Efficient Graph Research Articles

Efficient graph representation in graph neural networks for stress predictions in stiffened panels

Machine learning (ML) and deep learning (DL) techniques have gained significant attention as reduced order models (ROMs) to computationally expensive structural analysis methods, such as finite element analysis (FEA). Graph neural network (GNN) is a particular type of neural network which processes data that can be represented as graphs. This allows for efficient representation of complex geometries that can change during the conceptual design of a structure or a product. In this study, we propose a novel graph embedding for the efficient representation of 3D stiffened panels by considering separate plate domains as vertices. This approach is considered using Graph Sampling and Aggregation (GraphSAGE) to predict stress distributions in stiffened panels with varying geometries. A comparison between a finite element-vertex graph representation is conducted to demonstrate the effectiveness of the proposed approach. A comprehensive parametric study is performed to examine the effect of structural variables on stress predictions. A wide range of geometries is considered, material nonlinearity, a few boundary conditions, together with uniform and patch loading at various positions. The study involves straight and curved panels with uni- and bi-directional stiffeners. The proposed unit-vertex representation of the panel requires only about 2% of GPU memory and about 4% of training time in comparison to a finite element-vertex embedding. The GraphSAGE model with the proposed unit-vertex representation accurately captures stress distribution across all panels, achieving an average prediction accuracy of 92.3% for the maximum von Mises stress. Our results demonstrate the immense potential of graph neural networks with the proposed graph embedding as a robust reduced-order model for 3D structures.

A Survey of Computationally Efficient Graph Neural Networks for Reconfigurable Systems

Graph neural networks (GNNs) are powerful models capable of managing intricate connections in non-Euclidean data, such as social networks, physical systems, chemical structures, and communication networks. Despite their effectiveness, the large-scale and complex nature of graph data demand substantial computational resources and high performance during both training and inference stages, presenting significant challenges, particularly in the context of embedded systems. Recent studies on GNNs have investigated both software and hardware solutions to enhance computational efficiency. Earlier studies on deep neural networks (DNNs) have indicated that methods like reconfigurable hardware and quantization are beneficial in addressing these issues. Unlike DNN research, studies on efficient computational methods for GNNs are less developed and require more exploration. This survey reviews the latest developments in quantization and FPGA-based acceleration for GNNs, showcasing the capabilities of reconfigurable systems (often FPGAs) to offer customized solutions in environments marked by significant sparsity and the necessity for dynamic load management. It also emphasizes the role of quantization in reducing both computational and memory demands through the use of fixed-point arithmetic and streamlined vector formats. This paper concentrates on low-power, resource-limited devices over general hardware accelerators and reviews research applicable to embedded systems. Additionally, it provides a detailed discussion of potential research gaps, foundational knowledge, obstacles, and prospective future directions.

Efficient modeling of liquid splashing via graph neural networks with adaptive filter and aggregator fusion

PurposeThe purpose of this study is to advance the computational modeling of liquid splashing dynamics, while balancing simulation accuracy and computational efficiency, a duality often compromised in high-fidelity fluid dynamics simulations.Design/methodology/approachThis study introduces the fluid efficient graph neural network simulator (FEGNS), an innovative framework that integrates an adaptive filtering layer and aggregator fusion strategy within a graph neural network architecture. FEGNS is designed to directly learn from extensive liquid splash data sets, capturing the intricate dynamics and intrinsically complex interactions.FindingsFEGNS achieves a remarkable 30.3% improvement in simulation accuracy over traditional methods, coupled with a 51.6% enhancement in computational speed. It exhibits robust generalization capabilities across diverse materials, enabling realistic simulations of droplet effects. Comparative analyses and empirical validations demonstrate FEGNS’s superior performance against existing benchmark models.Originality/valueThe originality of FEGNS lies in its adaptive filtering layer, which independently adjusts filtering weights per node, and a novel aggregator fusion strategy that enriches the network’s expressive power by combining multiple aggregation functions. To facilitate further research and practical deployment, the FEGNS model has been made accessible on GitHub (https://github.com/nanjinyao/FEGNS/tree/main).

