The generalization capacity of Multi-Task Learning (MTL) becomes limited when unrelated tasks negatively impact each other by updating shared parameters with conflicting gradients, resulting in negative transfer and a reduction in MTL accuracy compared to single-task learning (STL). Recently, there has been an increasing focus on the fairness of MTL models, necessitating the optimization of both accuracy and fairness for individual tasks. Similarly to how negative transfer affects accuracy, task-specific fairness considerations can adversely influence the fairness of other tasks when there is a conflict of fairness loss gradients among jointly learned tasks, termed bias transfer. To address both negative and bias transfer in MTL, we introduce a novel method called FairBranch. FairBranch branches the MTL model by assessing the similarity of learned parameters, grouping related tasks to mitigate negative transfer. Additionally, it incorporates fairness loss gradient conflict correction between adjoining task-group branches to address bias transfer within these task groups. Our experiments in tabular and visual MTL problems demonstrate that FairBranch surpasses state-of-the-art MTL methods in terms of both fairness and accuracy.

翻译：多任务学习（MTL）的泛化能力在无关任务因梯度冲突更新共享参数而相互负面影响时受到限制，导致负迁移，并使MTL准确率低于单任务学习（STL）。近年来，MTL模型的公平性日益受到关注，这要求同时优化各个任务的准确率与公平性。类似于负迁移对准确率的影响，当联合学习任务间的公平性损失梯度存在冲突时，针对特定任务的公平性考量会对其他任务的公平性产生不利影响，这种现象称为偏置迁移。为解决MTL中的负迁移与偏置迁移，我们提出了一种名为FairBranch的新方法。FairBranch通过评估所学参数的相似性对MTL模型进行分支，将相关任务分组以缓解负迁移。此外，该方法在相邻任务组分支之间引入公平性损失梯度冲突校正，以应对任务组内部的偏置迁移。我们在表格与视觉MTL问题上的实验表明，FairBranch在公平性与准确率方面均超越了当前最先进的MTL方法。