DMTG：一次性可微多任务分组
DMTG: One-Shot Differentiable Multi-Task Grouping
AI总结：
本文提出 DMTG，将多任务分组建模为基于 Categorical 分布的可微剪枝问题，一次性联合完成任务分组与权重训练，并在 CelebA、Taskonomy 上验证了性能与效率。
摘要：
我们旨在通过多任务分组（MTG）解决包含大量任务的多任务学习（MTL）问题。给定 N 个任务，我们提出在一次性过程中同时从 2^N 个候选方案中识别最佳任务组并训练模型权重，同时充分利用高阶任务亲和性。这不同于开创性方法依次识别分组并训练模型权重的做法，那些方法中的分组识别通常依赖启发式规则。因此，我们的方法不仅提高了训练效率，还缓解了依次流程所引入的目标偏差，这种偏差可能导致次优解。具体而言，我们将 MTG 表述为在由底层 Categorical 分布决定的自适应网络架构上的完全可微剪枝问题。为了将 N 个任务划分为 K 个组（由 K 个编码器分支表示），我们最初设置 KN 个任务头，其中每个分支连接到所有 N 个任务头，以利用高阶任务亲和性。随后，我们通过学习松弛的可微 Categorical 分布，逐步将 KN 个头剪枝至 N 个，确保每个任务被专门且唯一地划分到仅一个分支中。在 CelebA 和 Taskonomy 数据集上进行的大量实验及详细消融研究表明，我们的方法具有良好的性能和效率。代码可在 https://github.com/ethanygao/DMTG 获取。
英文摘要：
We aim to address Multi-Task Learning (MTL) with a large number of tasks by Multi-Task Grouping (MTG). Given N tasks, we propose to simultaneously identify the best task groups from 2^N candidates and train the model weights simultaneously in one-shot, with the high-order task-affinity fully exploited. This is distinct from the pioneering methods which sequentially identify the groups and train the model weights, where the group identification often relies on heuristics. As a result, our method not only improves the training efficiency, but also mitigates the objective bias introduced by the sequential procedures that potentially lead to a suboptimal solution. Specifically, we formulate MTG as a fully differentiable pruning problem on an adaptive network architecture determined by an underlying Categorical distribution. To categorize N tasks into K groups (represented by K encoder branches), we initially set up KN task heads, where each branch connects to all N task heads to exploit the high-order task-affinity. Then, we gradually prune the KN heads down to N by learning a relaxed differentiable Categorical distribution, ensuring that each task is exclusively and uniquely categorized into only one branch. Extensive experiments on CelebA and Taskonomy datasets with detailed ablations show the promising performance and efficiency of our method. The codes are available at https://github.com/ethanygao/DMTG.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
