Associated Learning: Decomposing End-to-end Backpropagation based on Auto-encoders and Target Propagation

Abstract

Backpropagation (BP) is the cornerstone of today's deep learning algorithms, but it is inefficient partially because of backward locking, which means updating the weights of one layer locks the weight updates in the other layers. Consequently, it is challenging to apply parallel computing or a pipeline structure to update the weights in different layers simultaneously. In this paper, we introduce a novel learning structure called associated learning (AL), which modularizes the network into smaller components, each of which has a local objective. Because the objectives are mutually independent, AL can learn the parameters in different layers independently and simultaneously, so it is feasible to apply a pipeline structure to improve the training throughput. Specifically, this pipeline structure improves the complexity of the training time from O(nl), which is the time complexity when using BP and stochastic gradient descent (SGD) for training, to O(n + l), where n is the number of training instances and l is the number of hidden layers. Surprisingly, even though most of the parameters in AL do not directly interact with the target variable, training deep models by this method yields accuracies comparable to those from models trained using typical BP methods, in which all parameters are used to predict the target variable. Consequently, because of the scalability and the predictive power demonstrated in the experiments, AL deserves further study to determine the better hyperparameter settings, such as activation function selection, learning rate scheduling, and weight initialization, to accumulate experience, as we have done over the years with the typical BP method. Additionally, perhaps our design can also inspire new network designs for deep learning. Our implementation is available at https://github.com/SamYWK/Associated_Learning.

arXiv comment34 pages, 6 figures, 7 tables

References in corpus (16)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• A Convergence Theory for Deep Learning via Over-Parameterization
• Towards Biologically Plausible Deep Learning
• Direct Feedback Alignment Provides Learning in Deep Neural Networks
• Measuring the Effects of Data Parallelism on Neural Network Training
• Training Neural Networks Without Gradients: A Scalable ADMM Approach
• Training Neural Networks with Local Error Signals
• On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization
• How Auto-Encoders Could Provide Credit Assignment in Deep Networks via Target Propagation
• Decoupled Neural Interfaces using Synthetic Gradients
• Decoupled Parallel Backpropagation with Convergence Guarantee
• $\mathcal{G}$-softmax: Improving Intra-class Compactness and Inter-class Separability of Features
• Training Neural Networks Using Features Replay
• Greedy Layerwise Learning Can Scale to ImageNet
• Conducting Credit Assignment by Aligning Local Representations
• Weighted-SVD: Matrix Factorization with Weights on the Latent Factors