An integrated graph data privacy attack framework based on graph neural networks in IoT

SummaryKnowledge graphs contain a large amount of entity and relational data, and graph neural networks, as a class of efficient graph representation techniques based on deep learning, excel in knowledge graph modeling. However, previous neural network architectures for the most part only learn node representations and do not fully consider the heterogeneity of data. In this article, we innovatively propose a privacy attack framework based on IoT, PAFI, which is able to classify entities and relations, learn embedding representations in multi‐relational graphs, and can be applied to some existing neural network algorithms. Based on this, a fine‐grained privacy attack model, FPM, is proposed, which can perform attack operations on multiple targets, achieve selectivity of target tasks, and greatly improve the generalization ability of the attack model. In this article, the effectiveness of PAFI and FPM is demonstrated by real network datasets, and compared with previous attack methods, both of which achieve good results.

PECC: parallel expansion based on clustering coefficient for efficient graph partitioning

PECC: parallel expansion based on clustering coefficient for efficient graph partitioning

A Parallel Coloring Newton-Krylov Method for Multiphysics Coupling System in Nuclear Reactors

The Newton-Krylov method with the explicit Jacobian matrix is an efficient numerical method for solving the nuclear reactor nonlinear multiphysics coupling system. Compared with the Jacobian-free Newton-Krylov (JFNK) method, it has a better preconditioner matrix (the Jacobian matrix itself) and can achieve a more stable and faster convergence. How to compute the Jacobian matrix efficiently is a key issue for this method. The graph coloring algorithm is an essential technique and has been used to reduce the Jacobian computational burden by exploiting its sparsity. The fewer the coloring numbers in the Jacobian, the less the Jacobian computational cost will be. Besides, when computing the Jacobian in a distributed memory parallel environment, the parallel graph coloring algorithms are required because the Jacobian is distributed among processors. Currently, a popular parallel graph coloring algorithm has been used to color the Jacobian. However, this parallel graph coloring algorithm shows poor scalability in parallel. The coloring numbers will increase with the processors, resulting in poor Jacobian computational efficiency. In this paper, a more efficient parallel graph coloring method is proposed that aims to reduce the coloring numbers and improve Jacobian computation efficiency in parallel. The main feature of the new method is that the coloring numbers decrease with the increasing number of processors. A neutronics/thermal-hydraulic coupling problem arising from the simplified high-temperature gas coolant model is utilized to assess the performance of the newly proposed method. The results show that (1) the parallel coloring number is reduced significantly, (2) the Jacobian computed by the new method is completely correct and excellent parallel scalability is achieved, and (3) the parallel coloring Newton-Krylov method with explicit Jacobian is more efficient and more stable than the parallel JFNK due to a better preconditioner.

STWave+: A Multi-Scale Efficient Spectral Graph Attention Network With Long-Term Trends for Disentangled Traffic Flow Forecasting

STWave+: A Multi-Scale Efficient Spectral Graph Attention Network With Long-Term Trends for Disentangled Traffic Flow Forecasting

Poligras: Policy-Based Graph Summarization

Large graphs are ubiquitous. Their sizes, rates of growth, and complexity, however, have significantly outpaced human capabilities to ingest and make sense of them. As a cost-effective graph simplification technique, graph summarization is aimed to reduce large graphs into concise, structure-preserving, and quality-enhanced summaries readily available for efficient graph storage, processing, and visualization. Concretely, given a graph G , graph summarization condenses G into a succinct representation comprising (1) a supergraph with supernodes representing disjoint sets of vertices of G and superedges depicting aggregate-level connections between supernodes, and (2) a set of correction edges that help reconstruct G losslessly from the supergraph. Existing graph summarization solutions offer non-optimal graph summaries and are time-demanding in real-world large graphs. In this paper, we propose a learning-enhanced graph summarization approach, Poligras ( Poli cy-based gra ph summarization), to model the most critical computational component in graph summarization: supernode selection and merging. Specifically, we design a probabilistic policy learned and optimized by neural networks for efficient optimal supernode pair selection. As the first learning-enhanced, scalable graph summarization method, Poligras achieves significantly improved performance over state-of-the-art graph summarization solutions in real-world large graphs.

