graph neural networks

NEATWork: A Spatial Network Optimizer

NASA’s planned sustained presence of humans on the Moon will require significant volumes of icy regolith transport across the lunar surface. Algorithmic planning of efficient spatial transport networks connecting multiple terminals and optimizing across a range of objectives remains an open challenge. To address this problem, we developed NEATWork, a spatial network planner. By modifying the well-known NEAT genetic algorithm—traditionally used for the development of neural networks—we present a graph optimization approach that can take into account various spatial and topological objectives. We illustrate our solution using the case of lunar transport network planning, though it can be easily deployed in other network planning scenarios where spatial cost maps can be made and the flexibility for a black box cost function optimization is of interest. We provide two open-source implementations.

pinn-serving: Derivative-Aware Serving of Physics-Informed Neural Networks

A serving harness and benchmark suite for physics-informed neural networks (PINNs). Introduces derivative-graph baking, which differentiates a tanh MLP symbolically offline and emits the closed-form derivative recursion as a forward-only program, making derivative-valued queries compatible with standard inference backends and quantisation. Includes evidence that output-space accuracy monitoring cannot detect physics degradation at serving time, and a matched comparison against a Crank-Nicolson solver.

Bridging the antiviral drug design gap: a combined machine learning and QSAR approach for drug repurposing of host kinase inhibitors

Abstract Viral outbreaks combined with rapid emergence of mutated viruses have highlighted an urging need for accelerating antiviral drug discovery pipelines. Unfortunately, current drug discovery remains stuck to conventional methods which are slow especially during pandemics. In this article, we present a literature-based synthesis of an integrative machine learning (ML) guided QSAR framework that unifies ligand-based, structure-based, and systems biology approaches towards the aim of generating a host directed antiviral repurposing strategy. Moreover, a modern ML enhanced QSAR modeling strategy is proposed to target host directed therapeutics (HDTs), particularly the host kinase enzymes. The proposed framework integrates molecular descriptor modeling, ensemble learning methods (e.g., RF, gradient boosting), graph neural networks (GNNs), and multi-omics target prioritization to outline a predictive antiviral repurposing model. This structured workflow encompasses dataset assembly, descriptor generation, model training, virtual screening, and experimental validation as sequential stages to guide, rather than as a pipeline that has itself been built or independently validated here, translational deployment. The review is illustrated through a retrospective narrative synthesis of four independently published, clinically relevant repurposed HDTs, namely Baricitinib, Lapatinib, Bemcentinib, and Sunitinib. These published case studies, drawn from the primary literature, exemplify how AI/ML-enhanced QSAR and network-based approaches have been used elsewhere to identify active antiviral kinase inhibitors; they are presented here as illustrative evidence of feasibility of such a computational pipeline. Thus, the AI guided repurposing of host kinase inhibitors offers a systematically accelerated strategy to bridge the drug design gap, with the potential for faster therapeutic deployment against viral threats pending prospective, harmonized validation.

Graph neural networks for automated conjecture generation in number theory: a novel approach to pattern discovery

pinn-serving: Derivative-Aware Serving of Physics-Informed Neural Networks

A serving harness and benchmark suite for physics-informed neural networks (PINNs). Introduces derivative-graph baking, which differentiates a tanh MLP symbolically offline and emits the closed-form derivative recursion as a forward-only program, making derivative-valued queries compatible with standard inference backends and quantisation. Includes evidence that output-space accuracy monitoring cannot detect physics degradation at serving time, and a matched comparison against a Crank-Nicolson solver.

THE EVOLUTIONARY E-SPORTS CIVILIZATION MODEL (EECM): A Grand Unified Interdisciplinary Theory of Digital-Cognitive Civilization, Cognitive Capital, Artificial Intelligence Augmentation, Neuroeconomic Transformation, Virtual Ontology, and Civilizational Evolution

