SEARCH · Search NASA
Results for “heterogeneous graph”
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
Graph-Learning-Assisted State and Event Tracking for Solar-Penetrated Power Grids with Heterogeneous Data Sources
Unlike transmission systems, distribution systems do not typically contain sufficient metering to enable real-time state estimation. The lack of sufficient real-time measurements prohibits accurate and timely monitoring of the state of distribution systems. As a result, control and optimal operation of distribution systems, especially those containing large numbers of renewable generation units are not possible without proper data and information about the current state of the system. The main motivation of this project is to address this shortcoming by developing an approach which provides “predicted” real-time measurements so that they can be used to execute a distribution system state estimator. Thus, the objective of the project is to make the distribution systems fully observable, such that the hosting capacity for solar generation can be accurately estimated, and unnecessary solar curtailments can be avoided. In order to accomplish this goal, the project investigated the use of a grid-model-informed machine learning (ML) tool which integrates heterogeneous data streams obtained from AMI meters, SCADA as well as PMU measurements and created synchronous measurement snapshots for the state estimator (SE); and developed a hybrid robust SE which provides not only accurate state estimates but also real-time feedback for the ML model refinement.
Session Introduction: Graph Representations and Algorithms in Biomedicine
Connectivity is a fundamental property of biological systems: on the cellular level, proteins interact with each other to form protein-protein interaction networks (PPIs); on the organism level, neurons are arranged in a network; and on a community-level, species can have complex relationships with one another that drive the development and balance of an ecosystem. Graphs, representations of systems consisting of entities as vertices and their connections as edges, are a useful structure to characterize many such systems. Such models can be used to understand biological systems that naturally have a network structure, including PPIs, biological neurons, and ecosystems. In today’s information age, graph representations and algorithms (often in combination with machine learning techniques) are used to organize massive amounts of related data, much of which may be heterogeneous or unstructured, and identify patterns that represent novel biological insights. PSB’s 2023 session “Graph Representations and algorithms in Biomedicine,” encompasses modern developments in graph theory and its applications to various fields of biomedicine. This session includes a wide range of research - knowledge graphs built from text-mined health data, heterogeneous networks using multi-omic databases, and graphs refined to represent uncertainty or improve memory usage.
Optimizing High-Throughput Inference on Graph Neural Networks at Shared Computing Facilities with the NVIDIA Triton Inference Server
Abstract With machine learning applications now spanning a variety of computational tasks, multi-user shared computing facilities are devoting a rapidly increasing proportion of their resources to such algorithms. Graph neural networks (GNNs), for example, have provided astounding improvements in extracting complex signatures from data and are now widely used in a variety of applications, such as particle jet classification in high energy physics (HEP). However, GNNs also come with an enormous computational penalty that requires the use of GPUs to maintain reasonable throughput. At shared computing facilities, such as those used by physicists at Fermi National Accelerator Laboratory (Fermilab), methodical resource allocation and high throughput at the many-user scale are key to ensuring that resources are being used as efficiently as possible. These facilities, however, primarily provide CPU-only nodes, which proves detrimental to time-to-insight and computational throughput for workflows that include machine learning inference. In this work, we describe how a shared computing facility can use the NVIDIA Triton Inference Server to optimize its resource allocation and computing structure, recovering high throughput while scaling out to multiple users by massively parallelizing their machine learning inference. To demonstrate the effectiveness of this system in a realistic multi-user environment, we use the Fermilab Elastic Analysis Facility augmented with the Triton Inference Server to provide scalable and high-throughput access to a HEP-specific GNN and report on the outcome.