SIMPLE: Efficient Temporal Graph Neural Network Training at Scale with Dynamic Data Placement

Dynamic graphs are essential in real-world scenarios like social media and e-commerce for tasks such as predicting links and classifying nodes. Temporal Graph Neural Networks (T-GNNs) stand out as a prime solution for managing dynamic graphs, employing temporal message passing to compute node embeddings at specific timestamps. Nonetheless, the high CPU-GPU data loading overhead has become the bottleneck for efficient training of T-GNNs over large-scale dynamic graphs. In this work, we present SIMPLE, a versatile system designed to address the major efficiency bottleneck in training existing T-GNNs on a large scale. It incorporates a dynamic data placement mechanism, which maintains a small buffer space in available GPU memory and dynamically manages its content during T-GNN training. SIMPLE is also empowered by systematic optimizations towards data processing flow. We compare SIMPLE to the state-of-the-art generic T-GNN training system TGL on four large-scale dynamic graphs with different underlying T-GNN models. Extensive experimental results show that SIMPLE effectively cuts down 80.5% ~ 96.8% data loading cost, and accelerates T-GNN training by 1.8× ~ 3.8× (2.6× on average) compared to TGL.

An efficient graph embedding clustering approach for heterogeneous network

An efficient graph embedding clustering approach for heterogeneous network

Developing a novel causal inference algorithm for personalized biomedical causal graph learning using meta machine learning

BackgroundModeling causality through graphs, referred to as causal graph learning, offers an appropriate description of the dynamics of causality. The majority of current machine learning models in clinical decision support systems only predict associations between variables, whereas causal graph learning models causality dynamics through graphs. However, building personalized causal graphs for each individual is challenging due to the limited amount of data available for each patient.MethodIn this study, we present a new algorithmic framework using meta-learning for learning personalized causal graphs in biomedicine. Our framework extracts common patterns from multiple patient graphs and applies this information to develop individualized graphs. In multi-task causal graph learning, the proposed optimized initial guess of shared commonality enables the rapid adoption of knowledge to new tasks for efficient causal graph learning.ResultsExperiments on one real-world biomedical causal graph learning benchmark data and four synthetic benchmarks show that our algorithm outperformed the baseline methods. Our algorithm can better understand the underlying patterns in the data, leading to more accurate predictions of the causal graph. Specifically, we reduce the structural hamming distance by 50-75%, indicating an improvement in graph prediction accuracy. Additionally, the false discovery rate is decreased by 20-30%, demonstrating that our algorithm made fewer incorrect predictions compared to the baseline algorithms.ConclusionTo the best of our knowledge, this is the first study to demonstrate the effectiveness of meta-learning in personalized causal graph learning and cause inference modeling for biomedicine. In addition, the proposed algorithm can also be generalized to transnational research areas where integrated analysis is necessary for various distributions of datasets, including different clinical institutions.

Allok: a machine learning approach for efficient graph execution on CPU–GPU clusters

Allok: a machine learning approach for efficient graph execution on CPU–GPU clusters

GraphTango: A Hybrid Representation Format for Efficient Streaming Graph Updates and Analysis

Streaming graph processing performs batched updates and analytics on a time-evolving graph. The underlying representation format of the graph largely determines the throughputs of these updates and analytics phases. Existing representation formats usually employ variations of hash tables or adjacency lists. However, a recent study showed that the adjacency-list-based approaches perform poorly on heavy-tailed graphs, and the hash table-based approaches suffer on short-tailed graphs. We propose GraphTango, a hybrid representation format that provides excellent update and analytics throughput regardless of the graph’s degree distribution. GraphTango dynamically switches among three different formats based on a vertex’s degree: (i) Low-degree vertices store the edges directly with the neighborhood metadata, confining accesses to a single cache line, (2) Medium-degree vertices use adjacency lists, and (3) High-degree vertices use hash tables as well as adjacency lists. In this case, the adjacency list provides fast traversal during the analytics phase, while the hash table provides constant-time lookups during the update phase. We further optimized the performance by designing an open-addressing-based hash table that fully utilizes every fetched cache line. In addition, we developed a thread-local lock-free memory pool that allows fast growing/shrinking of the adjacency lists and hash tables in a multi-threaded environment. We evaluated GraphTango with the help of the SAGA-Bench framework and compared it with four other representation formats: Stinger, Degree-aware Robin Hood Hashing, and two adjacency list-based formats with different workload balancing scheme. On average, GraphTango provides 4.5x higher insertion throughput, 3.2x higher deletion throughput, and 1.1x higher analytics throughput over the next best format. Furthermore, we integrated GraphTango with the state-of-the-art graph processing frameworks DZiG and RisGraph. Compared to the vanilla DZiG and vanilla RisGraph, [GraphTango + DZiG] and [GraphTango + RisGraph] reduces the average batch processing time by 2.3x and 1.5x, respectively.

