Interpretable Graph Neural Networks for Predicting the Functional State of Protein Kinases
Explore the source record for details and available documents.
Ashwin Ravichandran↗
SEARCH · Engineering Papers
Results for “graph states”
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.
Addressing GPU memory limitations for Graph Neural Networks in High-Energy Physics applications
Introduction Reconstructing low-level particle tracks in neutrino physics can address some of the most fundamental questions about the universe. However, processing petabytes of raw data using deep learning techniques poses a challenging problem in the field of High Energy Physics (HEP). In the Exa.TrkX Project, an illustrative HEP application, preprocessed simulation data is fed into a state-of-art Graph Neural Network (GNN) model, accelerated by GPUs. However, limited GPU memory often leads to Out-of-Memory (OOM) exceptions during training, due to the large size of models and datasets. This problem is exacerbated when deploying models on High-Performance Computing (HPC) systems designed for large-scale applications. Methods We observe a high workload imbalance issue during GNN model training caused by the irregular sizes of input graph samples in HEP datasets, contributing to OOM exceptions. We aim to scale GNNs on HPC systems, by prioritizing workload balance in graph inputs while maintaining model accuracy. Our paper introduces diverse balancing strategies aimed at decreasing the maximum GPU memory footprint and avoiding the OOM exception, across various datasets. Results Our experiments showcase memory reduction of up to 32.14% compared to the baseline. We also demonstrate the proposed strategies can avoid OOM in application. Additionally, we create a distributed multi-GPU implementation using these samplers to demonstrate the scalability of these techniques on the HEP dataset. Discussion By assessing the performance of these strategies as data loading samplers across multiple datasets, we can gauge their effectiveness in both single-GPU and distributed environments. Our experiments, conducted on datasets of varying sizes and across multiple GPUs, broaden the applicability of our work to various GNN applications that handle input datasets with irregular graph sizes.
Lee, Claire Songhyun↗
The future evolution of energy-water-agriculture interconnectivity across the US
Abstract Energy, water, and agricultural resources across the globe are highly interconnected. This interconnectivity poses science challenges, such as understanding and modeling interconnections, as well as practical challenges, such as efficiently managing interdependent resource systems. Using the US as an example, this study seeks to define and explore how interconnectivity evolves over space and time under a range of influences. Concepts from graph theory and input–output analysis are used to visualize and quantify key intersectoral linkages using two new indices: the ‘Interconnectivity Magnitude Index’ and the ‘Interconnectivity Spread Index’. Using the Global Change Analysis Model (GCAM-USA), we explore the future evolution of these indices under four scenarios that explore a range of forces, including socioeconomic and technological change. Analysis is conducted at both national and state level spatial scales from 2015 to 2100. Results from a Reference scenario show that resource interconnectivity in the US is primarily driven by water use amongst different sectors, while changes in interconnectivity are driven by a decoupling of the water and electricity systems, as power plants become more water-efficient over time. High population and GDP growth results in relatively more decoupling of sectors, as a larger share of water and energy is used outside of interconnected sector feedback loops. Lower socioeconomic growth results in the opposite trend. Transitioning to a low-carbon economy increases interconnectivity because of the expansion of purpose-grown biomass, which strengthens the connections between water and energy. The results highlight that while some regions may experience similar sectoral stress projections, the composition of the intersectoral connectivity leading to that sectoral stress may call for distinctly different multi-sector co-management strategies. The methodology we introduce here can be applied in diverse geographical and sectoral contexts to enable better understanding of where, when, and how coupling or decoupling between sectors could evolve and be better managed.