GraphCH: A Deep Framework for Assessing Cyber-Human Aspects in Insider Threat Detection
Insider threat is one of the most damaging cyber attacks that could cause the loss of intellectual property and enterprise data security breaches. Action sequence data such as host logs are used to investigate such threats and develop anomaly-based AI detectors. However, insider threat actions are similar to legitimate user activities, causing AI detectors to fail and suffer from high false alarm rates. Therefore, user cyber activity logs are inadequate to fully unfold insider threats. In this study, we adopt human psychological principles of risk-taking and impulsiveness along with host data to assess the influence and usefulness of human behavioral aspects in insider threat detection. Here, we hypothesize that individuals' impulsive and risk-taking behavior correlates with cyberspace activities. To validate our hypothesis, we conducted an IRB-approved study recruiting 35 participants who work in a large U.S. university and collected their cyber and psychological data for 90 days. Host and human-behavioral data analysis and mapping indicate that impulsive and risk-taking users trigger more system errors causing (un)intentional insider threats and are susceptible to attackers' social engineering and cognitive hacking. Utilizing cyber-human aspects, we introduce a Cyber-Human Graph Neural Network (GNN) based framework GraphCH to identify abnormal user behaviors and detect insider threats.
Templates for Risk Informed Assurance with Curvature Embeddings (TRACE)
We investigate recovery of geometric structure from networks embedded in manifolds with spatially varying curvature, extending the constant-curvature framework of Lubold et al. (2023). Our work supports cascade risk assessment in critical infrastructure through the Templates for Risk-informed Assurance with Curvature Embeddings (TRACE) framework. Simulations on a bi-modal Gaussian surface show that constant-curvature methods yield weighted averages shaped by clique patterns, while hierarchical clustering identifies distinct regimes. Localized estimation, however, reveals boundary contamination in transitional regions. To address heterogeneity, we develop distance metrics for graphs with edge and node features, proving their metric validity, and validate them via deterministic graph generation from canonical tilings. We further propose a diffusion-based anomaly detection approach that treats networks as glued manifolds, using curvature discontinuities to detect structural anomalies. Employing the carré-du-champ operator and scalar curvature, we achieve robust anomaly discrimination, demonstrated on the Singapore Water Treatment (SWaT) dataset with joint network-traffic and sensor features. Integration with TRACE reveals how curvature shapes cascade dynamics: positive curvature impedes, while negative curvature accelerates propagation. This geometric perspective provides interpretable risk metrics and visualization tools for critical infrastructure managers. While full validation remains ongoing, our contributions establish a rigorous foundation for geometric analysis of network resilience and cascade vulnerability.
An Adaptive Flow Solver for Air-Borne Vehicles Undergoing Time-Dependent Motions/Deformations
This report describes a concurrent Euler flow solver for flows around complex 3-D bodies. The solver is based on a cell-centered finite volume methodology on 3-D unstructured tetrahedral grids. In this algorithm, spatial discretization for the inviscid convective term is accomplished using an upwind scheme. A localized reconstruction is done for flow variables which is second order accurate. Evolution in time is accomplished using an explicit three-stage Runge-Kutta method which has second order temporal accuracy. This is adapted for concurrent execution using another proven methodology based on concurrent graph abstraction. This solver operates on heterogeneous network architectures. These architectures may include a broad variety of UNIX workstations and PCs running Windows NT, symmetric multiprocessors and distributed-memory multi-computers. The unstructured grid is generated using commercial grid generation tools. The grid is automatically partitioned using a concurrent algorithm based on heat diffusion. This results in memory requirements that are inversely proportional to the number of processors. The solver uses automatic granularity control and resource management techniques both to balance load and communication requirements, and deal with differing memory constraints. These ideas are again based on heat diffusion. Results are subsequently combined for visualization and analysis using commercial CFD tools. Flow simulation results are demonstrated for a constant section wing at subsonic, transonic, and a supersonic case. These results are compared with experimental data and numerical results of other researchers. Performance results are under way for a variety of network topologies.