Improving Graph Compression for Efficient Resource-Constrained Graph Analytics

Recent studies have shown the promise of directly processing compressed graphs. However, its benefits have been limited by high peak-memory usage and unbearably long compression time. In this paper, we introduce Laconic, a novel rule-based graph processing solution that overcomes the challenges of restricted memory and impractical compression time faced by existing approaches. Laconic, for the first time, ensures minimal memory overhead during compression and significantly reduces graph sizes, thus reducing peak memory demand during computations. By employing an efficient parallel compression algorithm, Laconic achieves a remarkable reduction in compression time. In our experiments, we compare Laconic with state-of-the-art solutions. The results demonstrate that Laconic outperforms other methods, reducing peak memory consumption by an average of 70% during compression and 66% during computation. Additionally, Laconic reduces rule compression time by an average of 93% compared to traditional rule-based compression, achieving a 2.47× higher compression ratio, and providing a 2.12× performance speedup.

Efficient Unsupervised Community Search with Pre-Trained Graph Transformer

Community search has aroused widespread interest in the past decades. Among existing solutions, the learning-based models exhibit outstanding performance in terms of accuracy by leveraging labels to 1) train the model for community score learning, and 2) select the optimal threshold for community identification. However, labeled data are not always available in real-world scenarios. To address this notable limitation of learning-based models, we propose a pre-trained graph Trans former based community search framework that uses Zero label (i.e., unsupervised), termed TransZero. TransZero has two key phases, i.e., the offline pre-training phase and the online search phase. Specifically, in the offline pre-training phase, we design an efficient and effective community search graph transformer ( CSGphormer ) to learn node representation. To pre-train CSGphormer without the usage of labels, we introduce two self-supervised losses, i.e., personalization loss and link loss, motivated by the inherent uniqueness of node and graph topology, respectively. In the online search phase, with the representation learned by the pre-trained CSGphormer , we compute the community score without using labels by measuring the similarity of representations between the query nodes and the nodes in the graph. To free the framework from the usage of a label-based threshold, we define a new function named expected score gain to guide the community identification process. Furthermore, we propose two efficient and effective algorithms for the community identification process that run without the usage of labels. Extensive experiments over 10 public datasets illustrate the superior performance of TransZero regarding both accuracy and efficiency.

Efficient non-isomorphic graph enumeration algorithms for several intersection graph classes

Intersection graphs are well-studied in the area of graph algorithms. Some intersection graph classes are known to have algorithms enumerating all unlabeled graphs by reverse search. Since these algorithms output graphs one by one and the numbers of graphs in these classes are vast, they work only for a small number of vertices. Binary decision diagrams (BDDs) are compact data structures for various types of data and useful for solving optimization and enumeration problems. This study proposes enumeration algorithms for five intersection graph classes, which admit O(n)-bit string representations for their member graphs. Our algorithm for each class enumerates all unlabeled graphs with n vertices over BDDs representing the binary strings in time polynomial in n. Moreover, our algorithms are extended so that it enumerates those with constraints on the maximum (bi)clique size and/or the number of edges.

