论文标题
单个验证模型的各种彩票促进了合奏
Diverse Lottery Tickets Boost Ensemble from a Single Pretrained Model
论文作者
论文摘要
结合是一种流行的方法，用于提高绩效作为最后的度假胜地。但是，从单个预验证的模型中进行的多个模型并不是很有效。这可能是由于合奏成员之间缺乏多样性所致。本文提出了多机票集合，该集合会对单个预审计模型的不同子网进行填充，并将其合并。我们从经验上证明，赢得门票子网比密集网络产生的预测更多样化，它们的合奏在某些任务上的表现优于标准合奏。
Ensembling is a popular method used to improve performance as a last resort. However, ensembling multiple models finetuned from a single pretrained model has been not very effective; this could be due to the lack of diversity among ensemble members. This paper proposes Multi-Ticket Ensemble, which finetunes different subnetworks of a single pretrained model and ensembles them. We empirically demonstrated that winning-ticket subnetworks produced more diverse predictions than dense networks, and their ensemble outperformed the standard ensemble on some tasks.