A distributed program composition system
A graphical technique for creating distributed computer programs is investigated and a prototype implementation is described which serves as a testbed for the concepts. The type of programs under examination is restricted to those comprising relatively heavyweight parts that intercommunicate by passing messages of typed objects. Such programs are often presented visually as a directed graph with computer program parts as the nodes and communication channels as the edges. This class of programs, called parts-based programs, is not well supported by existing computer systems; much manual work is required to describe the program to the system, establish the communication paths, accommodate the heterogeneity of data types, and to locate the parts of the program on the various systems involved. The work described solves most of these problems by providing an interface for describing parts-based programs in this class in a way that closely models the way programmers think about them: using sketches of diagraphs. Program parts, the computational modes of the larger program system are categorized in libraries and are accessed with browsers. The process of programming has the programmer draw the program graph interactively. Heterogeneity is automatically accommodated by the insertion of type translators where necessary between the parts. Many decisions are necessary in the creation of a comprehensive tool for interactive creation of programs in this class. Possibilities are explored and the issues behind such decisions are presented. An approach to program composition is described, not a carefully implemented programming environment. However, a prototype implementation is described that can demonstrate the ideas presented.
Biolink Model: A universal schema for knowledge graphs in clinical, biomedical, and translational science
Abstract Within clinical, biomedical, and translational science, an increasing number of projects are adopting graphs for knowledge representation. Graph‐based data models elucidate the interconnectedness among core biomedical concepts, enable data structures to be easily updated, and support intuitive queries, visualizations, and inference algorithms. However, knowledge discovery across these “knowledge graphs” (KGs) has remained difficult. Data set heterogeneity and complexity; the proliferation of ad hoc data formats; poor compliance with guidelines on findability, accessibility, interoperability, and reusability; and, in particular, the lack of a universally accepted, open‐access model for standardization across biomedical KGs has left the task of reconciling data sources to downstream consumers. Biolink Model is an open‐source data model that can be used to formalize the relationships between data structures in translational science. It incorporates object‐oriented classification and graph‐oriented features. The core of the model is a set of hierarchical, interconnected classes (or categories) and relationships between them (or predicates) representing biomedical entities such as gene, disease, chemical, anatomic structure, and phenotype. The model provides class and edge attributes and associations that guide how entities should relate to one another. Here, we highlight the need for a standardized data model for KGs, describe Biolink Model, and compare it with other models. We demonstrate the utility of Biolink Model in various initiatives, including the Biomedical Data Translator Consortium and the Monarch Initiative, and show how it has supported easier integration and interoperability of biomedical KGs, bringing together knowledge from multiple sources and helping to realize the goals of translational science.
Simulator for heterogeneous dataflow architectures
A new simulator is developed to simulate the execution of an algorithm graph in accordance with the Algorithm to Architecture Mapping Model (ATAMM) rules. ATAMM is a Petri Net model which describes the periodic execution of large-grained, data-independent dataflow graphs and which provides predictable steady state time-optimized performance. This simulator extends the ATAMM simulation capability from a heterogenous set of resources, or functional units, to a more general heterogenous architecture. Simulation test cases show that the simulator accurately executes the ATAMM rules for both a heterogenous architecture and a homogenous architecture, which is the special case for only one processor type. The simulator forms one tool in an ATAMM Integrated Environment which contains other tools for graph entry, graph modification for performance optimization, and playback of simulations for analysis.