Khan, Zarrar (ORCID:0000000281478553)↗
The Monarch Initiative in 2024: an analytic platform integrating phenotypes, genes and diseases across species
Abstract Bridging the gap between genetic variations, environmental determinants, and phenotypic outcomes is critical for supporting clinical diagnosis and understanding mechanisms of diseases. It requires integrating open data at a global scale. The Monarch Initiative advances these goals by developing open ontologies, semantic data models, and knowledge graphs for translational research. The Monarch App is an integrated platform combining data about genes, phenotypes, and diseases across species. Monarch's APIs enable access to carefully curated datasets and advanced analysis tools that support the understanding and diagnosis of disease for diverse applications such as variant prioritization, deep phenotyping, and patient profile-matching. We have migrated our system into a scalable, cloud-based infrastructure; simplified Monarch's data ingestion and knowledge graph integration systems; enhanced data mapping and integration standards; and developed a new user interface with novel search and graph navigation features. Furthermore, we advanced Monarch's analytic tools by developing a customized plugin for OpenAI’s ChatGPT to increase the reliability of its responses about phenotypic data, allowing us to interrogate the knowledge in the Monarch graph using state-of-the-art Large Language Models. The resources of the Monarch Initiative can be found at monarchinitiative.org and its corresponding code repository at github.com/monarch-initiative/monarch-app.
60 APPLIED LIFE SCIENCES↗
Grid Topology Discovery Algorithm Evaluation of Suitability for Utility Deployment (CRADA 606 Final Report)
This work presents the results of a field-informed demonstration aimed at evaluating the practical suitability of a topology discovery algorithm for utility environments. We demonstrated an algorithm that uses a graph-theory-informed state estimation approach for model selection. In collaboration with Survalent and Peninsula Light Co., the algorithm was applied to real feeder models and field measurements from supervisory control and data acquisition (SCADA) and advanced metering infrastructure (AMI) systems to identify the operational topology of a power distribution system. The demonstration assessed the algorithm’s performance under realistic data conditions, including sparse and noisy measurements, and examined its ability to identify the most likely network configurations. The results confirmed that the approach can effectively narrow down feasible topologies, providing operators with improved situational awareness of network status. Key lessons learned emphasize the need for systematic data validation and strategic sensor placement to enhance observability. These insights inform future deployment strategies and guide refinements for broader adoption in utility operations.
24 POWER TRANSMISSION AND DISTRIBUTION↗
Max-independent set and the quantum alternating operator ansatz
he maximum-independent set (MIS) problem of graph theory using the quantum alternating operator ansatz is studied. We perform simulations on the Rigetti Forest simulator for the square ring, K 2,3 , and K3,3 graphs and analyze the dependence of the algorithm on the depth of the circuit and initial states. The probability distribution of observation of the feasible states representing maximum-independent sets is observed to be asymmetric for the MIS problem, which is unlike the Max-Cut problem where the probability distribution of feasible states is symmetric. For asymmetric graphs, it is shown that the algorithm clearly favors the independent set with the larger number of elements even for finite circuit depth. Finally, we also compare the approximation ratios for the algorithm when we choose different initial states for the square ring graph and show that it is dependent on the choice of the initial state.
71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
Performability analysis using semi-Markov reward processes
Beaudry (1978) proposed a simple method of computing the distribution of performability in a Markov reward process. Two extensions of Beaudry's approach are presented. The method is generalized to a semi-Markov reward process by removing the restriction requiring the association of zero reward to absorbing states only. The algorithm proceeds by replacing zero-reward nonabsorbing states by a probabilistic switch; it is therefore related to the elimination of vanishing states from the reachability graph of a generalized stochastic Petri net and to the elimination of fast transient states in a decomposition approach to stiff Markov chains. The use of the approach is illustrated with three applications.
Ciardo, Gianfranco↗
A VLSI decomposition of the deBruijn graph
The nth order deBruijn graph Bn is the state diagram for an n-stage binary shift register. It is a directed graph with 2 to the n vertices, each labeled with an n-bit binary string, and 2 to the n+1 edges, each labeled with an (n+1)-bit binary string. It is shown that Bn can be built by appropriately connecting together with extra edges many isomorphic copies of a fixed graph, which is called a building block for Bn. The efficiency of such a building block is refined as the fraction of the edges of Bn which are present in the copies of the building block. It is then shown that for any alpha less than 1, there exists a graph which is a building block for Bn of efficiency greater than alpha for all sufficiently large n. The results are illustrated by showing how a special hierarchical family of building blocks has been used to construct a very large Viterbi decoder which will be used on the Galileo mission.
