arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1901.08296cs.LGcs.CVcs.NEstat.ML
收藏

属性图上的深度学习:从图到它们的嵌入和返回的旅程

Deep Learning on Attributed Graphs: A Journey from Graphs to Their Embeddings and Back

Université Paris-Est(巴黎东部大学);Ecole des Ponts(法国国立桥路学校);KU Leuven(鲁汶大学);Australian National University(澳大利亚国立大学);INRIA Sophia Antipolis(法国国家信息与自动化研究所索菲亚·安蒂波利斯分部)

Martin Simonovsky

摘要:

图是表示实体对之间关系的强大概念。具有底层图结构的数据可以在许多学科中找到,并且人们自然希望更好地理解这些数据。近年来,深度学习(DL)在各种机器学习任务中取得了重大突破,特别是在数据以网格结构化的情况下,例如文本、语音或图像理解。然而,令人惊讶的是,很少有人直接探索DL在任意图形结构数据上的适用性。本论文的目标是研究图上深度学习的体系结构,并研究如何将适用于序列和图像数据的概念转移、适应或推广到这个领域。我们专注于两个重要的原语:将图或其节点嵌入到连续的向量空间表示(编码)中,反之,从这些向量生成图(解码)。为此,我们作出以下贡献。首先,我们介绍了边缘条件卷积(ECC),在空间域中执行的图上的卷积类操作,其中过滤器是基于边缘属性动态生成的。该方法适用于任意结构和变化结构的图的编码。其次,我们提出了超级点图,一个中间点云表示与丰富的边缘属性编码对象部分之间的上下文关系。在此基础上,利用椭圆曲线对大规模点云数据进行分割,而不牺牲细节。第三,我们提出了GraphVAE,一个图形生成器,使我们能够解码图形与变量,但上限的节点数量利用近似图匹配对齐的预测与其输入的自动编码器。该方法适用于分子生成的任务。

英文摘要:

A graph is a powerful concept for representation of relations between pairs of entities. Data with underlying graph structure can be found across many disciplines and there is a natural desire for understanding such data better. Deep learning (DL) has achieved significant breakthroughs in a variety of machine learning tasks in recent years, especially where data is structured on a grid, such as in text, speech, or image understanding. However, surprisingly little has been done to explore the applicability of DL on arbitrary graph-structured data directly. The goal of this thesis is to investigate architectures for DL on graphs and study how to transfer, adapt or generalize concepts that work well on sequential and image data to this domain. We concentrate on two important primitives: embedding graphs or their nodes into a continuous vector space representation (encoding) and, conversely, generating graphs from such vectors back (decoding). To that end, we make the following contributions. First, we introduce Edge-Conditioned Convolutions (ECC), a convolution-like operation on graphs performed in the spatial domain where filters are dynamically generated based on edge attributes. The method is used to encode graphs with arbitrary and varying structure. Second, we propose SuperPoint Graph, an intermediate point cloud representation with rich edge attributes encoding the contextual relationship between object parts. Based on this representation, ECC is employed to segment large-scale point clouds without major sacrifice in fine details. Third, we present GraphVAE, a graph generator allowing us to decode graphs with variable but upper-bounded number of nodes making use of approximate graph matching for aligning the predictions of an autoencoder with its inputs. The method is applied to the task of molecule generation.

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。

↑