arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1908.02436cs.LGcs.CVstat.ML
收藏

连续图流

Continuous Graph Flow

Borealis AI(北极光人工智能);Princeton University(普林斯顿大学);Simon Fraser University(西蒙弗雷泽大学)

Zhiwei Deng, Megha Nawhal, Lili Meng, Greg Mori

摘要:

在本文中,我们提出了连续图流,一个生成的连续流为基础的方法,旨在模拟复杂的分布图结构的数据。一旦学习,该模型可以应用于任意图,定义由图表示的随机变量的概率密度。它被制定为一个常微分方程系统与共享和可重用的功能,操作的图形。这导致了一种新型的神经图消息传递方案,该方案随着时间的推移执行连续的消息传递。这类模型提供了几个优点:灵活的表示,可以推广到可变的数据维度;能够在复杂的数据分布中建模依赖关系;可逆和内存效率;以及准确和有效的数据可能性计算。我们证明了我们的模型在不同领域的各种生成任务的有效性:图形生成,图像拼图生成和布局生成场景图。我们提出的模型实现了显着更好的性能相比,国家的最先进的模型。

英文摘要:

In this paper, we propose Continuous Graph Flow, a generative continuous flow based method that aims to model complex distributions of graph-structured data. Once learned, the model can be applied to an arbitrary graph, defining a probability density over the random variables represented by the graph. It is formulated as an ordinary differential equation system with shared and reusable functions that operate over the graphs. This leads to a new type of neural graph message passing scheme that performs continuous message passing over time. This class of models offers several advantages: a flexible representation that can generalize to variable data dimensions; ability to model dependencies in complex data distributions; reversible and memory-efficient; and exact and efficient computation of the likelihood of the data. We demonstrate the effectiveness of our model on a diverse set of generation tasks across different domains: graph generation, image puzzle generation, and layout generation from scene graphs. Our proposed model achieves significantly better performance compared to state-of-the-art models.

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。

↑