arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.11698cs.LG
收藏

标签增强的数据增强

Data Augmentation For Label Enhancement

Southeast University(东南大学)

Zhiqiang Kou, Yuheng Jia, Jing Wang, Boyu Shi, Xin Geng

摘要:

标签分布(LD)使用描述度来描述实例,从而在标签歧义的情况下提供更细粒度的监督信息。然而,LD在许多现实世界的应用中是不可用的。为了获得LD,标签增强(LE)出现了从逻辑标签中恢复LD。现有的LE方法存在以下问题:(\textbf{i})使用逻辑标签来训练到LD的映射,但监督信息过于松散,导致模型预测不准确;(\textbf{ii})忽略特征冗余,直接使用收集的特征。为了求解(\textbf{i}),我们使用特征空间的拓扑来生成更准确的标签置信度。为了解决(\textbf{ii}),我们提出了一种新的监督LE降维方法,该方法将原始数据投影到低维特征空间。结合以上两个,我们得到的增广数据LE。在此基础上,提出了一种基于标签置信度和约简特征的非线性LE模型。在12个真实数据集上进行了大量的实验,结果表明,我们的方法始终优于其他五种比较方法。

英文摘要:

Label distribution (LD) uses the description degree to describe instances, which provides more fine-grained supervision information when learning with label ambiguity. Nevertheless, LD is unavailable in many real-world applications. To obtain LD, label enhancement (LE) has emerged to recover LD from logical label. Existing LE approach have the following problems: (\textbf{i}) They use logical label to train mappings to LD, but the supervision information is too loose, which can lead to inaccurate model prediction; (\textbf{ii}) They ignore feature redundancy and use the collected features directly. To solve (\textbf{i}), we use the topology of the feature space to generate more accurate label-confidence. To solve (\textbf{ii}), we proposed a novel supervised LE dimensionality reduction approach, which projects the original data into a lower dimensional feature space. Combining the above two, we obtain the augmented data for LE. Further, we proposed a novel nonlinear LE model based on the label-confidence and reduced features. Extensive experiments on 12 real-world datasets are conducted and the results show that our method consistently outperforms the other five comparing approaches.

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。

↑