Latent Space Bayesian Optimization With Latent Data Augmentation for Enhanced Exploration

IF 2.7 4区 计算机科学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Onur Boyar;Ichiro Takeuchi
{"title":"Latent Space Bayesian Optimization With Latent Data Augmentation for Enhanced Exploration","authors":"Onur Boyar;Ichiro Takeuchi","doi":"10.1162/neco_a_01708","DOIUrl":null,"url":null,"abstract":"Latent space Bayesian optimization (LSBO) combines generative models, typically variational autoencoders (VAE), with Bayesian optimization (BO), to generate de novo objects of interest. However, LSBO faces challenges due to the mismatch between the objectives of BO and VAE, resulting in poor exploration capabilities. In this article, we propose novel contributions to enhance LSBO efficiency and overcome this challenge. We first introduce the concept of latent consistency/inconsistency as a crucial problem in LSBO, arising from the VAE-BO mismatch. To address this, we propose the latent consistent aware-acquisition function (LCA-AF) that leverages consistent points in LSBO. Additionally, we present LCA-VAE, a novel VAE method that creates a latent space with increased consistent points through data augmentation in latent space and penalization of latent inconsistencies. Combining LCA-VAE and LCA-AF, we develop LCA-LSBO. Our approach achieves high sample efficiency and effective exploration, emphasizing the significance of addressing latent consistency through the novel incorporation of data augmentation in latent space within LCA-VAE in LSBO. We showcase the performance of our proposal via de novo image generation and de novo chemical design tasks.","PeriodicalId":54731,"journal":{"name":"Neural Computation","volume":"36 11","pages":"2446-2478"},"PeriodicalIF":2.7000,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neural Computation","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10810345/","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Latent space Bayesian optimization (LSBO) combines generative models, typically variational autoencoders (VAE), with Bayesian optimization (BO), to generate de novo objects of interest. However, LSBO faces challenges due to the mismatch between the objectives of BO and VAE, resulting in poor exploration capabilities. In this article, we propose novel contributions to enhance LSBO efficiency and overcome this challenge. We first introduce the concept of latent consistency/inconsistency as a crucial problem in LSBO, arising from the VAE-BO mismatch. To address this, we propose the latent consistent aware-acquisition function (LCA-AF) that leverages consistent points in LSBO. Additionally, we present LCA-VAE, a novel VAE method that creates a latent space with increased consistent points through data augmentation in latent space and penalization of latent inconsistencies. Combining LCA-VAE and LCA-AF, we develop LCA-LSBO. Our approach achieves high sample efficiency and effective exploration, emphasizing the significance of addressing latent consistency through the novel incorporation of data augmentation in latent space within LCA-VAE in LSBO. We showcase the performance of our proposal via de novo image generation and de novo chemical design tasks.
潜空间贝叶斯优化与潜数据增强,以加强探索。
潜空间贝叶斯优化(LSBO)将生成模型(通常是变异自动编码器(VAE))与贝叶斯优化(BO)相结合,生成新的感兴趣对象。然而,由于贝叶斯优化(BO)和变异自编码器(VAE)的目标不匹配,LSBO 面临着挑战,导致探索能力低下。在本文中,我们将提出新的贡献,以提高 LSBO 的效率并克服这一挑战。我们首先介绍了潜在一致性/不一致性的概念,它是 LSBO 中的一个关键问题,由 VAE-BO 不匹配引起。为了解决这个问题,我们提出了潜在一致性感知获取函数(LCA-AF),它利用了 LSBO 中的一致性点。此外,我们还提出了 LCA-VAE,这是一种新颖的 VAE 方法,它通过在潜在空间中增加数据和对潜在不一致性进行惩罚来创建一个具有更多一致点的潜在空间。结合 LCA-VAE 和 LCA-AF,我们开发了 LCA-LSBO。我们的方法实现了高采样效率和有效探索,通过在 LSBO 的 LCA-VAE 中新加入潜空间数据增强,强调了解决潜一致性问题的重要性。我们通过全新图像生成和全新化学设计任务展示了我们建议的性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Neural Computation
Neural Computation 工程技术-计算机:人工智能
CiteScore
6.30
自引率
3.40%
发文量
83
审稿时长
3.0 months
期刊介绍: Neural Computation is uniquely positioned at the crossroads between neuroscience and TMCS and welcomes the submission of original papers from all areas of TMCS, including: Advanced experimental design; Analysis of chemical sensor data; Connectomic reconstructions; Analysis of multielectrode and optical recordings; Genetic data for cell identity; Analysis of behavioral data; Multiscale models; Analysis of molecular mechanisms; Neuroinformatics; Analysis of brain imaging data; Neuromorphic engineering; Principles of neural coding, computation, circuit dynamics, and plasticity; Theories of brain function.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信