Workshop
AI for Accelerated Materials Design (AI4Mat)
Santiago Miret 路 Marta Skreta 路 Zamyla Morgan-Chan 路 Benjamin Sanchez-Lengeling 路 Shyue Ping Ong 路 Alan Aspuru-Guzik
Room 386
Fri 2 Dec, 6 a.m. PST
Self-Driving Materials Laboratories have greatly advanced the automation of material design and discovery. They require the integration of diverse fields and consist of three primary components, which intersect with many AI-related research topics:
- AI-Guided Design. This component intersects heavily with algorithmic research at NeurIPS, including (but not limited to) various topic areas such as: Reinforcement Learning and data-driven modeling of physical phenomena using Neural Networks (e.g. Graph Neural Networks and Machine Learning For Physics).
- Automated Chemical Synthesis. This component intersects significantly with robotics research represented at NeurIPS, and includes several parts of real-world robotic systems such as: managing control systems (e.g. Reinforcement Learning) and different sensor modalities (e.g. Computer Vision), as well as predictive models for various phenomena (e.g. Data-Based Prediction of Chemical Reactions).
- Automated Material Characterization. This component intersects heavily with a diverse set of supervised learning techniques that are well-represented at NeurIPS such as: computer vision for microscopy images and automated machine learning based analysis of data generated from different kinds of instruments (e.g. X-Ray based diffraction data for determining material structure).
Schedule
Fri 6:00 a.m. - 6:30 a.m.
|
Opening Remarks
(
AI4Mat Program Committee
)
>
SlidesLive Video |
馃敆 |
Fri 6:30 a.m. - 7:30 a.m.
|
Everyday Research Challenges in AI for Automated Materials Design
(
Panel
)
>
SlidesLive Video |
馃敆 |
Fri 7:30 a.m. - 8:00 a.m.
|
AI-Guided Design Keynote
(
Keynote
)
>
SlidesLive Video |
Elsa Olivetti 馃敆 |
Fri 8:00 a.m. - 8:30 a.m.
|
Coffee Break
|
馃敆 |
Fri 8:30 a.m. - 8:40 a.m.
|
Open MatSci ML Toolkit: A Flexible Framework for Machine Learning in Materials Science
(
Spotlight
)
>
link
SlidesLive Video |
Santiago Miret 路 Kin Long Kelvin Lee 路 Carmelo Gonzales 路 Marcel Nassar 路 Krzysztof Sadowski 馃敆 |
Fri 8:40 a.m. - 8:50 a.m.
|
Accelerating the Discovery of Rare Materials with Bounded Optimization Techniques
(
Spotlight
)
>
link
SlidesLive Video |
Alexander E. Siemenn 路 zekun ren 路 Qianxiao Li 路 Tonio Buonassisi 馃敆 |
Fri 8:50 a.m. - 9:00 a.m.
|
A Data-efficient Multiobjective Machine Learning Method For 3D-printed Architected Materials Design
(
Spotlight
)
>
link
SlidesLive Video |
Bo Peng 路 Ye Wei 路 Yu Qin 路 Jiabao Dai 路 Liuliu Han 路 Yue Li 路 Peng Wen 馃敆 |
Fri 9:00 a.m. - 9:10 a.m.
|
MolPAL: Software for Sample Efficient High-Throughput Virtual Screening
(
Spotlight
)
>
link
SlidesLive Video |
David Graff 路 Connor Coley 馃敆 |
Fri 9:10 a.m. - 9:30 a.m.
|
AI-Guided Design Spotlight Q&A
(
Q&A
)
>
SlidesLive Video |
馃敆 |
Fri 9:30 a.m. - 10:30 a.m.
|
Poster Session
(
Poster Session
)
>
|
馃敆 |
Fri 10:30 a.m. - 11:00 a.m.
|
Lunch
(
Lunch
)
>
|
馃敆 |
Fri 11:00 a.m. - 11:30 a.m.
