arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.07729cs.LGeess.SPstat.ML
收藏

用于多关系鲁棒学习的张量图卷积网络

Tensor Graph Convolutional Networks for Multi-relational and Robust Learning

Univ. of Minnesota(明尼苏达大学);King Juan Carlos Univ.(胡安卡洛斯国王大学)

Vassilis N. Ioannidis, Antonio G. Marques, Georgios B. Giannakis

摘要:

“数据泛滥”的时代重新激发了人们对基于图的学习方法及其广泛应用的兴趣,从社会学和生物学到交通和通信。在这种图形感知方法的背景下,本文介绍了一种张量-图卷积网络(TGCN),用于从与由张量表示的图形集合相关联的数据进行可扩展的半监督学习(SSL)。新型TGCN架构的关键方面是通过可学习的权重动态适应张量图中的不同关系,以及考虑基于图的正则化器以促进平滑性并减轻过度参数化。最终目标是设计一个强大的学习架构,能够:发现复杂和高度非线性的数据关联,组合(和选择)多种类型的关系,随着图的大小优雅地扩展,并保持对图边缘扰动的鲁棒性。所提出的架构不仅在节点自然涉及不同关系的应用中(例如,在社交网络中捕获家庭、友谊和工作关系的多关系图),而且在鲁棒学习设置中,其中图需要一定程度的不确定性,并且不同的张量板对应于标称图的不同版本(实现)。数值测试表明,所提出的架构相对于标准GCN实现了显着提高的性能,应对最先进的对抗攻击,并导致显着的SSL性能超过蛋白质相互作用网络。

英文摘要:

The era of "data deluge" has sparked renewed interest in graph-based learning methods and their widespread applications ranging from sociology and biology to transportation and communications. In this context of graph-aware methods, the present paper introduces a tensor-graph convolutional network (TGCN) for scalable semi-supervised learning (SSL) from data associated with a collection of graphs, that are represented by a tensor. Key aspects of the novel TGCN architecture are the dynamic adaptation to different relations in the tensor graph via learnable weights, and the consideration of graph-based regularizers to promote smoothness and alleviate over-parameterization. The ultimate goal is to design a powerful learning architecture able to: discover complex and highly nonlinear data associations, combine (and select) multiple types of relations, scale gracefully with the graph size, and remain robust to perturbations on the graph edges. The proposed architecture is relevant not only in applications where the nodes are naturally involved in different relations (e.g., a multi-relational graph capturing family, friendship and work relations in a social network), but also in robust learning setups where the graph entails a certain level of uncertainty, and the different tensor slabs correspond to different versions (realizations) of the nominal graph. Numerical tests showcase that the proposed architecture achieves markedly improved performance relative to standard GCNs, copes with state-of-the-art adversarial attacks, and leads to remarkable SSL performance over protein-to-protein interaction networks.

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。

↑