Original Node Research Articles

Simplifying Distributed Neural Network Training on Massive Graphs: Randomized Partitions Improve Model Aggregation

Distributed Graph Neural Network (GNN) training facilitates learning on massive graphs that surpass the storage and computational capabilities of a single machine. Traditional distributed frameworks strive for performance parity with centralized training by maximally recovering cross-instance node dependencies, relying either on inter-instance communication or periodic fallback to centralized training. However, these processes create overhead and constrain the scalability of the framework. In this work, we propose a streamlined framework for distributed GNN training that eliminates these costly operations, yielding improved scalability, convergence speed, and performance over state-of-the-art approaches. Our framework (1) comprises independent trainers that asynchronously learn local models from locally-available parts of the training graph, and (2) synchronizes these local models only through periodic (time-based) model aggregation. Contrary to prevailing belief, our theoretical analysis shows that it is not essential to maximize the recovery of cross-instance node dependencies to achieve performance parity with centralized training. Instead, our framework leverages randomized assignment of nodes or super-nodes (i.e., collections of original nodes) to partition the training graph in order to enhance data uniformity and minimize discrepancies in gradient and loss function across instances. Experiments on social and e-commerce networks with up to 1.3 billion edges show that our proposed framework achieves state-of-the-art performance and 2.31x speedup compared to the fastest baseline, despite using less training data.

Topology modification against membership inference attack in Graph Neural Networks

Graph Neural Networks (GNNs) can effectively leverage information from graph data and apply to various downstream tasks, such as recommendation system, or anomaly detection. Previous studies have shown that node-level GNNs are susceptible to membership inference attacks, potentially leaking private information about the nodes. However, current studies on defending against such attacks primarily focuses on image and text data. They may not be directly applicable to graph data. In addition, classic defense methods such as differential privacy, regularization techniques, and adversarial training. They may reduce model availability or require model retraining while protecting privacy. To deal with these problems, we propose a novel defense strategy against membership inference attacks in graph neural networks. The strategy involves augmenting the graph with additional nodes and modifying its topology to create a new privacy-preserving graph, thereby protecting the privacy of the original nodes. We conducted extensive experiments on three representative GNN models and compared them with state-of-the-art baseline methods to support our research. The experimental results demonstrate that our method significantly reduces the success rate of membership inference attacks while maintaining the basic performance of the target model.

Managing Resources for Shared Micromobility: Approximate Optimality in Large-Scale Systems

We consider the problem of managing resources in shared micromobility systems (bike sharing and scooter sharing). An important task in managing such systems is periodic repositioning/recharging/sourcing of units to avoid stockouts or excess inventory at nodes with unbalanced flows. We consider a discrete-time model; each period begins with an initial inventory at each node in the network, and then, customers (demand) materialize at the nodes. Each customer picks up a unit at the origin node and drops it off at a randomly sampled destination node with an origin-specific probability distribution. We model the above network inventory management problem as an infinite horizon discrete-time discounted Markov decision process (MDP) and prove the asymptotic optimality of a novel mean-field approximation to the original MDP as the number of stations becomes large. To compute an approximately optimal policy for the mean-field dynamics, we provide an algorithm with a running time that is logarithmic in the desired optimality gap. Lastly, we compare the performance of our mean field-based policy with state-of-the-art heuristics via numerical experiments, including experiments using Austin scooter-sharing data. This paper was accepted by Jeannette Song, operations management. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2022.02023 .

Path Through Specified Nodes and Links in a Network

A constrained shortest route problem in graph theory is about determination of a shortest path between two given nodes of the network that also visits a given set of specified nodes or a set of specified links before arriving to the destination. These earlier approaches did not consider specified elements containing both nodes and links of the given network. This paper finds a shortest path joining the origin node to the destination node, which is constrained to pass through a set of ‘K’ specified elements of the given network, where K1 number of elements represent nodes, 0<K1<K, and K2 number of elements represent links, where K1+K2=K. Alternatively, if the specified elements representing nodes are contained in the set Sn and the remaining elements representing links by the set Sl, and the set of specified elements denoted by the set Se, then Se={Sn ∪ Sl}. Such restricted path will also have real-life applications. Depending upon the configuration of the specified elements, these constrained paths may have loops. The approach discussed in this paper is a heuristic approach, which finds the required constrained path in a real time.

