arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.04649cs.LGstat.ML
收藏

学习通过深度互动重新调整权重

Learning to Reweight with Deep Interactions

Microsoft Research Asia(微软亚洲研究院)

Yang Fan, Yingce Xia, Lijun Wu, Shufang Xie, Weiqing Liu, Jiang Bian, Tao Qin, Xiang-Yang Li

摘要:

最近,教学的概念已被引入到机器学习中,其中教师模型被用于通过数据选择、损失函数设计等来指导学生模型(其将用于实际任务)的训练。学习重新加权,这是一种使用教师模型重新加权训练数据的特定类型的教学,由于其简单性和有效性而备受关注。在现有的学习重新加权工作中,教师模型只利用浅层/表面信息,如训练迭代次数和来自训练/验证集的学生模型的损失/准确性,但忽略了学生模型的内部状态,这限制了学习重新加权的潜力。在这项工作中,我们提出了一种改进的数据重新加权算法,其中学生模型提供其内部状态的教师模型,和教师模型返回自适应权重的训练样本,以加强学生模型的训练。教师模型与学生模型使用从验证集传播的Meta梯度进行联合训练。对带有干净/噪声标签的图像分类和神经机器翻译的实验表明,我们的算法比以前的方法有显着的改进。

英文摘要:

Recently, the concept of teaching has been introduced into machine learning, in which a teacher model is used to guide the training of a student model (which will be used in real tasks) through data selection, loss function design, etc. Learning to reweight, which is a specific kind of teaching that reweights training data using a teacher model, receives much attention due to its simplicity and effectiveness. In existing learning to reweight works, the teacher model only utilizes shallow/surface information such as training iteration number and loss/accuracy of the student model from training/validation sets, but ignores the internal states of the student model, which limits the potential of learning to reweight. In this work, we propose an improved data reweighting algorithm, in which the student model provides its internal states to the teacher model, and the teacher model returns adaptive weights of training samples to enhance the training of the student model. The teacher model is jointly trained with the student model using meta gradients propagated from a validation set. Experiments on image classification with clean/noisy labels and neural machine translation empirically demonstrate that our algorithm makes significant improvement over previous methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