This paper proposes the Evolutionary E-Sports Civilization Model (EECM), a grand interdisciplinary theoretical framework designed to explain the transformation of gaming, cognition, digital interaction, artificial intelligence, and virtual systems into a new civilizational paradigm. The theory argues that E-sports represents far more than organized competitive gaming; rather, it constitutes a symbolic and structural manifestation of the ongoing transition from industrial civilization toward a digital-cognitive civilization.The framework integrates mathematics, complexity science, neuroscience, psychology, philosophy, sociology, economics, political science, cybernetics, systems theory, information theory, artificial intelligence, and digital ontology into a unified explanatory architecture. It proposes that modern civilization increasingly transforms psychologically meaningful activities into measurable, monetizable, and algorithmically optimized systems of production and social organization.Within this framework, cognition itself becomes a form of capital. Human attention, strategic reasoning, adaptive intelligence, reflex optimization, emotional regulation, collaborative cognition, and digital interaction evolve into economically productive assets. The theory therefore introduces the concept of Cognitive Capital, a post-industrial expansion of classical economic production factors.The EECM framework further argues that artificial intelligence acts as a civilizational amplifier, accelerating the transformation of digital environments into self-organizing socio-economic ecosystems governed increasingly through algorithmic optimization. E-sports is analyzed as an emergent prototype of future virtual civilization structures, where entertainment, labor, economics, governance, identity, and AI converge into unified digital systems.Mathematically, the paper formalizes these transformations using nonlinear dynamical systems, complexity theory, graph theory, information entropy, game theory, network theory, chaos theory, and probabilistic scaling functions. Philosophically, the theory synthesizes concepts from Aristotle, Plato, Nietzsche, Heidegger, Marx, Foucault, Bourdieu, Sartre, Kant, and contemporary philosophy of technology. Psychologically and neuroscientifically, the model incorporates flow theory, predictive processing, dopamine reward systems, cognitive load theory, neural plasticity, and human-machine symbiosis.The framework also explores geopolitical implications, platform sovereignty, AI governance, digital identity formation, algorithmic social structures, metaverse civilization, and the future political economy of virtual systems. Ultimately, the theory proposes that E-sports is not merely a recreational phenomenon but an early-stage manifestation of a broader civilizational transition in which cognition, attention, and digital interaction become the dominant organizational principles of society.

Learning on Edges: A Narrative Review of Graph Neural Networks from Recursive Networks to Geometric Deep Learning

Graph neural networks---learning over relational, irregular structure by passing messages between nodes---generalized deep learning's grids to the graph: molecules, social networks, knowledge bases, and the web. This article presents a narrative review of that arc's canonical line: Sperduti and Starita's 1997 structure classification, Gori, Monfardini, and Scarselli's 2005 graph-domain learning, Scarselli and colleagues' 2009 GNN model, Bruna and colleagues' 2014 spectral networks, Defferrard and colleagues' 2016 localized filtering, Kipf and Welling's 2017 graph convolutions, Gilmer and colleagues' 2017 message passing, Hamilton, Ying, and Leskovec's 2017 GraphSAGE, Velickovic and colleagues' 2018 attention, Ying and colleagues' 2019 GNNExplainer, Wu and colleagues' 2021 comprehensive survey, and Bronstein and colleagues' 2021 geometric deep learning. The synthesis is organized around three themes: recursion, in which state propagation over nodes founded learning on graphs; convolution, in which spectral theory and message passing gave the graph a deep architecture; and geometry, in which attention, pooling, explainability, and symmetry made the network general. It is concluded that the GNN is deep learning's relational settlement---convolution's invariance learned from graph geometry rather than grid regularity---and that its message-passing abstraction is one of machine learning's cleanest unifications.

Learning on Edges: A Narrative Review of Graph Neural Networks from Recursive Networks to Geometric Deep Learning

Graph neural networks---learning over relational, irregular structure by passing messages between nodes---generalized deep learning's grids to the graph: molecules, social networks, knowledge bases, and the web. This article presents a narrative review of that arc's canonical line: Sperduti and Starita's 1997 structure classification, Gori, Monfardini, and Scarselli's 2005 graph-domain learning, Scarselli and colleagues' 2009 GNN model, Bruna and colleagues' 2014 spectral networks, Defferrard and colleagues' 2016 localized filtering, Kipf and Welling's 2017 graph convolutions, Gilmer and colleagues' 2017 message passing, Hamilton, Ying, and Leskovec's 2017 GraphSAGE, Velickovic and colleagues' 2018 attention, Ying and colleagues' 2019 GNNExplainer, Wu and colleagues' 2021 comprehensive survey, and Bronstein and colleagues' 2021 geometric deep learning. The synthesis is organized around three themes: recursion, in which state propagation over nodes founded learning on graphs; convolution, in which spectral theory and message passing gave the graph a deep architecture; and geometry, in which attention, pooling, explainability, and symmetry made the network general. It is concluded that the GNN is deep learning's relational settlement---convolution's invariance learned from graph geometry rather than grid regularity---and that its message-passing abstraction is one of machine learning's cleanest unifications.