Graph Contrastive Learning with Node-Level Accurate Difference

Graph contrastive learning (GCL) has attracted extensive research interest due to its powerful ability to capture latent structural and semantic information of graphs in a self-supervised manner. Existing GCL methods commonly adopt predefined graph augmentations to generate two contrastive views. Subsequently, they design a contrastive pretext task between these views with the goal of maximizing their agreement. These methods assume the augmented graph can fully preserve the semantics of the original. However, typical data augmentation strategies in GCL, such as random edge dropping, may alter the properties of the original graph. As a result, previous GCL methods overlooked graph differences, potentially leading to difficulty distinguishing between graphs that are structurally similar but semantically different. Therefore, we argue that it is necessary to design a method that can quantify the dissimilarity between the original and augmented graphs to more accurately capture the relationships between samples. In this work, we propose a novel graph contrastive learning framework, named Accurate Difference-based Node-Level Graph Contrastive Learning (DNGCL), which helps the model distinguish similar graphs with slight differences by learning node-level differences between graphs. Specifically, we train the model to distinguish between original and augmented nodes via a node discriminator and employ cosine dissimilarity to accurately measure the difference between each node. Furthermore, we employ multiple types of data augmentation commonly used in current GCL methods on the original graph, aiming to learn the differences between nodes under different augmentation strategies and help the model learn richer local information. We conduct extensive experiments on six benchmark datasets and the results show that our DNGCL outperforms most state-of-the-art baselines, which strongly validates the effectiveness of our model.

Generalized load modeling approach considering multiple distributed generation integration

To solve the problem of node characteristic uncertainty caused by the connection of multiple distributed generations to the original load node, a new method for modeling the steady-state characteristics of generalized load nodes based on scene clustering was proposed. Scenario clustering takes into account three factors: wind farm output fluctuation, photovoltaic output fluctuation, and demand-side power load fluctuation, and extracts typical scenarios of generalized load data. According to the uncertainty change of node characteristics in different scenarios, the clustering data is segmented and refined, and its probability distribution is counted. Clustering information, probability information, and maximum value are used as three types of features of generalized load and are custom encoded as 12-dimensional feature vectors as neural network inputs. To improve the identification performance of generalized load features, the back propagation (BP) dichotomy neural network is used to build a unified model of node features. The simulation results show that the proposed method can not only model accurately but also introduce probability information through statistical data samples, which can provide an auxiliary reference for the prediction and regulation of generalized loads.

Harnessing collective structure knowledge in data augmentation for graph neural networks

Graph neural networks (GNNs) have achieved state-of-the-art performance in graph representation learning. Message passing neural networks, which learn representations through recursively aggregating information from each node and its neighbors, are among the most commonly-used GNNs. However, a wealth of structural information of individual nodes and full graphs is often ignored in such process, which restricts the expressive power of GNNs. Various graph data augmentation methods that enable the message passing with richer structure knowledge have been introduced as one main way to tackle this issue, but they are often focused on individual structure features and difficult to scale up with more structure features. In this work we propose a novel approach, namely collective structure knowledge-augmented graph neural network (CoS-GNN), in which a new message passing method is introduced to allow GNNs to harness a diverse set of node- and graph-level structure features, together with original node features/attributes, in augmented graphs. In doing so, our approach largely improves the structural knowledge modeling of GNNs in both node and graph levels, resulting in substantially improved graph representations. This is justified by extensive empirical results where CoS-GNN outperforms state-of-the-art models in various graph-level learning tasks, including graph classification, anomaly detection, and out-of-distribution generalization.

Self-organizing broad network with frequency-domain analysis

The broad network (BN) based on random feature extraction has fast computational nature. However, it usually suffers from redundant features due to its randomization in dealing with massive samples, which brings the risk of overfitting. To overcome this problem, a self-organizing BN (SO-BN) is proposed in this article. First, several groups of polynomial-based fuzzy rules (P-FRs) are embedded into BN instead of the original feature nodes. Then, P-FR with the form of approximated bell functions has the capability to cope with the uncertainties of feature extraction. Second, a frequency domain parameter calculation algorithm is presented to update the parameters of P-FRs in SO-BN. Different from traditional randomization, P-FRs are shaped with frequency-domain analysis for achieving the representative features of samples. Third, an efficient self-organizing mechanism is built to adjust the structure of the enhancement layer dynamically. Then, the enhancement layer can be expanded and pruned rapidly to reduce the redundant feature as well as improve the performance of SO-BN. Finally, the proposed SO-BN is tested on two benchmark datasets and three real-world engineering applications, especially the prediction of sunspot numbers, electrical output and total phosphorus concentration. The results indicate that SO-BN can achieve superior prediction performance than other models.

