arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.10403cs.LGcs.CC
收藏

通过图神经网络解决可证明困难的代表性选择问题

Tackling Provably Hard Representative Selection via Graph Neural Networks

Google Research(谷歌研究院)

Mehran Kazemi, Anton Tsitsulin, Hossein Esfandiari, MohammadHossein Bateni, Deepak Ramachandran, Bryan Perozzi, Vahab Mirrokni

AI总结:

该研究证明面向学习的代表性选择问题多项式时间内难以近似求解,提出基于图神经网络的RS-GNN模型,利用图结构有效求解该问题,在8个基准上显著优于现有基线。

摘要:

代表性选择(Representative Selection,RS)是从数据集中找到一小部分能代表整个数据集的样本子集的问题。本文研究属性图场景下的RS问题,聚焦于寻找能让基于所选代表训练的模型精度最优的代表性节点。理论层面,我们为(无图结构场景下的)RS建立了新的难度结论:证明了一种极具实用性的变体(面向学习的RS)在多项式时间内无法以任何合理因子近似求解,这意味着广泛使用的代理函数的最优解与模型实际精度之间可能存在显著差距。随后我们研究了数据点之间存在(同质性)图结构或可构建此类结构的场景,证明通过恰当的建模方法,这类结构的存在可将困难的(面向学习的)RS问题转化为可有效求解的问题。为此,我们提出了RS-GNN,这是一种基于图神经网络的表示学习型RS模型。实验层面,我们在8个基准测试集上验证了RS-GNN的有效性:无论是预定义图结构的问题,还是由节点特征相似性诱导出图的问题,RS-GNN相较现有基线方法均取得了显著提升。

英文摘要:

Representative Selection (RS) is the problem of finding a small subset of exemplars from a dataset that is representative of the dataset. In this paper, we study RS for attributed graphs, and focus on finding representative nodes that optimize the accuracy of a model trained on the selected representatives. Theoretically, we establish a new hardness result forRS (in the absence of a graph structure) by proving that a particular, highly practical variant of it (RS for Learning) is hard to approximate in polynomial time within any reasonable factor, which implies a significant potential gap between the optimum solution of widely-used surrogate functions and the actual accuracy of the model. We then study the setting where a (homophilous) graph structure is available, or can be constructed, between the data points.We show that with an appropriate modeling approach, the presence of such a structure can turn a hard RS (for learning) problem into one that can be effectively solved. To this end, we develop RS-GNN, a representation learning-based RS model based on Graph Neural Networks. Empirically, we demonstrate the effectiveness of RS-GNN on problems with predefined graph structures as well as problems with graphs induced from node feature similarities, by showing that RS-GNN achieves significant improvements over established baselines on a suite of eight benchmarks.

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。

↑