Avoiding Your Teacher’s Mistakes: Training Neural Networks with Controlled Weak Supervision
Mostafa Dehghani1 Aliaksei Severyn2 Sascha Rothe2 Jaap Kamps1 1 University of Amsterdam 2 Google Research
Abstract
In this paper, we propose a semi-supervised learning method where we train two neural networks in a multi-task fashion: a target network and a confidence network. The target network is optimized to perform a given task and is trained using a large set of unlabeled data that are weakly annotated. We propose to weight the gradient updates to the target network using the scores provided by the second confidence network, which is trained on a small amount of supervised data. Thus we avoid that the weight updates computed from noisy labels harm the quality of the target network model. We evaluate our learning strategy on two different tasks: document ranking and sentiment classification. The results demonstrate that our approach not only enhances the performance compared to the baselines but also speeds up the learning process from weak labels.
中文速览
深度神经网络在文档排序、情感分类等任务上表现出色，但严重依赖大量人工标注数据，而现实中精标数据往往极为有限。为此，研究者提出了一种半监督学习框架：用一个"弱标注器"（启发式规则或弱模型）自动生成大规模噪声标签，同时用少量精标数据训练一个"置信度网络"，该网络在反向传播时动态调整每条弱标注样本对"目标网络"参数更新的贡献权重，从而让可信度低的噪声样本少影响模型、可信度高的样本多贡献梯度。两个网络共享底层表示层，以多任务方式交替训练，既让置信度网络借助海量弱标注数据学到更好的表示，也让目标网络从少量精标数据中获益。在文档排序和情感分类两项任务上的实验表明，该方法不仅比传统"先预训练、再微调"的两阶段做法取得更好的性能，还能显著加快从弱标签中收敛的速度——这为现实中难以获取大规模精标数据的场景提供了一条切实可行的训练路径。
原文 arXiv:1711.00313;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1711.00313v2