ET-AL: Entropy-targeted active learning for bias mitigation in
                    materials data

Zhang, Hengrui; Rondinelli, James M.; Chen, Wei

doi:10.1063/5.0138913

Cited by 13 publications

(7 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, an investigation of possible high-entropy alloys found wide disparities in compound space group (Figure b) . Even knowledge of what materials can be made is limited, as many observed materials are metastable, and computational thermochemistry data sets have biased distributions of formation energies for different structure types . Furthermore, nearly all experimental and computational data consider low-pressure systems, yet chemical bonding and periodic trends are radically different at high pressures relevant to materials under extreme conditions .…”

Section: The Challenge Of the Exceptionalmentioning

confidence: 99%

“…31 Even knowledge of what materials can be made is limited, as many observed materials are metastable, 35 and computational thermochemistry data sets have biased distributions of formation energies for different structure types. 36 Furthermore, nearly all experimental and computational data consider low-pressure systems, yet chemical bonding and periodic trends are radically different at high pressures relevant to materials under extreme conditions. 37 There remains plenty of room to discover new materials and molecules, and we are far from the regime of pure interpolation.…”

Section: The Challenge Of the Exceptional Iia What Is Exceptional?mentioning

confidence: 99%

“…The information entropy of the observed property distribution can be useful for identifying outcome imbalances, and active learning used to prioritize new samples to correct these imbalances, recently demonstrated in the context of formation energy/structure biases of intermetallic compounds. 36 To understand how properties are coupled to one another, it might even be useful to fill in equally rare contraindicated regions with undesirable trade-offs ("antiexceptional materials"). Learning general ways to reach arbitrary outputs can serve as waypoints to the desired solution.…”

Section: Vc Sample What Can Be Made and How To Make It � Defer Optimi...mentioning

confidence: 99%

See 2 more Smart Citations

In Pursuit of the Exceptional: Research Directions for Machine Learning in Chemical and Materials Science

Schrier,

Norquist,

Buonassisi

et al. 2023

J. Am. Chem. Soc.

View full text Add to dashboard Cite

Exceptional molecules and materials with one or more extraordinary properties are both technologically valuable and fundamentally interesting, because they often involve new physical phenomena or new compositions that defy expectations. Historically, exceptionality has been achieved through serendipity, but recently, machine learning (ML) and automated experimentation have been widely proposed to accelerate target identification and synthesis planning. In this Perspective, we argue that the data-driven methods commonly used today are well-suited for optimization but not for the realization of new exceptional materials or molecules. Finding such outliers should be possible using ML, but only by shifting away from using traditional ML approaches that tweak the composition, crystal structure, or reaction pathway. We highlight case studies of high-T c oxide superconductors and superhard materials to demonstrate the challenges of ML-guided discovery and discuss the limitations of automation for this task. We then provide six recommendations for the development of ML methods capable of exceptional materials discovery: (i) Avoid the tyranny of the middle and focus on extrema; (ii) When data are limited, qualitative predictions that provide direction are more valuable than interpolative accuracy; (iii) Sample what can be made and how to make it and defer optimization; (iv) Create room (and look) for the unexpected while pursuing your goal; (v) Try to fill-in-the-blanks of input and output space; (vi) Do not confuse human understanding with model interpretability. We conclude with a description of how these recommendations can be integrated into automated discovery workflows, which should enable the discovery of exceptional molecules and materials.

show abstract

Section: The Challenge Of the Exceptionalmentioning

confidence: 99%

Section: The Challenge Of the Exceptional Iia What Is Exceptional?mentioning

confidence: 99%

Section: Vc Sample What Can Be Made and How To Make It � Defer Optimi...mentioning

confidence: 99%

See 1 more Smart Citation

In Pursuit of the Exceptional: Research Directions for Machine Learning in Chemical and Materials Science

