arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.08772cs.LGstat.ML
收藏

Set2Graph:从集合中学习图形

Set2Graph: Learning Graphs From Sets

Weizmann Institute of Science(魏茨曼科学研究所);New York University(纽约大学);NVIDIA Research(英伟达研究院)

Hadar Serviansky, Nimrod Segol, Jonathan Shlomi, Kyle Cranmer, Eilam Gross, Haggai Maron, Yaron Lipman

摘要:

机器学习中的许多问题可以转换为从集合到图的学习函数,或者更一般地转换为超图;简而言之,Set 2Graph函数。例子包括聚类,学习图上的顶点和边特征,以及学习集合中三元组的特征。建立Set 2Graph模型的一种自然方法是描述所有线性等变集到超图层,并将它们与非线性激活叠加。这带来了两个挑战:(i)这些网络的表达能力还没有得到很好的理解;(ii)这些模型将遭受高的,往往是棘手的计算和内存复杂性,因为它们的维度呈指数级增长。本文提出了一类学习Set 2Graph函数的神经网络模型,它既实用又具有最大表达能力(通用性),即能逼近紧集上任意连续的Set 2Graph函数.在不同的机器学习任务上测试这些模型,主要是粒子物理学的应用,我们发现它们对现有的基线有利。

英文摘要:

Many problems in machine learning can be cast as learning functions from sets to graphs, or more generally to hypergraphs; in short, Set2Graph functions. Examples include clustering, learning vertex and edge features on graphs, and learning features on triplets in a collection. A natural approach for building Set2Graph models is to characterize all linear equivariant set-to-hypergraph layers and stack them with non-linear activations. This poses two challenges: (i) the expressive power of these networks is not well understood; and (ii) these models would suffer from high, often intractable computational and memory complexity, as their dimension grows exponentially. This paper advocates a family of neural network models for learning Set2Graph functions that is both practical and of maximal expressive power (universal), that is, can approximate arbitrary continuous Set2Graph functions over compact sets. Testing these models on different machine learning tasks, mainly an application to particle physics, we find them favorable to existing baselines.

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。

↑