Collins, Oliver↗
Becoming Reactive by Concretization
One way to build a reactive system is to construct an action table indexed by the current situation or stimulus. The action table describes what course of action to pursue for each situation or stimulus. This paper describes an incremental approach to constructing the action table through achieving goals with a hierarchical search system. These hierarchies are generated with transformations called concretizations, which add constraints to a problem and which can reduce the search space. The basic idea is that an action for a state is looked up in the action table and executed whenever the action table has an entry for that state; otherwise, a path is found to the nearest (cost-wise in a graph with costweighted arcs) state that has a mappring from a state in the next highest hierarchy. For each state along the solution path, the successor state in the path is cached in the action table entry for that state. Without caching, the hierarchical search system can logarithmically reduce search. When the table is complete the system no longer searches: it simply reacts by proceeding to the state listed in the table for each state. Since the cached information is specific only to the nearest state in the next highest hierarchy and not the goal, inter-goal transfer of reactivity is possible. To illustrate our approach, we show how an implemented hierarchical search system can completely reactive.
Prieditis, Armand↗
A Graph Dynamical neural network approach for decoding dynamical states in ferroelectrics.
Ferroelectric materials such as BaTiO 3 show tremendous potential for emerging advances in memory devices, particular neuromorphic type devices. High density of memory can be obtained by stabilising polar domain walls at the nanoscale, regions of discontinuity between the well-defined polarization order parameter, but little is known about what controls their structure and dynamics in real nanoscale materials. Indeed, chiral polar domain walls have been observed in heterogeneous ferroelectrics, such as oxygen-deficient BaTiO 3 , but very little is known about how such polar-domains walls interact with defects. Indeed, a critical understanding of how dynamics of domain-walls depend on point-defects is crucial to create engineered ferroelectric memory devices. For this work, we perform large-scale simulations of nansocale domain-wall dynamics in pristine and defective BaTiO 3 using reactive force-field developed by us earlier (Phys. Chem. Chem. Phys., 2019, 21, 18240–18249), and capture their dynamical dependence on point defects using a graph dynamical neural-network approach, which we adapted to interrogate solids with well-defined order-parameters, and implemented using Pytorch based libraries. Our machine learning (ML) approach goes beyond the traditional post-processing methods to capture both spatial and temporal heterogeneities of large-scale molecular dynamics simulations of complex defective ferroelectric oxide materials. We crucially find that isolated oxygen vacancies introduce very localized spatial regions (~1–2 unit-cell in length) that show slow dipole relaxation due to formation of defect-dipoles, and that these defect-dipoles in turn slow the intrinsic dynamics of domain walls. Further, the roughness of domain walls, also influenced by vacancies, introduce dynamic heterogeneity along the domain-wall. As such we find a novel mechanism by which quenched disorder due to defects introduce dynamic heterogeneity thereby influencing response to external fields (particularly time varying fields) in a ferroelectric. Our study also emphasizes the need for creating digital twins of dynamical quantities to achieve autonomous in operando control of nanoscale switching.
42 ENGINEERING↗
Clifford orbits from cayley graph quotients
We describe the structure of the $n$-qubit Clifford group $\mathcal{C}_n$ via Cayley graphs, whose vertices represent group elements and edges represent generators. In order to obtain the action of Clifford gates on a given quantum state, we introduce a quotient procedure. Quotienting the Cayley graph by the stabilizer subgroup of a state gives a reduced graph which depicts the state's Clifford orbit. Using this protocol for $\mathcal{C}_2$, we reproduce and generalize the reachability graphs. Since the procedure is state-independent, we extend our study to non-stabilizer states, including the W and Dicke states. Furthermore, our new construction provides a more precise understanding of state evolution under Clifford circuit action.
