arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.06375cs.LGcs.AI
收藏

HOT-VAE:通过基于注意力的变分自编码器学习多标签分类的高阶标签相关性

HOT-VAE: Learning High-Order Label Correlation for Multi-Label Classification via Attention-Based Variational Autoencoders

Cornell University(康奈尔大学);Cornell Lab of Ornithology(康奈尔鸟类学实验室)

Wenting Zhao, Shufeng Kong, Junwen Bai, Daniel Fink, Carla Gomes

摘要:

了解环境特征如何影响从个别物种到物种群落的生物多样性格局,对于减轻全球变化的影响至关重要。保护规划和监测的一个中心目标是能够准确预测物种群落的发生以及这些群落如何随空间和时间变化。这就引出了计算机科学领域一个具有挑战性且长期存在的问题--如何对数百个标签进行准确的多标签分类?这个问题的关键挑战是它的指数大小的输出空间与要预测的标签的数量有关。因此,必须通过利用标签之间的相关性(或依赖性)来促进学习过程。以前的方法主要集中在对标签对的相关性进行建模;然而,现实世界对象之间的复杂关系往往超过二阶。本文提出了一种新的多标签分类框架--高阶连接变分自编码器(HOT-VAE),它实现了自适应的高阶标签相关学习。我们通过实验验证了我们的模型在传统的F1分数和各种生态指标上的鸟类分布数据集上优于现有的最先进的方法。为了证明我们的方法是通用的,我们还在几个应用领域的其他七个公共真实世界数据集上进行了实证分析,Hot-VAE表现出优于以前的方法的性能。

英文摘要:

Understanding how environmental characteristics affect bio-diversity patterns, from individual species to communities of species, is critical for mitigating effects of global change. A central goal for conservation planning and monitoring is the ability to accurately predict the occurrence of species communities and how these communities change over space and time. This in turn leads to a challenging and long-standing problem in the field of computer science - how to perform ac-curate multi-label classification with hundreds of labels? The key challenge of this problem is its exponential-sized output space with regards to the number of labels to be predicted.Therefore, it is essential to facilitate the learning process by exploiting correlations (or dependency) among labels. Previous methods mostly focus on modelling the correlation on label pairs; however, complex relations between real-world objects often go beyond second order. In this paper, we pro-pose a novel framework for multi-label classification, High-order Tie-in Variational Autoencoder (HOT-VAE), which per-forms adaptive high-order label correlation learning. We experimentally verify that our model outperforms the existing state-of-the-art approaches on a bird distribution dataset on both conventional F1 scores and a variety of ecological metrics. To show our method is general, we also perform empirical analysis on seven other public real-world datasets in several application domains, and Hot-VAE exhibits superior performance to previous methods.

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。

↑