On the Orthogonality of Knowledge Distillation with Other Techniques: From an Ensemble Perspective
arXiv:2009.04120
Abstract
To put a state-of-the-art neural network to practical use, it is necessary to design a model that has a good trade-off between the resource consumption and performance on the test set. Many researchers and engineers are developing methods that enable training or designing a model more efficiently. Developing an efficient model includes several strategies such as network architecture search, pruning, quantization, knowledge distillation, utilizing cheap convolution, regularization, and also includes any craft that leads to a better performance-resource trade-off. When combining these technologies together, it would be ideal if one source of performance improvement does not conflict with others. We call this property as the orthogonality in model efficiency. In this paper, we focus on knowledge distillation and demonstrate that knowledge distillation methods are orthogonal to other efficiency-enhancing methods both analytically and empirically. Analytically, we claim that knowledge distillation functions analogous to a ensemble method, bootstrap aggregating. This analytical explanation is provided from the perspective of implicit data augmentation property of knowledge distillation. Empirically, we verify knowledge distillation as a powerful apparatus for practical deployment of efficient neural network, and also introduce ways to integrate it with other methods effectively.
arXiv commentUnder review
References in corpus (27)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Distilling the Knowledge in a Neural Network
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
- mixup: Beyond Empirical Risk Minimization
- Neural Architecture Search with Reinforcement Learning
- Improved Regularization of Convolutional Neural Networks with Cutout
- FitNets: Hints for Thin Deep Nets
- Wide Residual Networks
- Do Deep Nets Really Need to be Deep?
- Understanding deep learning requires rethinking generalization
- Compressing Deep Convolutional Networks using Vector Quantization
- AutoAugment: Learning Augmentation Policies from Data
- Pruning Filters for Efficient ConvNets
- Born Again Neural Networks
- A Closer Look at Memorization in Deep Networks
- Shake-Shake regularization
- Neural Optimizer Search with Reinforcement Learning
- ShakeDrop Regularization for Deep Residual Learning
- Deep ReLU Networks Have Surprisingly Few Activation Patterns
- Moonshine: Distilling with Cheap Convolutions
- Paraphrasing Complex Network: Network Compression via Factor Transfer
- Feature-map-level Online Adversarial Knowledge Distillation
- A novel channel pruning method for deep neural network compression
- Deep Mutual Learning
- Neural Architecture Search without Training
- Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness