# Efficient and scalable expansion of property limits                    <i>via</i>                    novelty-guided exploration

https://mdr.nims.go.jp/datasets/fa25c6e2-589c-43bd-af64-6fa6a7099c71

## File

- [d6dd00294c.pdf](https://mdr.nims.go.jp/filesets/5359bc53-4213-4b24-aefa-1763792d8c1b/download) ([Detail](https://mdr.nims.go.jp/filesets/5359bc53-4213-4b24-aefa-1763792d8c1b.md))

## Id

fa25c6e2-589c-43bd-af64-6fa6a7099c71

## Local identifier



## Visibility

open_to_public

## State

published

## Created at

2026-09-23T01:44:18.736161Z

## Updated at

2026-09-24T00:31:40.864635Z

## Published at

2026-09-24T03:43:07.735835Z

## Doi



## First published url

https://doi.org/10.1039/d6dd00294c

## Date published

2026-07-21

## Recorded date published

2026-9-16

## Resource type

journal_article

## Manuscript type

vor

## Collection



## Title

- title: |-
    Efficient and scalable expansion of property limits
                        <i>via</i>
                        novelty-guided exploration
  title_type: original
  lang: en

## Description

- description: Finding diverse and high-quality candidates in vast design spaces remains
    an important challenge in scientific research, including molecular design and
    material discovery. A recent line of work treats observed properties as samples
    from an unknown distribution and selects candidates that promote more uniform
    coverage of the property space using Stein discrepancy as the metric. However,
    these methods do not explicitly account for the information gain of newly acquired
    data, which can limit exploration of novel regions. In addition, they are not
    designed for efficient batch selection and may suffer performance degradation
    when applied in batch settings. Moreover, they incur substantial computational
    cost due to both large per-iteration overhead and increasing cost as the number
    of observations grows. To address these limitations, we incorporate predictive
    uncertainty into the objective function and introduce diversity-aware batch selection
    strategies to promote informative and diverse candidates. In addition, we propose
    a sampled Stein novelty estimator and efficient tensor calculations that significantly
    reduce computational overhead. Performance and runtime evaluations on molecular
    and materials datasets show that our method enables scalable and sample-efficient
    expansion of property-space coverage.
  description_type: abstract
  lang: und

## Creator

- name: Satoru Fujii
  role: author
  orcid: https://orcid.org/0009-0004-0324-8949
- name: Ryo Tamura
  role: author
  orcid: https://orcid.org/0000-0002-0349-358X
- name: Masato Sumita
  role: author
  orcid: https://orcid.org/0000-0002-3506-1028
- name: Kei Terayama
  role: author
  orcid: https://orcid.org/0000-0003-3914-248X

## Contact agent



## Publisher

organization: Royal Society of Chemistry (RSC)

## Managing organization



## Keyword

- subject: novelty-guided exploration
  schema: not_defined

## Rights

- identifier: https://creativecommons.org/licenses/by/4.0/

## Other identifier(s)



## Data origin



## Embargo



## Journal

- title: Digital Discovery
  issn: 2635098X
  volume: '5'
  issue: '9'
  start_page: 3756
  end_page: 3765

## Conference



## Related item



## Funding

- identifier: 25K01492
  funder_name: Japan Society for the Promotion of Science
- identifier: JPMXP1122683430
  funder_name: Ministry of Education, Culture, Sports, Science and Technology
- identifier: JPMJFR232U
  funder_name: Japan Science and Technology Agency

## Instrument



## Instrument operator



## Instrument managing organization



## Measurement method



## Specimen



## Chemical composition



## Structure for specimen



## Structural feature for specimen



## Specific property for specimen



## Process for specimen treatment



## Computational method



## Energy level/transition state



## Software



## Custom property



## Fileset

- id: 5359bc53-4213-4b24-aefa-1763792d8c1b
  filename: d6dd00294c.pdf
  content_type: application/pdf
  size: 1362716
  md5: 86874cea0ea81a364aecb788929b4b60

## Thumbnail

fileset_id: 5359bc53-4213-4b24-aefa-1763792d8c1b
filename: d6dd00294c.pdf