72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
Red-QAOA: Efficient Variational Optimization through Circuit Reduction
The Quantum Approximate Optimization Algorithm (QAOA) provides a quantum solution for combinatorial optimization problems. However, the optimal parameter searching process of QAOA is greatly affected by noise, leading to non-optimal solutions. This paper introduces a novel approach to optimize QAOA by exploiting the energy landscape concentration of similar instances via graph reduction, thus addressing the effect of noise. We formalize the notion of similar instances in QAOA and develop a Simulated Annealing-based graph reduction algorithm, called Red-QAOA, to identify the most similar subgraph for efficient parameter optimization. Red-QAOA outperforms state-of-the-art Graph Neural Network (GNN) based graph pooling techniques in performance and demonstrates effectiveness on a diverse set of real-world optimization problems encompassing 3200 graphs. Red-QAOA reduced the node counts and edge counts by 28% and 37%, respectively, while maintaining a low mean square error of 2%. These enable the identification of an optimal parameter set that is closer to the ideal true optimal solution in the presence of noise. By substantially streamlining the search for QAOA parameters, our approach sets the stage for the practical application of quantum algorithms in solving complex optimization problems.
Wang, Meng↗
CRADA Number NFE-24-10110 with Qubit Engineering Inc. (CRADA Final Report)
Over the past year, the Qubit Engineering team has pushed the frontiers of power‑grid optimization, working in close collaboration with Oak Ridge National Laboratory (ORNL) and the Tennessee Valley Authority (TVA). Their progress is reflected in three newly submitted conference papers, “Unified Relational GNN Architecture for AC Optimal Power Flow Calculations in Electric Grids,” “Graph‑Based Attention Mechanisms for Solving the AC Optimal Power Flow Problem in Electrical‑Power Networks,” and “Enhanced Power‑Grid Maintenance Planning and Quantum‑Inspired Combinatorial Prospects.” These publications showcase state‑of‑the‑art graph‑neural‑network methods for AC‑OPF and novel quantum‑inspired heuristics for maintenance scheduling. Beyond the academic results, the Qubit team has converted the research into two production‑grade tools built on TVA data: Neuro‑Grid, an AI‑driven power‑flow simulator that provides instant, interactive full‑grid load‑flow visualizations, and Quanta‑Grid, a quantum‑inspired maintenance‑scheduling engine to support logistics optimization for power utilities. Together, these advances demonstrate how Qubit’s partnership with ORNL and TVA is delivering practical, physics‑grounded analytics for next‑generation grid management.
24 POWER TRANSMISSION AND DISTRIBUTION↗
Isentropic decompression of fluids from crustal and mantle pressures
Criteria are derived according to which the flow of single-phase magmatic fluids and the rarefaction expansion of low-viscosity liquids and gases may be considered approximately isentropic. Graphs of entropy vs. density with contours of constant pressure and mass fraction are used to examine the possible thermodynamic histories of H2O and CO2 decompressing isentropically from crustal and upper mantle pressures; these graphs offer a simple visual representation of a number of thermodynamic variables involved in isentropic processes. It is shown how the graphs can be used to examine the behavior of volatiles that (1) ascend in volcanic systems originating at different depths within the earth, and (2) decompress from a shock Hugoniot state. Entropy-density graphs are presented separately for H2O and CO2.
Kieffer, S. W.↗
Bit-GraphBLAS: Bit-Level Optimizations of Matrix-Centric Graph Processing on GPU
In the graph data structure like adjacency matrix, the connectivity of two nodes can be sufficiently represented using only 1 bit, but they are generally treated as 32-bit full-precision in state-of-the-art graph frameworks to adopt common sparse format such as CSR. Meanwhile, bit-level parallelism has recently be explored to have high-performance potential and low storage requirement on GPUs with dense bit-tiles. To fill the gap, our solution is a hierarchical storage format that contains the bit-indexing base and dense bit-tile units. Inherently, the granularity of the bit-tile is an essential factor in achieving both storage compression and GPU parallelism. How to find a sweet spot that trades off between avoiding sparsity and exploiting is comprehensively researched in this work. In the experiment, we evaluate the proposed storage format and algorithms on modern generation GPUs, including Pascal and Volta, to figure out critical software co-designs in conjunction with existing hardware-specific optimization.
