graph neural networks

PGNN-Based Harmonic Source Localization in Distribution Networks

Accurate localization and quantification of multiple harmonic sources from limited synchronized measurements remain challenging in distribution networks. To address measurement noise, limited phasor measurement unit (PMU) deployment, and insufficient physical consistency in purely data-driven models, this paper propose...

A model of a universal linguistic knowledge graph for Turkic languages

The article describes a new model of a universal linguistic knowledge graph for Turkic languages as a basis for creating ontolinguistic resources. In the model, world knowledge is formalized as an ontological core that integrates taxonomic and situational ontologies (by analogy with WordNet and FrameNet) and is closely...

First-principles data for solid-solution Nb–Zr, Ta–Zr, and V–Zr binary alloys with body-centered-cubic structures

We present three open-access datasets containing density functional theory (DFT) calculations for refractory solid-solution binary alloys niobium–zirconium (NbZr), tantalum–zirconium (TaZr), and vanadium–zirconium (VZr) in 128-atom body-centered-cubic (BCC) supercells. These datasets extend our previously published fir...

Enhancing Multi-Label retinal Disease diagnosis via Multi-Expert graph neural active learning

Accurate identification of retinal diseases often requires multi-label annotation from domain specialists, yet high-quality labels remain expensive and inconsistent across experts. To address this challenge, we propose a knowledge-driven multi-expert active learning framework that integrates graph-based reasoning and a...

Macro-Micro Cross-Attention Graph Neural Network for Molecular Reconstruction of Petroleum Fractions

Advancing chemical reaction prediction in data-scarce drug discovery with active and geometric deep learning.

The success of generative molecular design depends on the synthetic accessibility of the molecules it creates. While computational models can help predict chemical reactions, their current effectiveness is limited by a lack of reference data and the difficulty of accurately predicting reaction regioselectivity. Here, t...

FlexENN: A Graph Neural Network for Binding Energy Prediction of Globular and Intrinsically Disordered Proteins

Abstract Intrinsically disordered proteins (IDPs) drive a large fraction of cellular signaling, transcription, and assembly through interfaces that often lack a defined geometry, making the prediction of their binding energies challenging for methods developed primarily for folded complexes. Here, we introduce FlexENN,...

Real-time hydrogen gas explosion prediction from fuel cell vehicles by physics-informed graph neural network

Hydrogen fuel cell vehicles (HFCVs) generate electricity from hydrogen via electrochemical reactions and offer an efficient, environmentally friendly pathway to the dual‑carbon targets. Nevertheless, hydrogen leakage can rapidly mix with air to form large flammable vapor clouds. In congested urban areas, the resulting...

Data-Driven On/Off Topology Optimization of Electromagnetic Devices Based on Graph Physics-Informed Neural Networks and Physics-Guided Reinforcement Learning

Topology optimization of electromagnetic devices is computationally formidable owing to the combinatorial on/off material distribution on unstructured finite element meshes and repeated Maxwell equation solves. This paper develops GPRL-TO, a data-driven framework addressing both difficulties through three synergistic c...

Neural network for logic synthesis optimization

Intelligent Circuit Design: Exploring Artificial Intelligence for Logic Gate Synthesis and Optimization

Modern integrated circuits contain billions of logic gates, while thermal and sub-micron parasitic limits make every design decision more expensive. Classical logic synthesis relies on deterministic minimization and hand-engineered heuristics that struggle to balance Power, Performance, and Area (PPA) at the same time....

NORMAN Kow model v0.1: QMRF, model card and SusDat predictions

Regression model for the n-octanol/water partition coefficient (log Kow) of the neutral form of organic chemicals, developed for the NORMAN network: the mean of gradient-boosted trees (XGBoost and LightGBM) and a graph neural network (Chemprop D-MPNN). It was trained on 14 836 structures with measured values, 13 530 fr...