arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1609.04508cs.LGcs.AIstat.ML
收藏

用于集体分类的列网络

Column Networks for Collective Classification

Deakin University(迪肯大学)

Trang Pham, Truyen Tran, Dinh Phung, Svetha Venkatesh

摘要:

关系学习处理以关系结构为特征的数据。一个重要的任务是集体分类,这是联合分类网络对象。虽然它有很大的希望产生比非集体分类器更好的准确性,但集体分类在计算上具有挑战性,并且没有利用深度学习的最新突破。我们提出了列网络(CLN),一种新的深度学习模型,用于多关系域中的集体分类。CLN具有许多理想的理论特性:(i)它编码任何两个实例之间的多关系;(ii)它是深而紧凑的,允许复杂的功能在网络级近似一个小的自由参数集;(iii)本地和关系特征同时学习;(iv)自然支持实例之间的长范围,高阶依赖关系;以及(v)至关重要的是,学习和推理是有效的,在网络的大小和关系的数量上是线性的。我们评估CLN在多个现实世界中的应用:(a)软件项目中的延迟预测,(b)PubMed糖尿病出版物分类和(c)电影类型分类。在所有应用中,CLN都表现出比最先进的竞争对手更高的准确性。

英文摘要:

Relational learning deals with data that are characterized by relational structures. An important task is collective classification, which is to jointly classify networked objects. While it holds a great promise to produce a better accuracy than non-collective classifiers, collective classification is computational challenging and has not leveraged on the recent breakthroughs of deep learning. We present Column Network (CLN), a novel deep learning model for collective classification in multi-relational domains. CLN has many desirable theoretical properties: (i) it encodes multi-relations between any two instances; (ii) it is deep and compact, allowing complex functions to be approximated at the network level with a small set of free parameters; (iii) local and relational features are learned simultaneously; (iv) long-range, higher-order dependencies between instances are supported naturally; and (v) crucially, learning and inference are efficient, linear in the size of the network and the number of relations. We evaluate CLN on multiple real-world applications: (a) delay prediction in software projects, (b) PubMed Diabetes publication classification and (c) film genre classification. In all applications, CLN demonstrates a higher accuracy than state-of-the-art rivals.

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。

↑