Accelerating Materials Discovery: A Review of Machine Learning in X‐Ray Absorption Spectroscopy

X‐ray absorption spectroscopy (XAS) is a critical technique for probing the local structural and electronic properties of materials. Advanced synchrotron radiation facilities generate complex, high‐dimensional spectra, which pose significant challenges for traditional analysis methods while simultaneously offering unprecedented opportunities for machine learning (ML). This review systematically elaborates how ML models are driving the transformation of XAS data analysis. We not only cover supervised and unsupervised learning methods for spectral classification and clustering but also delve into cutting‐edge deep learning architectures. These include graph neural networks for precise “structure‐to‐spectra” mapping and diffusion models for generative tasks and structure prediction. We provide a comprehensive overview of the key challenges in data‐driven XAS, including the feature engineering of spectra and structures, strategies for solving the “spectra‐to‐structure” Inverse Problem, and Sim2Real methods for bridging the “Domain Gap” between simulated and experimental data. Furthermore, we emphasize the importance of model eXplainable artificial intelligence and uncertainty quantification for building trust in scientific research. Finally, this review looks ahead to the future of the field, driven by materials informatics and autonomous experiments. Active Learning techniques, represented by Bayesian optimization, are pioneering “self‐driving” smart XAS experiments, which will greatly accelerate the discovery and design of new materials.

pinn-serving: Derivative-Aware Serving of Physics-Informed Neural Networks

A serving harness and benchmark suite for physics-informed neural networks (PINNs). Introduces derivative-graph baking, which differentiates a tanh MLP symbolically offline and emits the closed-form derivative recursion as a forward-only program, making derivative-valued queries compatible with standard inference backends and quantisation. Includes evidence that output-space accuracy monitoring cannot detect physics degradation at serving time, and a matched comparison against a Crank-Nicolson solver.

THE EVOLUTIONARY E-SPORTS CIVILIZATION MODEL (EECM): A Grand Unified Interdisciplinary Theory of Digital-Cognitive Civilization, Cognitive Capital, Artificial Intelligence Augmentation, Neuroeconomic Transformation, Virtual Ontology, and Civilizational Evolution

This paper proposes the Evolutionary E-Sports Civilization Model (EECM), a grand interdisciplinary theoretical framework designed to explain the transformation of gaming, cognition, digital interaction, artificial intelligence, and virtual systems into a new civilizational paradigm. The theory argues that E-sports represents far more than organized competitive gaming; rather, it constitutes a symbolic and structural manifestation of the ongoing transition from industrial civilization toward a digital-cognitive civilization.The framework integrates mathematics, complexity science, neuroscience, psychology, philosophy, sociology, economics, political science, cybernetics, systems theory, information theory, artificial intelligence, and digital ontology into a unified explanatory architecture. It proposes that modern civilization increasingly transforms psychologically meaningful activities into measurable, monetizable, and algorithmically optimized systems of production and social organization.Within this framework, cognition itself becomes a form of capital. Human attention, strategic reasoning, adaptive intelligence, reflex optimization, emotional regulation, collaborative cognition, and digital interaction evolve into economically productive assets. The theory therefore introduces the concept of Cognitive Capital, a post-industrial expansion of classical economic production factors.The EECM framework further argues that artificial intelligence acts as a civilizational amplifier, accelerating the transformation of digital environments into self-organizing socio-economic ecosystems governed increasingly through algorithmic optimization. E-sports is analyzed as an emergent prototype of future virtual civilization structures, where entertainment, labor, economics, governance, identity, and AI converge into unified digital systems.Mathematically, the paper formalizes these transformations using nonlinear dynamical systems, complexity theory, graph theory, information entropy, game theory, network theory, chaos theory, and probabilistic scaling functions. Philosophically, the theory synthesizes concepts from Aristotle, Plato, Nietzsche, Heidegger, Marx, Foucault, Bourdieu, Sartre, Kant, and contemporary philosophy of technology. Psychologically and neuroscientifically, the model incorporates flow theory, predictive processing, dopamine reward systems, cognitive load theory, neural plasticity, and human-machine symbiosis.The framework also explores geopolitical implications, platform sovereignty, AI governance, digital identity formation, algorithmic social structures, metaverse civilization, and the future political economy of virtual systems. Ultimately, the theory proposes that E-sports is not merely a recreational phenomenon but an early-stage manifestation of a broader civilizational transition in which cognition, attention, and digital interaction become the dominant organizational principles of society.

pinn-serving: Derivative-Aware Serving of Physics-Informed Neural Networks

A serving harness and benchmark suite for physics-informed neural networks (PINNs). Introduces derivative-graph baking, which differentiates a tanh MLP symbolically offline and emits the closed-form derivative recursion as a forward-only program, making derivative-valued queries compatible with standard inference backends and quantisation. Includes evidence that output-space accuracy monitoring cannot detect physics degradation at serving time, and a matched comparison against a Crank-Nicolson solver.