In multi-task learning (MTL), gradient balancing has recently attracted more research interest than loss balancing since it often leads to better performance. However, loss balancing is much more efficient than gradient balancing, and thus it is still worth further exploration in MTL. Note that prior studies typically ignore that there exist varying improvable gaps across multiple tasks, where the improvable gap per task is defined as the distance between the current training progress and desired final training progress. Therefore, after loss balancing, the performance imbalance still arises in many cases. In this paper, following the loss balancing framework, we propose two novel improvable gap balancing (IGB) algorithms for MTL: one takes a simple heuristic, and the other (for the first time) deploys deep reinforcement learning for MTL. Particularly, instead of directly balancing the losses in MTL, both algorithms choose to dynamically assign task weights for improvable gap balancing. Moreover, we combine IGB and gradient balancing to show the complementarity between the two types of algorithms. Extensive experiments on two benchmark datasets demonstrate that our IGB algorithms lead to the best results in MTL via loss balancing and achieve further improvements when combined with gradient balancing. Code is available at https://github.com/YanqiDai/IGB4MTL.

翻译：在多任务学习（MTL）中，梯度平衡相较于损失平衡近年来吸引了更多研究兴趣，因为其往往能带来更好的性能。然而，损失平衡的效率远高于梯度平衡，因此仍值得在MTL中进一步探索。值得注意的是，先前的研究通常忽略了多个任务之间存在不同的可改进间隙——每个任务的可改进间隙定义为当前训练进度与期望最终训练进度之间的距离。因此，在损失平衡之后，性能不平衡在许多情况下仍然会出现。本文在损失平衡框架下，提出两种新颖的MTL可改进间隙平衡（IGB）算法：一种采用简单启发式方法，另一种（首次）将深度强化学习应用于MTL。特别地，两种算法均不直接平衡MTL中的损失，而是选择动态分配任务权重以实现可改进间隙平衡。此外，我们将IGB与梯度平衡相结合，展示了这两类算法之间的互补性。在两个基准数据集上的大量实验表明，我们的IGB算法通过损失平衡在MTL中取得了最佳结果，并且与梯度平衡结合时实现了进一步性能提升。代码开源地址：https://github.com/YanqiDai/IGB4MTL。