BrickQA: Bridging the Semantic Gap in Building Operations with Dynamic Graph Exploration
While standardized ontologies like the Brick schema address data heterogeneity in Building Automation Systems (BAS), accessing this semantic data remains a challenge as domain experts often lack the expertise to formulate complex SPARQL queries. To bridge this gap, we present BrickQA, a Large Language Model (LLM)-based framework that translates natural language into executable SPARQL queries through structured query decomposition, dynamic schema exploration, and inline validation. BrickQA utilizes an iterative reasoning agent to actively navigate graph topology through dynamic exploration actions without requiring exhaustive context injection or model fine-tuning. This approach effectively mitigates hallucinations, particularly in large-scale building knowledge graphs. Empirical evaluation on BuildingQA, a standardized benchmark, demonstrates that BrickQA significantly outperforms ReAct baselines, delivering a 0.291–0.355 absolute F1 improvement while achieving 3 × –12.7 × higher token cost-efficiency. Beyond these metrics, the framework maintains structural fidelity across heterogeneous buildings and remains resilient to ambiguous queries without requiring site-specific fine-tuning. Furthermore, a case study on operational analytics validates the framework’s capability to handle temporal and aggregation constraints, effectively transforming abstract semantic models into actionable facility management insights.1
IRIS-MEMFLOW: Data Flow-Enabled Portable Memory Orchestration in IRIS Runtime for Diverse Heterogeneity
Task-based programming models and execution paradigms provide a means to decompose a computation by expressing it as a graph in which each node represents a specific computation operating on memory objects and the edges define the dependencies in the execution flow. In this execution model, independent nodes in the graph can be executed concurrently in different computing devices, making it suitable for heterogeneous systems in which computing devices with different architectures coexist. However, careful memory orchestration across heterogeneous devices is needed because copies of the same memory object may reside in multiple devices during execution. Manually ensuring such an orchestration is quite challenging. Not only must an application developer guard against race conditions, but they must also optimize data movement between the host and devices because unnecessary data movement significantly impacts performance. To mitigate these challenges, we enhance the IRIS heterogeneous runtime and introduce IRIS-MEMFLOW–a data flow–enabled portable memory abstraction for seamlessly orchestrating memory in diverse heterogeneous computing environments. By using data-flow analysis, IRIS-MEMFLOW guards against race conditions while multiple heterogeneous devices access memory objects. IRIS-MEMFLOW also optimizes data movement between the host and devices without manual intervention. As a result, IRIS provides improved programming productivity, performance, and portability for multidevice heterogeneous executions in high-performance computing and cloud systems that run diverse architectures from different vendors. The efficacy of IRIS-MEMFLOW is evaluated through experiments that show its capability in terms of programming productivity, multidevice heterogeneity, portability, and low overhead versus the state of the art.
KG-Hub—building and exchanging biological knowledge graphs
Knowledge graphs (KGs) are a powerful approach for integrating heterogeneous data and making inferences in biology and many other domains, but a coherent solution for constructing, exchanging, and facilitating the downstream use of KGs is lacking. Here we present KG-Hub, a platform that enables standardized construction, exchange, and reuse of KGs. Features include a simple, modular extract–transform–load pattern for producing graphs compliant with Biolink Model (a high-level data model for standardizing biological data), easy integration of any OBO (Open Biological and Biomedical Ontologies) ontology, cached downloads of upstream data sources, versioned and automatically updated builds with stable URLs, web-browsable storage of KG artifacts on cloud infrastructure, and easy reuse of transformed subgraphs across projects. Current KG-Hub projects span use cases including COVID-19 research, drug repurposing, microbial–environmental interactions, and rare disease research. KG-Hub is equipped with tooling to easily analyze and manipulate KGs. KG-Hub is also tightly integrated with graph machine learning (ML) tools which allow automated graph ML, including node embeddings and training of models for link prediction and node classification.
The Deep-Time Digital Earth program: data-driven discovery in geosciences
Current barriers hindering data-driven discoveries in deep-time Earth (DE) include: substantial volumes of DE data are not digitized; many DE databases do not adhere to FAIR (findable, accessible, interoperable and reusable) principles; we lack a systematic knowledge graph for DE; existing DE databases are geographically heterogeneous; a significant fraction of DE data is not in open-access formats; tailored tools are needed. These challenges motivate the Deep-Time Digital Earth (DDE) program initiated by the International Union of Geological Sciences and developed in cooperation with national geological surveys, professional associations, academic institutions and scientists around the world. DDE’s mission is to build on previous research to develop a systematic DE knowledge graph, a FAIR data infrastructure that links existing databases and makes dark data visible, and tailored tools for DE data, which are universally accessible. DDE aims to harmonize DE data, share global geoscience knowledge and facilitate data-driven discovery in the understanding of Earth’s evolution.
