arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1904.08049cs.LGcs.IRstat.ML
收藏

用于多标签分类的神经消息传递

Neural Message Passing for Multi-Label Classification

University of Virginia(弗吉尼亚大学)

Jack Lanchantin, Arshdeep Sekhon, Yanjun Qi

摘要:

多标签分类(MLC)是为给定样本分配一组目标标签的任务。MLC中组合标签相互作用的建模一直是一个长期的挑战。我们提出了标签消息传递(LaMP)神经网络,以有效地模拟多个标签的联合预测。LaMP将标签视为标签交互图上的节点,并使用基于注意力的神经消息传递来计算每个标签节点的隐藏表示。注意力使LaMP能够为每个标签的邻居节点分配不同的重要性,学习标签如何交互(隐式)。所提出的模型简单,准确,可解释,结构不可知,适用于预测密集标签,因为LaMP是令人难以置信的并行化。我们在七个真实世界的MLC数据集上验证了LaMP的好处,涵盖了广泛的输入/输出类型,并优于最先进的结果。值得注意的是,LaMP能够直观地解释每个标签的分类如何取决于样本的元素,同时依赖于它与其他标签的相互作用。我们在https://github.com/QData/LaMP上提供代码和数据集

英文摘要:

Multi-label classification (MLC) is the task of assigning a set of target labels for a given sample. Modeling the combinatorial label interactions in MLC has been a long-haul challenge. We propose Label Message Passing (LaMP) Neural Networks to efficiently model the joint prediction of multiple labels. LaMP treats labels as nodes on a label-interaction graph and computes the hidden representation of each label node conditioned on the input using attention-based neural message passing. Attention enables LaMP to assign different importance to neighbor nodes per label, learning how labels interact (implicitly). The proposed models are simple, accurate, interpretable, structure-agnostic, and applicable for predicting dense labels since LaMP is incredibly parallelizable. We validate the benefits of LaMP on seven real-world MLC datasets, covering a broad spectrum of input/output types and outperforming the state-of-the-art results. Notably, LaMP enables intuitive interpretation of how classifying each label depends on the elements of a sample and at the same time rely on its interaction with other labels. We provide our code and datasets at https://github.com/QData/LaMP

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。

↑