|
Automated Materials Synthesis Keynote
(
Keynote
)
>
SlidesLive Video |
Connor Coley 馃敆 |
Fri 11:30 a.m. - 11:40 a.m.
|
Element-Wise Formulation of Inorganic Retrosynthesis
(
Spotlight
)
>
link
SlidesLive Video |
Seongmin Kim 路 Juhwan Noh 路 Geun Ho Gu 路 SHU-AN CHEN 路 Yousung Jung 馃敆 |
Fri 11:40 a.m. - 11:50 a.m.
|
A High-Throughput Platform for Efficient Exploration of Polypeptides Chemical Space via Automation and Machine Learning
(
Spotlight
)
>
link
SlidesLive Video |
Guangqi Wu 路 Connor Coley 路 Hua Lu 馃敆 |
Fri 11:50 a.m. - 12:00 p.m.
|
Differential top-k learning for template-based single-step retrosynthesis
(
Spotlight
)
>
link
SlidesLive Video |
Andres M Bran 路 Philippe Schwaller 馃敆 |
Fri 12:00 p.m. - 12:10 p.m.
|
A self-driving laboratory optimizes a scalable materials manufacturing process
(
Spotlight
)
>
link
SlidesLive Video |
12 presentersConnor Rupnow 路 Benjamin MacLeod 路 Mehrdad Mokhtari 路 Karry Ocean 路 Kevan Dettelbach 路 Daniel Lin 路 Fraser Parlane 路 Hsi Chiu 路 Michael Rooney 路 Christopher Waizenegger 路 Elija de Hoog 路 Curtis Berlinguette |
Fri 12:10 p.m. - 12:30 p.m.
|
Automated Materials Synthesis Spotlight Q&A
(
Q&A
)
>
SlidesLive Video |
馃敆 |
Fri 12:30 p.m. - 1:00 p.m.
|
Automated Materials Characterization Keynote
(
Keynote
)
>
SlidesLive Video |
Huolin Xin 馃敆 |
Fri 1:00 p.m. - 1:30 p.m.
|
Coffee Break
|
馃敆 |
Fri 1:30 p.m. - 1:40 p.m.
|
Robust design of semi-automated clustering models for 4D-STEM datasets
(
Spotlight
)
>
link
SlidesLive Video |
Alexandra Bruefach 路 Colin Ophus 路 Mary Scott 馃敆 |
Fri 1:40 p.m. - 1:50 p.m.
|
A Survey on Evaluation Metrics for Synthetic Material Micro-Structure Images from Generative Models
(
Spotlight
)
>
link
SlidesLive Video |
Devesh Shah 路 Anirudh Suresh 路 Alemayehu Solomon Admasu 路 devesh upadhyay 路 Kalyanmoy Deb 馃敆 |
Fri 1:50 p.m. - 2:00 p.m.
|
Experimental platform and digital twin for AI-driven materials optimization and discovery for microelectronics using atomic layer deposition
(
Spotlight
)
>
link
SlidesLive Video |
Angel Yanguas-Gil 路 Steve Letourneau 路 Noah Paulson 路 Jeffrey Elam 馃敆 |
Fri 2:00 p.m. - 2:10 p.m.
|
The Largest Knowledge Graph in Materials Science - Entities, Relations, and Link Prediction through Graph Representation Learning
(
Spotlight
)
>
link
SlidesLive Video |
Vineeth Venugopal 路 Sumit Pai 路 Elsa Olivetti 馃敆 |
Fri 2:10 p.m. - 2:30 p.m.
|
Automated Materials Synthesis Spotlight Q&A
(
Q&A
)
>
SlidesLive Video |
馃敆 |
Fri 2:30 p.m. - 3:00 p.m.