Chen, Jou-An↗
Assessing the Feasibility of Bordered Block Diagonal Reordering in Power System Matrices using Fully Convolutional Network
In electromagnetic transient (EMT) simulations for power systems and inverter-based resources (IBRs), the arrangement of states within the system's linear equations, represented by matrix A in Ax=b, is critical. The state ordering in matrix A can highlight distinct characteristics of the system's graph, and identifying an optimal state ordering is crucial for efficient computation. The choice of state ordering, however, is dependent on the solver used, as each solver may perform optimally with different matrix patterns. With a wide array of matrix reordering algorithms available, selecting the most suitable one becomes challenging without insights into the matrix's ideal configuration. To address this, the paper proposes a fully convolutional network (FCN) to evaluate the reordering potential of the A matrix into a bordered block diagonal (BBD) pattern, which is commonly observed in power system and IBR modeling. The FCN's assessment aims to streamline the solver's operation, which in turn could substantially reduce the computational time required to find a solution.
Xia, Qianxue↗
Automatic Code Generation for High-Performance Graph Algorithms
Graph problems are common across fields of scientific computing and social sciences. However, despite their importance, implementing graph algorithms effectively on modern computing systems is a challenging task that requires significant programming effort and generally results in customized implementations. Current computing and memory hierarchies are not architected for irregular computations resulting in challenges for graph algorithms to achieve high performance on those architectures. In this paper, we present GraphX, a novel compiler framework and DSL designed to simplify the development of efficient graph algorithms and achieve high performance on modern computing systems. GraphX consists of a DSL for efficient implementation of graph algorithms, various optimizations, such as support for sparse linear algebra and workspace transformations, optimized graph primitives, including semiring and masking, and a high-performance code generation engine. Using GraphX, users can implement graph algorithms using a semantically-rich language with graph-oriented operators. GraphX uses these semantics to automatically generate efficient code for target architectures, increasing performance and portability across architectures. The composable nature of GraphX makes it possible to extend the set of optimizations and architectures without modifying the source code. We demonstrate GraphX outperforms state-of-the-art graph libraries, such as LAGraph, up to $3.7 speedup in semiring operations, $2.19 speedup in an important sparse computational kernel, and $9.05 speedup in graph processing algorithms.
compiler, graph algorithms, semiring, masking, wor↗
Explore Spatio‐Temporal Learning of Large Sample Hydrology Using Graph Neural Networks
Abstract Streamflow forecasting over gauged and ungauged basins play a vital role in water resources planning, especially under the changing climate. Increased availability of large sample hydrology data sets, together with recent advances in deep learning techniques, has presented new opportunities to explore temporal and spatial patterns in hydrological signatures for improving streamflow forecasting. The purpose of this study is to adapt and benchmark several state‐of‐the‐art graph neural network (GNN) architectures, including ChebNet, Graph Convolutional Network (GCN), and GraphWaveNet, for end‐to‐end graph learning. We explicitly represent river basins as nodes in a graph, learn the spatiotemporal nodal dependencies, and then use the learned relations to predict streamflow simultaneously across all nodes in the graph. The efficacy of the developed GNN models is investigated using the Catchment Attributes and MEteorology for Large‐sample Studies (CAMELS) data set under two settings, fixed graph topology (transductive learning), and variable graph topology (inductive learning), with the latter applicable to prediction in ungauged basins (PUB). Results indicate that GNNs are generally robust and computationally efficient, achieving similar or better performance than a baseline model trained using the long short‐term memory (LSTM) network. Further analyses are conducted to interpret the graph learning process at the edge and node levels and to investigate the effect of different model configurations. We conclude that graph learning constitutes a viable machine learning‐based method for aggregating spatiotemporal information from a multitude of sources for streamflow forecasting
Sun, Alexander Y.↗