Learning Compact Neural Networks with Deep Overparameterised Multitask Learning
This work addresses the problem of resource-efficient multitask learning for real-world applications, but it is incremental as it builds on existing overparameterization techniques.
The paper tackles the challenge of training compact neural networks to match or exceed the performance of larger models in multitask learning by introducing an overparameterized design that shares parameters effectively across tasks, achieving competitive results on NYUv2 and COCO datasets.
Compact neural network offers many benefits for real-world applications. However, it is usually challenging to train the compact neural networks with small parameter sizes and low computational costs to achieve the same or better model performance compared to more complex and powerful architecture. This is particularly true for multitask learning, with different tasks competing for resources. We present a simple, efficient and effective multitask learning overparameterisation neural network design by overparameterising the model architecture in training and sharing the overparameterised model parameters more effectively across tasks, for better optimisation and generalisation. Experiments on two challenging multitask datasets (NYUv2 and COCO) demonstrate the effectiveness of the proposed method across various convolutional networks and parameter sizes.