Learned Weight Sharing for Deep Multi-Task Learning by Natural Evolution Strategy and Stochastic Gradient Descent
This work addresses performance limitations in multi-task learning for AI applications, though it is incremental as it builds on existing methods.
The paper tackles the problem of determining which weights to share in deep multi-task learning, proposing an algorithm that learns weight assignments using natural evolution strategy and stochastic gradient descent, resulting in task-specific networks with lower test errors on three datasets compared to baselines.
In deep multi-task learning, weights of task-specific networks are shared between tasks to improve performance on each single one. Since the question, which weights to share between layers, is difficult to answer, human-designed architectures often share everything but a last task-specific layer. In many cases, this simplistic approach severely limits performance. Instead, we propose an algorithm to learn the assignment between a shared set of weights and task-specific layers. To optimize the non-differentiable assignment and at the same time train the differentiable weights, learning takes place via a combination of natural evolution strategy and stochastic gradient descent. The end result are task-specific networks that share weights but allow independent inference. They achieve lower test errors than baselines and methods from literature on three multi-task learning datasets.