论文标题
单个模型合奏使用伪标签和不同的向量
Single Model Ensemble using Pseudo-Tags and Distinct Vectors
论文作者
论文摘要
模型合奏技术通常会增加神经网络中的任务性能；但是，它们需要增加时间，记忆和管理工作。在这项研究中，我们提出了一种新型方法，该方法可以通过单个模型复制模型集合的效果。我们的方法使用k-distinct伪标签和k-Distinct向量在单个参数空间内创建K虚拟模型。几个数据集上的文本分类和序列标记任务的实验表明，我们的方法模仿或优于传统模型集合，具有1/k-times较少的参数。
Model ensemble techniques often increase task performance in neural networks; however, they require increased time, memory, and management effort. In this study, we propose a novel method that replicates the effects of a model ensemble with a single model. Our approach creates K-virtual models within a single parameter space using K-distinct pseudo-tags and K-distinct vectors. Experiments on text classification and sequence labeling tasks on several datasets demonstrate that our method emulates or outperforms a traditional model ensemble with 1/K-times fewer parameters.
