Adaptive Weight Assignment Scheme For Multi-task Learning
This is an incremental improvement for multi-task learning practitioners, addressing a known bottleneck in loss weighting.
The paper tackles the problem of improper weight assignment in multi-task learning, where equal weighting reduces performance, by proposing a simple adaptive weight assignment scheme that emphasizes difficult tasks. Empirical results show it achieves better performance than two popular methods on both image and textual data.
Deep learning based models are used regularly in every applications nowadays. Generally we train a single model on a single task. However, we can train multiple tasks on a single model under multi-task learning settings. This provides us many benefits like lesser training time, training a single model for multiple tasks, reducing overfitting, improving performances etc. To train a model in multi-task learning settings we need to sum the loss values from different tasks. In vanilla multi-task learning settings we assign equal weights but since not all tasks are of similar difficulty we need to allocate more weight to tasks which are more difficult. Also improper weight assignment reduces the performance of the model. We propose a simple weight assignment scheme in this paper which improves the performance of the model and puts more emphasis on difficult tasks. We tested our methods performance on both image and textual data and also compared performance against two popular weight assignment methods. Empirical results suggest that our proposed method achieves better results compared to other popular methods.