|
Closing Remarks
(
AI4Mat Program Committee
)
>
SlidesLive Video |
馃敆 |
-
|
Integrating AI, automation and multiscale simulations for end-to-end design of phase-separating proteins ( Poster ) > link | Arvind Ramanathan 馃敆 |
-
|
Geometric Considerations for Normalization Layers in Equivariant Neural Networks ( Poster ) > link | Max Aalto 路 Ekdeep S Lubana 路 Hidenori Tanaka 馃敆 |
-
|
Multi-Objective GFlowNets ( Poster ) > link | Moksh Jain 路 Sharath Chandra Raparthy 路 Alex Hernandez-Garcia 路 Jarrid Rector-Brooks 路 Yoshua Bengio 路 Santiago Miret 路 Emmanuel Bengio 馃敆 |
-
|
Generative Design of Material Microstructures for Organic Solar Cells using Diffusion Models ( Poster ) > link | Ethan Herron 路 Xian Yeow Lee 路 Aditya Balu 路 Baskar Ganapathysubramanian 路 Soumik Sarkar 路 Adarsh Krishnamurthy 馃敆 |
-
|
Assessing multi-objective optimization of molecules with genetic algorithms against relevant baselines ( Poster ) > link | Nathanael Kusanda 路 Gary Tom 路 Riley Hickman 路 AkshatKumar Nigam 路 Kjell Jorner 路 Alan Aspuru-Guzik 馃敆 |
-
|
Information Recovery via Matrix Completion for Piezoresponse Force Microscopy Data ( Poster ) > link | Henry Yuchi 路 Kerisha Williams 路 Gardy Ligonde 路 Matthew Repasky 路 Yao Xie 路 Nazanin Bassiri-Gharb 馃敆 |
-
|
Self-driving Multimodal Studies at User Facilities ( Poster ) > link |
14 presentersPhillip M Maffettone 路 Daniel Allan 路 Stuart Campbell 路 Matthew Carbone 路 Thomas Caswell 路 Brian DeCost 路 Dmitri Gavrilov 路 Marcus Hanwell 路 Howie Joress 路 Joshua Lynch 路 Bruce Ravel 路 Stuart Wilkins 路 Jakub Wlodek 路 Daniel Olds |
-
|
On Multi-information source Constraint Active Search ( Poster ) > link | Gustavo Malkomes 路 Bolong Cheng 路 Santiago Miret 馃敆 |
-
|
PhAST: Physics-Aware, Scalable, and Task-specific GNNs for accelerated catalyst design ( Poster ) > link | ALEXANDRE DUVAL 路 Victor Schmidt 路 Alex Hernandez-Garcia 路 Santiago Miret 路 Yoshua Bengio 路 David Rolnick 馃敆 |
-
|
Autonomous Materials Discovery for Organic Photovoltaics ( Poster ) > link | Changhyun Hwang 路 Seungjoo Yi 路 David Friday 路 Nicholas Angello 路 Tiara Torres-Flores 路 Nick Jackson 路 Martin Burke 路 Charles Schroeder 路 Ying Diao 馃敆 |
-
|
Human-in-the-Loop Approaches For Task Guidance In Manufacturing Settings ( Poster ) > link | Ramesh Manuvinakurike 路 Santiago Miret 路 Richard Beckwith 路 Saurav Sahay 路 Giuseppe Raffa 馃敆 |
-
|
Is GPT-3 all you need for machine learning for chemistry? ( Poster ) > link | Kevin Jablonka 路 Philippe Schwaller 路 Berend Smit 馃敆 |
-
|
More trustworthy Bayesian optimization of materials properties by adding human into the loop ( Poster ) > link | Armi Tiihonen 路 Louis Filstroff 路 Petrus Mikkola 路 Emma Lehto 路 Samuel Kaski 路 Milica Todorovi膰 路 Patrick Rinke 馃敆 |
-
|
Actively Learning Costly Reward Functions for Reinforcement Learning ( Poster ) > link | Andr茅 Eberhard 路 Houssam Metni 路 Georg Fahland 路 Alexander Stroh 路 Pascal Friederich 馃敆 |
