论文标题
可控的动态多任务体系结构
Controllable Dynamic Multi-Task Architectures
论文作者
论文摘要
多任务学习通常会遇到任务之间的资源竞争，特别是当模型容量有限时。这项挑战激发了模型，这些模型可以控制任务的相对重要性和推理时间内的总计算成本。在这项工作中，我们提出了这样一个可控的多任务网络，该网络会动态调整其体系结构和权重，以匹配所需的任务偏好以及资源约束。与仅调整固定体系结构中权重的现有动态多任务方法相反，我们的方法具有动态控制总计算成本并匹配用户偏爱的任务重要性的灵活性。我们通过利用任务亲和力和一种新颖的分支正规损失来进行输入偏好，并因此预测具有适应权重的树结构模型，提出了对两个超网络的培训。在三个多任务基准测试的实验，即Pascal-Context，NYU-V2和CIFAR-100，显示了我们方法的功效。项目页面可从https://www.nec-labs.com/~mas/dymu获得。
Multi-task learning commonly encounters competition for resources among tasks, specifically when model capacity is limited. This challenge motivates models which allow control over the relative importance of tasks and total compute cost during inference time. In this work, we propose such a controllable multi-task network that dynamically adjusts its architecture and weights to match the desired task preference as well as the resource constraints. In contrast to the existing dynamic multi-task approaches that adjust only the weights within a fixed architecture, our approach affords the flexibility to dynamically control the total computational cost and match the user-preferred task importance better. We propose a disentangled training of two hypernetworks, by exploiting task affinity and a novel branching regularized loss, to take input preferences and accordingly predict tree-structured models with adapted weights. Experiments on three multi-task benchmarks, namely PASCAL-Context, NYU-v2, and CIFAR-100, show the efficacy of our approach. Project page is available at https://www.nec-labs.com/~mas/DYMU.
