Results 111 to 120 of about 6,698,922 (291)

Sustainable Materials Design With Multi‐Modal Artificial Intelligence

open access: yesAdvanced Science, EarlyView.
Critical mineral scarcity, high embodied carbon, and persistent pollution from materials processing intensify the need for sustainable materials design. This review frames the problem as multi‐objective optimization under heterogeneous, high‐dimensional evidence and highlights multi‐modal AI as an enabling pathway.
Tianyi Xu   +8 more
wiley   +1 more source

Hyperbolic Graph Wavelet Neural Network

open access: yesTsinghua Science and Technology
Graph neural networks (GNNs), grounded in spatial or spectral domains, have achieved remarkable success in learning graph representations in Euclidean space.
Wenjie Zheng   +5 more
doaj   +1 more source

Barron Space for Graph Convolutional Neural Networks

open access: yesJournal of Fourier Analysis and Applications
Graph convolutional neural network (GCNN) operates on graph domain and it has achieved a superior performance to accomplish a wide range of tasks. In this paper, we introduce a Barron space of functions on a compact domain of graph signals. We prove that the proposed Barron space is a reproducing kernel Banach space, it can be decomposed into the union
Seok-Young Chung, Qiyu Sun
openaire   +2 more sources

Unifying Composition and Process Design: A Heterogeneous Graph Neural Network for Discovering High‐Performance Cu Alloys

open access: yesAdvanced Science, EarlyView.
By overcoming the fixed‐path limitations of conventional machine learning, a heterogeneous graph neural network fundamentally reconstructs material data representation. Integrating variable processing sequences with intrinsic elemental features, this framework enables exploratory optimization across high‐dimensional spaces.
Jie Yin   +12 more
wiley   +1 more source

Spectral-designed depthwise separable graph neural networks

open access: yes, 2020
International audienceThis paper aims at revisiting Convolutional Graph Neural Networks (ConvGNNs) by designing new graph convolutions in spectral domain with a custom frequency profile while applying them in the spatial domain.
Renton, Guillaume   +5 more
core   +2 more sources

Efficient Screening of Organic Singlet Fission Molecules Using Graph Neural Networks

open access: yesAdvanced Science, EarlyView.
A high‐throughput screening framework based on graph neural networks (GNNs) and multi‐level validation facilitates the identification of singlet fission (SF) candidates. By efficiently predicting excitation energies across 20 million molecules, and integrating TDDFT calculations, synthetic accessibility assessments, and GW+BSE calculations, this ...
Li Fu   +5 more
wiley   +1 more source

Broadening Hard‐Magnet Discovery Beyond Symmetry Constraints via Unified Effective Anisotropy

open access: yesAdvanced Science, EarlyView.
A unified effective‐anisotropy descriptor (Keff) extends hard‐magnet screening across all seven crystal systems, beyond the uniaxial restriction of conventional searches. Machine‐learning screening of 9320 known ferromagnets and diffusion‐model generation together yield 38 rare‐earth‐free or ‐lean candidates with DFT‐validated magnetic hardness (κ > 1),
Hojae Kim   +5 more
wiley   +1 more source

Construction of Sabatier Volcanoes for CO2 Hydrogenation to C1‐2 Oxygenates Using Data‐Efficient Machine Learning

open access: yesAdvanced Science, EarlyView.
A new data‐efficient framework combining DFT calculations, a neural network model, and automated graph analysis of catalytic reaction networks is proposed and applied to CO2 hydrogenation on transition metal nanoparticles. The analysis shows how efficient C2 oxygenate production requires a balance between CHx formation, C–C coupling, protonation, and ...
Mikhail V. Polynski, Sergey M. Kozlov
wiley   +1 more source

Multiferroic‐Centric Materials and Systems Engineering for Battery Applications: An Insight Into Mechanisms, Strategies, and Characterizations

open access: yesAdvanced Science, EarlyView.
Multiferroic order parameters – polarization, magnetization, and ferroelastic strain – are positioned as dynamic design variables for batteries. Their mechanistic roles, practical tuning through fabrication and external fields, and ferroic‐resolved characterization routes are unified into a closed‐loop framework, revealing how coupled ferroic responses
Jiaqi Su   +13 more
wiley   +1 more source

Hierarchical Line Graph Neural Network: A Study on Alternative Representations of Graph-Structured Data [PDF]

open access: yes
openThis thesis addresses the challenge of feature-smoothing common in deep graph neural networks (GNNs), a topic of considerable interest over the past decade.
MOHAMMADI, SOLMAZ
core  

Home - About - Disclaimer - Privacy