-
|
Deep Reinforcement Learning for Inverse Inorganic Materials Design ( Poster ) > link | Elton Pan 路 Christopher Karpovich 路 Elsa Olivetti 馃敆 |
-
|
MEGAN: Multi Explanation Graph Attention Network ( Poster ) > link | Jonas Teufel 路 Luca Torresi 路 Patrick Reiser 路 Pascal Friederich 馃敆 |
-
|
Transfer Learning Lithium and Electrolyte Potential Energy Surfaces from Pure and Hybrid DFT ( Poster ) > link | James Stevenson 路 Leif Jacobson 路 Garvit Agarwal 路 Steven Dajnowicz 馃敆 |
-
|
Multivariate Prediction Intervals for Random Forests ( Poster ) > link | Brendan Folie 路 Maxwell Hutchinson 馃敆 |
-
|
DeepStruc: Towards structure solution from pair distribution function data using deep generative models ( Poster ) > link | Emil Thyge Skaaning Kj忙r 路 Andy S. Anker 路 Marcus Weng 路 Simon J. L. Billinge 路 Raghavendra Selvan 路 Kirsten Jensen 馃敆 |
-
|
A Generalized Framework for Microstructural Optimization using Neural Networks ( Poster ) > link | Saketh Sridhara 路 Aaditya Chandrasekhar 路 Krishnan Suresh 馃敆 |
-
|
Graph Contrastive Learning for Materials ( Poster ) > link | Teddy Koker 路 Keegan Quigley 路 Will Spaeth 路 Nathan Frey 路 Lin Li 馃敆 |
-
|
Group SELFIES: A Robust Fragment-Based Molecular String Representation ( Poster ) > link | Austin Cheng 路 Andy Cai 路 Santiago Miret 路 Gustavo Malkomes 路 Mariano Phielipp 路 Alan Aspuru-Guzik 馃敆 |
-
|
Extracting Structural Motifs from Pair Distribution Function Data of Nanostructures using Explainable Machine Learning ( Poster ) > link |
11 presentersAndy S. Anker 路 Emil Thyge Skaaning Kj忙r 路 Mikkel Juelsholt 路 Troels Christiansen 路 Susanne Skj忙rv酶 路 Mads J酶rgensen 路 Innokenty Kantor 路 Daniel S酶rensen 路 Simon J. L. Billinge 路 Raghavendra Selvan 路 Kirsten Jensen |
-
|
Neural Structure Fields with Application to Crystal Structure Auto-Encoders ( Poster ) > link | Naoya Chiba 路 Yuta Suzuki 路 Tatsunori Taniai 路 Ryo Igarashi 路 Yoshitaka Ushiku 路 Kotaro Saito 路 Kanta Ono 馃敆 |
-
|
Hyperparameter Optimization of Graph Neural Networks for the OpenCatalyst Dataset: A Case Study ( Poster ) > link | Carmelo Gonzales 路 Eric Lee 路 Kin Long Kelvin Lee 路 Joyce Tang 路 Santiago Miret 馃敆 |
-
|
AI-assisted chemical reaction impurity prediction and propagation ( Poster ) > link | Somesh Mohapatra 路 Daniel Griffin 馃敆 |
-
|
Conformer Search Using SE3-Transformers and Imitation Learning ( Poster ) > link | Luca Thiede 路 Santiago Miret 路 Krzysztof Sadowski 路 Haoping Xu 路 Mariano Phielipp 路 Alan Aspuru-Guzik 馃敆 |
-
|
A deep learning and data archaeology approach for mosquito repellent discovery ( Poster ) > link |
13 presentersJennifer Wei 路 Marnix Vlot 路 Benjamin Sanchez-Lengeling 路 Brian Lee 路 Luuk Berning 路 Martijn Vos 路 Rob Henderson 路 Wesley Qian 路 D. Michael Ando 路 Kurt Groetsch 路 Richard Gerkin 路 Alexander Wiltschko 路 Koen Dechering |