论文标题
多任务学习作为谈判游戏
Multi-Task Learning as a Bargaining Game
论文作者
论文摘要
在多任务学习（MTL）中，对联合模型进行了培训，可以同时对几个任务进行预测。联合培训降低了计算成本并提高数据效率；但是，由于这些不同任务的梯度可能需要冲突，因此训练MTL的联合模型通常比其相应的单任务同行产生的性能低。减轻此问题的一种常见方法是使用特定的启发式方法将每个任务梯度组合到联合更新方向上。在本文中，我们建议将梯度组合步骤视为一个议价游戏，在该游戏中，任务就在参数更新的联合方向达成协议。在某些假设下，议价问题具有独特的解决方案，称为NASH讨价还价解决方案，我们建议将其用作多任务学习的原则方法。我们描述了一种新的MTL优化程序NASH-MTL，并为其收敛性得出了理论保证。从经验上讲，我们表明NASH-MTL在各个领域的多个MTL基准上实现了最先进的结果。
In Multi-task learning (MTL), a joint model is trained to simultaneously make predictions for several tasks. Joint training reduces computation costs and improves data efficiency; however, since the gradients of these different tasks may conflict, training a joint model for MTL often yields lower performance than its corresponding single-task counterparts. A common method for alleviating this issue is to combine per-task gradients into a joint update direction using a particular heuristic. In this paper, we propose viewing the gradients combination step as a bargaining game, where tasks negotiate to reach an agreement on a joint direction of parameter update. Under certain assumptions, the bargaining problem has a unique solution, known as the Nash Bargaining Solution, which we propose to use as a principled approach to multi-task learning. We describe a new MTL optimization procedure, Nash-MTL, and derive theoretical guarantees for its convergence. Empirically, we show that Nash-MTL achieves state-of-the-art results on multiple MTL benchmarks in various domains.