Schrier,

Norquist,

Buonassisi

et al. 2023

J. Am. Chem. Soc.

View full text Add to dashboard Cite

show abstract

“…31 Even knowledge of what materials can be made is limited, as many observed materials are metastable, 35 and computational thermochemistry datasets have biased distributions of formation energies for different structure types. 36 Furthermore, nearly all experimental and computational data considers low-pressure systems, yet chemical bonding and periodic trends are radically different at high pressures relevant to materials under extreme conditions. 37 There remains plenty of room to discover new materials and molecules, and we are far from the regime of pure interpolation.…”

Section: Figurementioning

confidence: 99%

“…The information entropy of the observed property distribution can be useful for identifying outcome imbalances, and active learning used to prioritize new samples to correct these imbalances, recently demonstrated in the context of formation energy/structure biases of intermetallic compounds. 36 To understand how properties are coupled to one another, it might even be useful to fill in equally rare contraindicated regions with undesirable tradeoffs ("anti-exceptional materials"). Learning general ways to reach arbitrary outputs, can serve as steppingstones to the desired solution.…”

Section: Try To Fill-in-the-blanks Of Input and Output Spacementioning

confidence: 99%

In Pursuit of the Exceptional: Research Directions for Machine Learning in Chemical and Materials Science

Schrier,

Norquist,

Buonassisi

et al. 2023

Preprint

View full text Add to dashboard Cite

Exceptional molecules and materials with one or more extraordinary properties are both technologically valuable and fundamentally interesting because they often involve new physical phenomena or new compositions that defy expectations. Historically, exceptionality has been achieved through serendipity, but recently, machine learning (ML) and automated experimentation have been widely proposed to accelerate target identification and synthesis planning. In this Perspective, we argue that the data-driven methods commonly used today are well-suited for optimization but not for realizing new exceptional materials or molecules. Finding such outliers should be possible using ML, but only by shifting away from using traditional ML approaches that tweak the composition, crystal structure, or reaction pathway. We highlight case studies of high-Tc oxide superconductors and superhard materials to demonstrate the challenges of ML-guided discovery and discuss the limitations of automation for this task. We then provide six recommendations for the development of ML methods capable of exceptional materials discovery: (i) Avoid the tyranny of the middle and focus on extrema; (ii) When data is limited, qualitative predictions that provide direction are more valuable than interpolative accuracy; (iii) Sample what can be made and how to make it, and defer optimization; (iv) Create room (and look) for the unexpected while pursuing your goal; (v) Try to fill-in-the-blanks of input and output space; (vi) Do not confuse human understanding with model interpretability. We conclude with a description of how these recommendations can be integrated into automated discovery workflows that should enable the discovery of exceptional molecules and materials.

show abstract

Data‐Driven Design for Metamaterials and Multiscale Systems: A Review

Lee,

Chen,

Wang

et al. 2023

Advanced Materials

Self Cite

View full text Add to dashboard Cite

Metamaterials are artificial materials designed to exhibit effective material parameters that go beyond those found in nature. Composed of unit cells with rich designability that are assembled into multiscale systems, they hold great promise for realizing next‐generation devices with exceptional, often exotic, functionalities. However, the vast design space and intricate structure–property relationships pose significant challenges in their design. A compelling paradigm that could bring the full potential of metamaterials to fruition is emerging: data‐driven design. This review provides a holistic overview of this rapidly evolving field, emphasizing the general methodology instead of specific domains and deployment contexts. Existing research is organized into data‐driven modules, encompassing data acquisition, machine learning‐based unit cell design, and data‐driven multiscale optimization. The approaches are further categorized within each module based on shared principles, analyze and compare strengths and applicability, explore connections between different modules, and identify open research questions and opportunities.

show abstract

ET-AL: Entropy-targeted active learning for bias mitigation in materials data

Cited by 13 publications

References 54 publications

In Pursuit of the Exceptional: Research Directions for Machine Learning in Chemical and Materials Science

In Pursuit of the Exceptional: Research Directions for Machine Learning in Chemical and Materials Science

In Pursuit of the Exceptional: Research Directions for Machine Learning in Chemical and Materials Science

Data‐Driven Design for Metamaterials and Multiscale Systems: A Review

Contact Info

Product

Resources

About