Efficient Edge Computing: A Survey of High-Throughput Concurrent Processing Strategies for Graph Data

This paper reviews the strategies for high-throughput concurrent processing of graph data in edge computing environments. As information technology rapidly advances, particularly in areas such as the Internet of Things (IoT), smart cities, and autonomous driving, the need for real-time and efficient data processing continues to grow. Edge computing is a distributed computing paradigm that can process data at or near its origin, thereby reducing network latency, improving application performance, and reducing the load on central data centers. The discussion includes the application of edge computing in graph data processing, highlighting parallel computing models such as the Bulk Synchronous Parallel (BSP) model and other parallel optimization techniques like data partitioning and task scheduling. The paper also addresses specific challenges of parallel processing in edge computing, such as resource constraints, data communication delays, and strategies for security and privacy protection. Despite the significant potential edge computing has demonstrated in processing graph data, numerous challenges remain. Future research directions involve the development of new resource optimization algorithms, low-latency communication protocols, and technologies to enhance data security, aiming to achieve more efficient and secure graph data processing. This paper provides clear directions and a foundation for the efficient implementation of graph data processing in edge computing environments, positioning edge computing to play an increasingly significant role in real-time data analysis and intelligent applications.

Hierarchical Co‐generation of Parcels and Streets in Urban Modeling

AbstractWe present a computational framework for modeling land parcels and streets. In the real world, parcels and streets are highly coupled with each other since a street network connects all the parcels in a certain area. However, existing works model parcels and streets separately to simplify the problem, resulting in urban layouts with irregular parcels and/or suboptimal streets. In this paper, we propose a hierarchical approach to co‐generate parcels and streets from a user‐specified polygonal land shape, guided by a set of fundamental urban design requirements. At each hierarchical level, new parcels are generated based on binary splitting of existing parcels, and new streets are subsequently generated by leveraging efficient graph search tools to ensure that each new parcel has a street access. At the end, we optimize the geometry of the generated parcels and streets to further improve their geometric quality. Our computational framework outputs an urban layout with a desired number of regular parcels that are reachable via a connected street network, for which users are allowed to control the modeling process both locally and globally. Quantitative comparisons with state‐of‐the‐art approaches show that our framework is able to generate parcels and streets that are superior in some aspects.

GraphSER: Distance-Aware Stream-Based Edge Repartition for Many-Core Systems

With the explosive growth of graph data, distributed graph processing becomes popular and many graph hardware accelerators use distributed frameworks. Graph partitioning is foundation in distributed graph processing. However, dynamic changes in graph make existing partitioning shifted from its optimized points and cause system performance degraded. Therefore, more efficient dynamic graph partition methods are needed. In this work, we propose GraphSER, a dynamic graph partition method for many-core systems. In order to improve the cross-node spatial locality and reduce the overhead of repartition, we propose a stream-based edge repartition, in which each computing node sequentially traverses its local edge list in parallel, then migrating edges based on distance and replica degree. GraphSER does not need costly searching and prioritizes nodes so it can avoid poor cross-node spatial locality. Our evaluation shows that compared to state-of-the-art edge repartition software methods, GraphSER has an average speedup 1.52x, with the maximum up to 2x. Compared to the previous many-core hardware repartition method, GraphSER performance has an average of 40% improvement, with the maximum to 117%.

StructGNN: An efficient graph neural network framework for static structural analysis

In the field of structural analysis prediction via supervised learning, neural networks are widely employed. Recent advances in graph neural networks (GNNs) have expanded their capabilities, enabling the prediction of structures with diverse geometries by utilizing graph representations and GNNs' message-passing mechanism. However, conventional message-passing in GNNs doesn't align with structural properties, resulting in inefficient computation and limited generalization to extrapolated datasets. To address this, a novel structural graph representation, incorporating pseudo nodes as rigid diaphragms in each story, alongside an efficient GNN framework called StructGNN is proposed. StructGNN employs an adaptive message-passing mechanism tailored to the structure's story count, enabling seamless transmission of input loading features across the structural graph. Extensive experiments validate the effectiveness of this approach, achieving over 99% accuracy in predicting displacements, bending moments, and shear forces. StructGNN also exhibits strong generalization over non-GNN models, with an average accuracy of 96% on taller, unseen structures. These results highlight StructGNN's potential as a reliable, computationally efficient tool for static structural response prediction, offering promise for addressing challenges associated with dynamic seismic loads in structural analysis.