Joint Learning of Neural Networks via Iterative Reweighted Least Squares
arXiv:1905.06526
Abstract
In this paper, we introduce the problem of jointly learning feed-forward neural networks across a set of relevant but diverse datasets. Compared to learning a separate network from each dataset in isolation, joint learning enables us to extract correlated information across multiple datasets to significantly improve the quality of learned networks. We formulate this problem as joint learning of multiple copies of the same network architecture and enforce the network weights to be shared across these networks. Instead of hand-encoding the shared network layers, we solve an optimization problem to automatically determine how layers should be shared between each pair of datasets. Experimental results show that our approach outperforms baselines without joint learning and those using pretraining-and-fine-tuning. We show the effectiveness of our approach on three tasks: image classification, learning auto-encoders, and image generation.
References in corpus (9)
- Auto-Encoding Variational Bayes
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
- Improved Techniques for Training GANs
- Fine-Grained Visual Classification of Aircraft
- BEGAN: Boundary Equilibrium Generative Adversarial Networks
- Beyond Sharing Weights for Deep Domain Adaptation
- Domain Adaptation for Visual Applications: A Comprehensive Survey
- From source to target and back: symmetric bi-directional adaptive GAN