Clarifying trust of materials property predictions using neural networks with distribution-specific uncertainty quantification
It is critical that machine learning (ML) model predictions be trustworthy for high-throughput catalyst discovery approaches. Uncertainty quantification (UQ) methods allow estimation of the trustworthiness of an ML model, but these methods have not been well explored in the field of heterogeneous catalysis. Herein, we investigate different UQ methods applied to a crystal graph convolutional neural network to predict adsorption energies of molecules on alloys from the Open Catalyst 2020 dataset, the largest existing heterogeneous catalyst dataset. We apply three UQ methods to the adsorption energy predictions, namely k-fold ensembling, Monte Carlo dropout, and evidential regression. The effectiveness of each UQ method is assessed based on accuracy, sharpness, dispersion, calibration, and tightness. Evidential regression is demonstrated to be a powerful approach for rapidly obtaining tunable, competitively trustworthy UQ estimates for heterogeneous catalysis applications when using neural networks. Recalibration of model uncertainties is shown to be essential in practical screening applications of catalysts using uncertainties.
Graph identification of proteins in tomograms ( GRIP‐Tomo )
Abstract In this study, we present a method of pattern mining based on network theory that enables the identification of protein structures or complexes from synthetic volume densities, without the knowledge of predefined templates or human biases for refinement. We hypothesized that the topological connectivity of protein structures is invariant, and they are distinctive for the purpose of protein identification from distorted data presented in volume densities. Three‐dimensional densities of a protein or a complex from simulated tomographic volumes were transformed into mathematical graphs as observables. We systematically introduced data distortion or defects such as missing fullness of data, the tumbling effect, and the missing wedge effect into the simulated volumes, and varied the distance cutoffs in pixels to capture the varying connectivity between the density cluster centroids in the presence of defects. A similarity score between the graphs from the simulated volumes and the graphs transformed from the physical protein structures in point data was calculated by comparing their network theory order parameters including node degrees, betweenness centrality, and graph densities. By capturing the essential topological features defining the heterogeneous morphologies of a network, we were able to accurately identify proteins and homo‐multimeric complexes from 10 topologically distinctive samples without realistic noise added. Our approach empowers future developments of tomogram processing by providing pattern mining with interpretability, to enable the classification of single‐domain protein native topologies as well as distinct single‐domain proteins from multimeric complexes within noisy volumes.
Microstructure Validation of Graph Theory Model-Derived Cooling Rates in the Wire Arc Additive Manufacturing of ER70S-6 Steel
Wire arc additive manufacturing (WAAM) enables high-rate fabrication of large metallic components, but spatial variations in thermal history can lead to microstructural heterogeneity that requires efficient process models to evaluate. This study evaluates whether cooling rates extracted from a graph theory model (GTM)-based thermal simulation are consistent with the microstructural evolution observed in an ER70S-6 WAAM wall. Thermal histories from the model were analyzed at selected build heights, and cooling rates were extracted from the final thermal excursion through the austenite phase field. Microstructures at corresponding locations were characterized using electron backscatter diffraction (EBSD) to quantify grain size distributions, and pearlite interlamellar spacing was used as an additional indicator of cooling behavior. The modeled cooling rates were highest near the substrate and generally decreased with build height, consistent with the observed reduction in the fine grain fraction and the progressive shift in the grain size distribution as build height increased. Pearlite spacing trends also supported the modeled cooling rate variation. These results indicate that GTM-derived thermal histories can be post-processed into metallurgically meaningful cooling rate estimates for WAAM steel builds and linked to dataset specific empirical grain size distribution relationships for process–thermal history–microstructure assessment.
Node assignment in heterogeneous computing
A number of node assignment schemes, both static and dynamic, are explored for the Algorithm to Architecture Mapping Model (ATAMM). The architecture under consideration consists of heterogeneous processors and implements dataflow models of real-time applications. Terminology is developed for heterogeneous computing. New definitions are added to the ATAMM for token and assignment classifications. It is proved that a periodic execution is possible for dataflow graphs. Assignment algorithms are developed and proved. A design procedure is described for satisfying an objective function in an heterogeneous architecture. Several examples are provided for illustration.