalization.
Our theory shows how the gap between training and test loss can gradually build up over time due to repeated reuse of data.
arXiv Detail & Related papers (2024-02-02T01:41:38Z) - Deep Neural Networks Tend To Extrapolate Predictably [51.303814412294514]
neural network predictions tend to be unpredictable and overconfident when faced with out-of-distribution (OOD) inputs.
We observe that neural network predictions often tend towards a constant value as input data becomes increasingly OOD.
We show how one can leverage our insights in practice to enable risk-sensitive decision-making in the presence of OOD inputs.
arXiv Detail & Related papers (2023-10-02T03:25:32Z) - Decouple Graph Neural Networks: Train Multiple Simple GNNs Simultaneously Instead of One [60.5818387068983]
Graph neural networks (GNN) suffer from severe inefficiency.
We propose to decouple a multi-layer GNN as multiple simple modules for more efficient training.
We show that the proposed framework is highly efficient with reasonable performance.
arXiv Detail & Related papers (2023-04-20T07:21:32Z) - DCLP: Neural Architecture Predictor with Curriculum Contrastive Learning [5.2319020651074215]
We propose a Curricumum-guided Contrastive Learning framework for neural Predictor (DCLP)
Our method simplifies the contrastive task by designing a novel curriculum to enhance the stability of unlabeled training data distribution.
We experimentally demonstrate that DCLP has high accuracy and efficiency compared with existing predictors.
arXiv Detail & Related papers (2023-02-25T08:16:21Z) - Learning to Weight Samples for Dynamic Early-exiting Networks [35.03752825893429]
Early exiting is an effective paradigm for improving the inference efficiency of deep networks.
Our work proposes to adopt a weight prediction network to weight the loss of different training samples at each exit.
We show that the proposed weighting mechanism consistently improves the trade-off between classification accuracy and inference efficiency.
arXiv Detail & Related papers (2022-09-17T10:46:32Z) - Distributed Adversarial Training to Robustify Deep Neural Networks at
Scale [100.19539096465101]
Current deep neural networks (DNNs) are vulnerable to adversarial attacks, where adversarial perturbations to the inputs can change or manipulate classification.
To defend against such attacks, an effective approach, known as adversarial training (AT), has been shown to mitigate robust training.
We propose a large-batch adversarial training framework implemented over multiple machines.
arXiv Detail & Related papers (2022-06-13T15:39:43Z) - Neural Capacitance: A New Perspective of Neural Network Selection via
Edge Dynamics [85.31710759801705]
Current practice requires expensive computational costs in model training for performance prediction.
We propose a novel framework for neural network selection by analyzing the governing dynamics over synaptic connections (edges) during training.
Our framework is built on the fact that back-propagation during neural network training is equivalent to the dynamical evolution of synaptic connections.
arXiv Detail & Related papers (2022-01-11T20:53:15Z) - Retrieval Augmentation to Improve Robustness and Interpretability of
Deep Neural Networks [3.0410237490041805]
In this work, we actively exploit the training data to improve the robustness and interpretability of deep neural networks.
Specifically, the proposed approach uses the target of the nearest input example to initialize the memory state of an LSTM model or to guide attention mechanisms.
Results show the effectiveness of the proposed models for the two tasks, on the widely used Flickr8 and IMDB datasets.
arXiv Detail & Related papers (2021-02-25T17:38:31Z) - Predicting Neural Network Accuracy from Weights [25.73213712719546]
We show experimentally that the accuracy of a trained neural network can be predicted surprisingly well by looking only at its weights.
We release a collection of 120k convolutional neural networks trained on four different datasets to encourage further research in this area.
arXiv Detail & Related papers (2020-02-26T13:06:14Z)
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.