arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.03480cs.LGcs.AI
收藏

GSHOT:带标签图的少样本生成建模

GSHOT: Few-shot Generative Modeling of Labeled Graphs

Indian Institute of Technology Delhi(印度理工学院德里分校)

Sahil Manchanda, Shubham Gupta, Sayan Ranu, Srikanta Bedathur

AI总结:

针对深度图生成建模需要大量训练样本的问题,提出基于元学习的少样本带标签图生成框架GSHOT,通过迁移辅助数据集元知识和自步微调适配新数据集,在有限样本场景下生成图的保真度优于现有基线。

摘要:

深度图生成建模近年来因其直接学习潜在隐藏图分布的出色能力而备受关注。尽管这些技术取得了初步成功,但与大多数现有深度生成方法一样,它们需要大量训练样本才能学习到良好的模型。遗憾的是,在罕见病药物发现等场景中,往往无法获得大量训练样本。与此同时,少样本学习的最新进展为训练数据有限的应用场景打开了大门。在本研究中,我们提出了此前尚未被探索的少样本图生成建模范式。为此,我们开发了GSHOT——一种基于元学习的少样本带标签图生成建模框架。GSHOT学习从相似的辅助图数据集中迁移元知识。借助这些先验经验,GSHOT通过自步微调快速适配未见过的图数据集。我们在来自不同领域、训练样本有限的数据集上开展了大量实验,结果表明,与现有基线方法相比,GSHOT生成的图保真度更高。

英文摘要:

Deep graph generative modeling has gained enormous attraction in recent years due to its impressive ability to directly learn the underlying hidden graph distribution. Despite their initial success, these techniques, like much of the existing deep generative methods, require a large number of training samples to learn a good model. Unfortunately, large number of training samples may not always be available in scenarios such as drug discovery for rare diseases. At the same time, recent advances in few-shot learning have opened door to applications where available training data is limited. In this work, we introduce the hitherto unexplored paradigm of few-shot graph generative modeling. Towards this, we develop GSHOT, a meta-learning based framework for few-shot labeled graph generative modeling. GSHOT learns to transfer meta-knowledge from similar auxiliary graph datasets. Utilizing these prior experiences, GSHOT quickly adapts to an unseen graph dataset through self-paced fine-tuning. Through extensive experiments on datasets from diverse domains having limited training samples, we establish that GSHOT generates graphs of superior fidelity compared 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。

↑