BOARD

NOTICE

HOME > Board > Notice
GNN (Optimization, Materials design, schduling)
  • 관리자
  • |
  • 783
  • |
  • 2021-01-17

Top Applications of Graph Neural Networks 2021 | by Sergei Ivanov | Criteo R&D Blog | Jan, 2021 | Medium

At the beginning of the year, I have a feeling that Graph Neural Nets (GNNs) became a buzzword. As a researcher in this field, I feel a little bit proud (at least not ashamed) to say that I work on this. It was not always the case: three years ago when I was talking to my peers, who got busy working on GANs and Transformers, the general impression that they got on me was that I was working on exotic niche problems. Well, the field has matured substantially and here I propose to have a look at the top applications of GNNs that we have recently had.

Combinatorial Optimization

Solutions to combinatorial optimization (CO) problems are the workhorse of many important applications in finance, logistics, energy, life sciences, and hardware design. Most of these problems are formulated with graphs. As a result, a lot of ink over the last century has been spilled on algorithmic approaches that solve CO problems more efficiently; however, the ML-driven revolution of modern computing offered a new compelling way of learning solutions to such problems.

Google Brain team used GNN to optimize the power, area, and performance of a chip block for new hardware such as Google’s TPU. A computer chip can be divided into a graph of memory and logic components, each represented by its coordinate and type. Determining the placement of each component, while adhering to the constraints of density and routing congestion, is a laborious process that is still the art produced by electrical engineers. Their GNN model coupled with policy and value RL functions is capable to generate optimized placements for circuit chips matching or outperforming manually designed hardware.

Physics/Chemistry

Life sciences have benefited from representing the interactions between particles or molecules as a graph and then predicting the properties of such systems with GNNs. In Open Catalyst project by Facebook and CMU, the ultimate goal is to find new ways to store renewable energy such as coming from the sun or wind. One of the potential solutions is to convert such energy into other fuels, for example, hydrogen, through chemical reactions. However, this requires discovering new catalysts that drive the chemical reactions at a high rate, and known methods such as DFT are very expensive. The Open Catalyst project opens up the largest dataset of catalysts, their DFT relaxations, and GNN baselines. The hope is to find new low-cost molecules that would augment currently costly simulations, which take days, with efficient ML approximations of energy and forces of molecules, which can take milliseconds.

Image for post
Examples of initial and relaxed states of an adsorbate (small connected molecule) and a catalyst’s surface. To find a relaxed state for one pair adsorbate-catalyst one has to perform expensive DFT simulations that may take days. Zitnick et al. 2020

Researchers from DeepMind also applied GNN to simulate the dynamics of complex systems of particles such as water or sand. By predicting at each step a relative movement of each particle it’s possible to reconstruct plausibly the dynamics of the whole system and further gain insights about the underlying laws governing the motion. This, for example, was used for understanding the glass transition, one of the most interesting unsolved problems in solid state theory. Using GNNs not only allows simulating the dynamics during the transition but also gives a better understanding of how particles influence one another depending on the distance and time.

Furthermore, Fermilab, a US-based physics lab, works towards moving GNNs to production at the Large Hadron Collider (LHC) at CERN. The goal is to process millions of images and select those that could be relevant to the discovery of new particles. Their mission is to implement GNNs on FPGAs and integrate them with data acquisition processors, which would allow running GNNs remotely around the world. For more applications of GNNs in particle physics, check out this recent survey.

Drug Discovery

이전글 [남기전학생,JCR3%,IF=9,JHM]AI-CC연계 다매체모델 PAH거동및위해성평가
다음글 Open Catalyst project(FacebookAI-CMU)