Subgraph autoencoder with bridge nodes

Subgraph representation learning is a burgeoning field within graph representation learning. However, current methods in this field face several issues, including the inability to facilitate information interaction between subgraphs, the destruction of original node feature information, and the detrimental effect of the structural information of the entire graph on the extracted subgraph structural information. To address these issues, this paper proposes a method named the subgraph autoencoder with bridge nodes (SAWBN). Specifically, first, SAWBN enhances the data interaction capability by adding a bridge node and connecting it to all nodes within a subgraph. The addition of the bridge node creates indirect connections between subgraphs, enabling them to interact and exchange information during the message-passing phase. To the best of our knowledge, this is the first paper to propose the concept of bridge nodes and to introduce bridge nodes into subgraph representation learning. Second, SAWBN utilizes a new message-passing paradigm called graph convolution with different weights (GDW). During the convolution process, GDW can assign different weights to nodes inside and outside a subgraph, effectively distinguishing the importance of nodes without compromising the original node feature information. Third, SAWBN uses an autoencoder to reconstruct subgraph node features. This reconstruction can eliminate the interference of the structural information of the entire graph and regenerate subgraph node features that are rich in subgraph structural information. Finally, these subgraph node features are aggregated to achieve a good representation of the subgraph structural information. Extensive results on four real-world subgraph datasets demonstrate that SAWBN outperforms state-of-the-art baselines. The source code of SAWBN is publicly available at https://github.com/denggaoqin/SAWBN.

Trimetallic FeCoNi Metal-Organic Framework with Enhanced Peroxidase-like Activity for the Construction of a Colorimetric Sensor for Rapid Detection of Thiophenol in Water Samples.

In recent years, nanozymes have attracted particular interest and attention as catalysts because of their high catalytic efficiency and stability compared with natural enzymes, whereas how to use simple methods to further improve the catalytic activity of nanozymes is still challenging. In this work, we report a trimetallic metal-organic framework (MOF) based on Fe, Co and Ni, which was prepared by replacing partial original Fe nodes of the Fe-MOF with Co and Ni nodes. The obtained FeCoNi-MOF shows both oxidase-like activity and peroxidase-like activity. FeCoNi-MOF can not only oxidize the chromogenic substrate 3,3,5,5-tetramethylbenzidine (TMB) to its blue oxidation product oxTMB directly, but also catalyze the activation of H2O2 to oxidize the TMB. Compared with corresponding monometallic/bimetallic MOFs, the FeCoNi-MOF with equimolar metals hereby prepared exhibited higher peroxidase-like activity, faster colorimetric reaction speed (1.26-2.57 folds), shorter reaction time (20 min) and stronger affinity with TMB (2.50-5.89 folds) and H2O2 (1.73-3.94 folds), owing to the splendid synergistic electron transfer effect between Fe, Co and Ni. Considering its outstanding advantages, a promising FeCoNi-MOF-based sensing platform has been designated for the colorimetric detection of the biomarker H2O2 and environmental pollutant TP, and lower limits of detection (LODs) (1.75 μM for H2O2 and 0.045 μM for TP) and wider linear ranges (6-800 μM for H2O2 and 0.5-80 μM for TP) were obtained. In addition, the newly constructed colorimetric platform for TP has been applied successfully for the determination of TP in real water samples with average recoveries ranging from 94.6% to 112.1%. Finally, the colorimetric sensing platform based on FeCoNi-MOF is converted to a cost-effective paper strip sensor, which renders the detection of TP more rapid and convenient.

LMACL: Improving Graph Collaborative Filtering with Learnable Model Augmentation Contrastive Learning

Graph collaborative filtering (GCF) has achieved exciting recommendation performance with its ability to aggregate high-order graph structure information. Recently, contrastive learning (CL) has been incorporated into GCF to alleviate data sparsity and noise issues. However, most of the existing methods employ random or manual augmentation to produce contrastive views that may destroy the original topology and amplify the noisy effects. We argue that such augmentation is insufficient to produce the optimal contrastive view, leading to suboptimal recommendation results. In this article, we proposed a L earnable M odel A ugmentation C ontrastive L earning (LMACL) framework for recommendation, which effectively combines graph-level and node-level collaborative relations to enhance the expressiveness of collaborative filtering (CF) paradigm. Specifically, we first use the graph convolution network (GCN) as a backbone encoder to incorporate multi-hop neighbors into graph-level original node representations by leveraging the high-order connectivity in user-item interaction graphs. At the same time, we treat the multi-head graph attention network (GAT) as an augmentation view generator to adaptively generate high-quality node-level augmented views. Finally, joint learning endows the end-to-end training fashion. In this case, the mutual supervision and collaborative cooperation of GCN and GAT achieves learnable model augmentation. Extensive experiments on several benchmark datasets demonstrate that LMACL provides a significant improvement over the strongest baseline in terms of Recall and NDCG by 2.5%–3.8% and 1.6%–4.0%, respectively. Our model implementation code is available at https://github.com/LiuHsinx/LMACL .

