Machine Learning

1 readers

1 users here now

Community Rules:

Be nice. No offensive behavior, insults or attacks: we encourage a diverse community in which members feel safe and have a voice.
Make your post clear and comprehensive: posts that lack insight or effort will be removed. (ex: questions which are easily googled)
Beginner or career related questions go elsewhere. This community is focused in discussion of research and new projects that advance the state-of-the-art.
Limit self-promotion. Comments and posts should be first and foremost about topics of interest to ML observers and practitioners. Limited self-promotion is tolerated, but the sub is not here as merely a source for free advertisement. Such posts will be removed at the discretion of the mods.

founded 1 year ago

MODERATORS

communick@academy.garden

[R] Google DeepMind: 2.2 million new materials discovered using GNN (380k most stable, 736 already validated in labs) (alien.top)

submitted 11 months ago by Successful-Western27@alien.top to c/machinelearning@academy.garden

12 comments fedilink hide all child comments

Materials discovery is critical but tough. New materials enable big innovations like batteries or LEDs. But there are ~infinitely many combinations to try. Testing for them experimentally is slow and expensive.

So scientists and engineers want to simulate and screen materials on computers first. This can check way more candidates before real-world experiments. However, models historically struggled at accurately predicting if materials are stable.

Researchers at DeepMind made a system called GNoME that uses graph neural networks and active learning to push past these limits.

GNoME models materials' crystal structures as graphs and predicts formation energies. It actively generates and filters candidates, evaluating the most promising with simulations. This expands its knowledge and improves predictions over multiple cycles.

The authors introduced new ways to generate derivative structures that respect symmetries, further diversifying discoveries.

The results:

GNoME found 2.2 million new stable materials - equivalent to 800 years of normal discovery.
Of those, 380k were the most stable and candidates for validation.
736 were validated in external labs. These include a totally new diamond-like optical material and another that may be a superconductor.

Overall this demonstrates how scaling up deep learning can massively speed up materials innovation. As data and models improve together, it'll accelerate solutions to big problems needing new engineered materials.

TLDR: DeepMind made an AI system that uses graph neural networks to discover possible new materials. It found 2.2 million candidates, and over 300k are most stable. Over 700 have already been synthesized.

Full summary available here. Paper is here.

you are viewing a single comment's thread
view the rest of the comments

[–] DontShowYourBack@alien.top 1 points 11 months ago

My guess is that people tend to anthropomorphise many things, especially those they don’t really understand. A language model comes across as “smart” because we can converse with it in human ways. Thinking about material discovery is so distant for most that they don’t really grasp impressive and impactful this work can be.

Now, to me what’s happening here is extremely impressive and I’ve been a fan of deepmind their stem related work for a while. Seems like we could see some big acceleration in stem fields over next years, which will arguably have a bigger impact on people their lives than the things LLMs are used for right now.