Label distribution learning (LDL) differs from multi-label learning which aims at representing the polysemy of instances by transforming single-label values into descriptive degrees. Unfortunately, the feature space of the label distribution dataset is affected by human factors and the inductive bias of the feature extractor causing uncertainty in the feature space. Especially, for datasets with small-scale feature spaces (the feature space dimension $\approx$ the label space), the existing LDL algorithms do not perform well. To address this issue, we seek to model the uncertainty augmentation of the feature space to alleviate the problem in LDL tasks. Specifically, we start with augmenting each feature value in the feature vector of a sample into a vector (sampling on a Gaussian distribution function). Which, the variance parameter of the Gaussian distribution function is learned by using a sub-network, and the mean parameter is filled by this feature value. Then, each feature vector is augmented to a matrix which is fed into a mixer with local attention (\textit{TabMixer}) to extract the latent feature. Finally, the latent feature is squeezed to yield an accurate label distribution via a squeezed network. Extensive experiments verify that our proposed algorithm can be competitive compared to other LDL algorithms on several benchmarks.
翻译:标签分布学习( LDL) 与多标签学习( LDL) 不同, 多标签学习的目的是通过将单标签值转换成描述度来代表实例的多元性。 不幸的是, 标签分布数据集的特性空间受到人类因素的影响, 以及特性提取器的感应偏差导致特性空间的不确定性。 特别是, 对于具有小规模特性空间的数据集( 特征空间维度$\ approx$标签空间), 现有的 LDL 算法效果不佳。 为了解决这个问题, 我们试图模拟特性空间的不确定性增强, 以缓解 LDL 任务中的问题。 具体地说, 我们开始将一个样本的特性矢量中的每个特性值都添加到一个矢量中( 在 Gausian 分布函数上取样 ) 。 其中, Gausian 分布函数的差异参数通过子网络学习, 而平均参数则由这个特性值来填充。 然后, 每一个特性矢量矢量将添加到一个矩阵, 与本地注意的混合体(\ textitit{ TabMixer} 来提取隐性特性。 最后, 我们的矩阵的模型将可被压缩到其它的运算到其它的逻辑矩阵。