Fea2Lab:基于多标记学习的特征到标签生成模型

传统多标记学习方法通常只考虑和示例相关联的单个特征向量以及无差别地预测全体标签，从而忽视了与示例相似的其他示例及隐含的标签属性，造成输入空间特征信息较少、标签属性被忽略和对大标记空间预测效果差等问题.为解决以上问题，文章转化传统多标记学习任务为多标记学习的序列到序列任务，并由此提出新的多标记学习标签生成神经网络模型(Fea2Lab模型):通过交错的顺序排列示例和相似示例形成链式特征向量序列，来增加输入空间特征信息；通过挖掘标签属性来有差别地预测标签；通过在解码流程中使用全局标签信息，来缓解预测过程中出现的错误标签级联问题.在多个数据集上的实验结果和消融实验表明转化任务和Fea2Lab模型的合理性、可行性及有效性.

Fea2Lab: A Feature-to-Label Generation Model Based on Multi-Label Learning

Only a single feature vector associated with the instance is considered in the traditional multi-label learning method, which predicts the overall label without a difference, thereby ignoring other similar instances and hiding label attributes. That results in such problems as less input spatial feature information, label attributes ignored and poor prediction about the large label space. In order to solve the above problems, the traditional multi-label learning task is converted into the sequence-to-sequence task of multi-label learning. On this basis is proposed Fea2Lab, a novel neural network model of multi-label learning label sequence generation. In this model, the chained feature vector input sequence formed by staggered sequential arrangement instances and similar instances is used to enrich the input spatial feature information. The label attributes are mined to predict the labels in a targeted manner. In the decoding process, the global label information is used to ease the problem that the cascading of the wrong label appears. The experimental results and ablation experiments on multiple data sets show the rationality, feasibility and effectiveness of the transformation task and the Fea2Lab model.