arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.09871cs.LGcs.AI
收藏

关于图生成模型的评价方法

On Evaluation Metrics for Graph Generative Models

University of Guelph(圭尔夫大学);Vector Institute(向量研究所);Samsung, SAIT AI Lab(三星综合技术院人工智能实验室);POSTECH(浦项科技大学)

Rylee Thompson, Boris Knyazev, Elahe Ghalebi, Jungtaek Kim, Graham W. Taylor

摘要:

在图像生成中,可以通过视觉检查模型输出来自然地评估生成模型。然而,对于图生成模型(GGM)来说,情况并非总是如此,这使得它们的评估具有挑战性。目前,用于评估GGM的标准过程受到三个关键限制:i)它不产生单个分数,这使得模型选择具有挑战性,ii)在许多情况下,它未能考虑潜在的边缘和节点特征,以及iii)它执行起来非常缓慢。在这项工作中,我们减轻了这些问题,通过搜索标量,域不可知的,可扩展的指标评估和排名GGM。为此,我们研究了现有的GGM指标和基于神经网络的指标,这些指标来自使用从特定任务网络中提取的嵌入的图像生成模型。受某些图神经网络(GNN)在没有任何训练的情况下提取有意义的图表示的能力的启发,我们引入了几个基于未经训练的随机GNN提取的特征的度量。我们设计的实验,彻底测试指标的能力,以衡量所生成的图形的多样性和保真度,以及他们的样本和计算效率。根据样本的数量,我们推荐两个基于随机GNN的指标中的一个,我们证明它比现有的指标更具表达力。虽然我们专注于将这些指标应用于GGM评估,但在实践中,这使得能够轻松计算任何两组图之间的相异性,而不管域如何。我们的代码发布于:https://github.com/uoguelph-mlrg/GGM-metrics。

英文摘要:

In image generation, generative models can be evaluated naturally by visually inspecting model outputs. However, this is not always the case for graph generative models (GGMs), making their evaluation challenging. Currently, the standard process for evaluating GGMs suffers from three critical limitations: i) it does not produce a single score which makes model selection challenging, ii) in many cases it fails to consider underlying edge and node features, and iii) it is prohibitively slow to perform. In this work, we mitigate these issues by searching for scalar, domain-agnostic, and scalable metrics for evaluating and ranking GGMs. To this end, we study existing GGM metrics and neural-network-based metrics emerging from generative models of images that use embeddings extracted from a task-specific network. Motivated by the power of certain Graph Neural Networks (GNNs) to extract meaningful graph representations without any training, we introduce several metrics based on the features extracted by an untrained random GNN. We design experiments to thoroughly test metrics on their ability to measure the diversity and fidelity of generated graphs, as well as their sample and computational efficiency. Depending on the quantity of samples, we recommend one of two random-GNN-based metrics that we show to be more expressive than pre-existing metrics. While we focus on applying these metrics to GGM evaluation, in practice this enables the ability to easily compute the dissimilarity between any two sets of graphs regardless of domain. Our code is released at: https://github.com/uoguelph-mlrg/GGM-metrics.

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。

↑