Spatial-temporal memory enhanced multi-level attention network for origin-destination demand prediction

Origin-destination demand prediction is a critical task in the field of intelligent transportation systems. However, accurately modeling the complex spatial-temporal dependencies presents significant challenges, which arises from various factors, including spatial, temporal, and external influences such as geographical features, weather conditions, and traffic incidents. Moreover, capturing multi-scale dependencies of local and global spatial dependencies, as well as short and long-term temporal dependencies, further complicates the task. To address these challenges, a novel framework called the Spatial-Temporal Memory Enhanced Multi-Level Attention Network (ST-MEN) is proposed. The framework consists of several key components. Firstly, an external attention mechanism is incorporated to efficiently process external factors into the prediction process. Secondly, a dynamic spatial feature extraction module is designed that effectively captures the spatial dependencies among nodes. By incorporating two skip-connections, this module preserves the original node information while aggregating information from other nodes. Finally, a temporal feature extraction module is proposed that captures both continuous and discrete temporal dependencies using a hierarchical memory network. In addition, multi-scale features cascade fusion is incorporated to enhance the performance of the proposed model. To evaluate the effectiveness of the proposed model, extensively experiments are conducted on two real-world datasets. The experimental results demonstrate that the ST-MEN model achieves excellent prediction accuracy, where the maximum improvement can reach to 19.1%.

A heterogeneous graph-based semi-supervised learning framework for access control decision-making

For modern information systems, robust access control mechanisms are vital in safeguarding data integrity and ensuring the entire system’s security. This paper proposes a novel semi-supervised learning framework that leverages heterogeneous graph neural network-based embedding to encapsulate both the intricate relationships within the organizational structure and interactions between users and resources. Unlike existing methods focusing solely on individual user and resource attributes, our approach embeds organizational and operational interrelationships into the hidden layer node embeddings. These embeddings are learned from a self-supervised link prediction task based on a constructed access control heterogeneous graph via a heterogeneous graph neural network. Subsequently, the learned node embeddings, along with the original node features, serve as inputs for a supervised access control decision-making task, facilitating the construction of a machine-learning access control model. Experimental results on the open-sourced Amazon access control dataset demonstrate that our proposed framework outperforms models using original or manually extracted graph-based features from previous works. The prepossessed data and codes are available on GitHub,facilitating reproducibility and further research endeavors.

Heuristic Incident Edge Path Algorithm for Interval-Valued Neutrosophic Transportation Network

Neutrosophic Set is an extension of Fuzzy set theory dealts with uncertain environments in Transportation, Decision-making etc. Finding the shortest path for an uncertain environment is one of the most challenging tasks, many heuristic algorithms play a vital role in releasing this task. This research article an heuristic algorithmic approach using graph theoretical methods helps the researcher to crack the challenge and which type of algorithm can use the type of score functions are discussed. especially, the interval-valued Neutrosophic transportation problem (IVNTP) is considered for finding the shortest path which is a real-world decision-making problem in an ambiguous (uncertain) environment. Providing the shortest and finest way to address this ambiguity leads to the success of researcher to the organization. The algorithm used has been introduced for determination of interval-valued Neutrosophic shortest path (IVNSP) from the origin node to all other nodes by de-neutrosophicated edges using score functions. An illustrative Interval-valued neutrosophic transportation problem explains the algorithm’s efficacy and authenticity to find optimum result; this research article discusses about the nature of score functions, and some score function were taken into consideration. Further, the heuristic algorithm used is applicable for both positive and negative weighted edges; it was elaborated and compared with existing algorithm results also it provided all pair of shortest path. Future study and brief study of this article was disclosed in conclusion.

Simulating Fuel Assembly Bowing: A Neutron-Diffusion Method Based on Arbitrary Quadrilateral Node and Conformal Mapping Technique

Fuel assembly bowing, widely observed in a pressurized water reactor (PWR), often results in an asymmetrical power distribution. This paper proposes a neutron-diffusion method that integrates the arbitrary quadrilateral node with the conformal mapping technique to characterize the impact of fuel assembly bowing on power distribution. The proposed method involves a nonlinear iteration process to solve the neutron-diffusion equation. The global coarse-mesh finite difference equation is established on the arbitrary quadrilateral nodes, which are redivided in response to fuel assembly bowing. The local two-node nodal expansion method equation is established on the rectangular nodes, which are mapped from the original arbitrary quadrilateral nodes using the conformal mapping technique. The proposed method has improved our self-developed core code, named SPARK, for PWRs. To verify this novel method, two distinct types of fuel assembly bowing are modeled based on the mini core. The reference results for these models were obtained using the Monte Carlo code NECP-MCX. The numerical results suggest a robust agreement between the biases of keff and power distributions and their corresponding reference results.

Research on traffic flow prediction method based on adaptive multi-channel graph convolutional neural networks

In order to address the issues of predefined adjacency matrices inadequately representing information in road networks, insufficiently capturing spatial dependencies of traffic networks, and the potential problem of excessive smoothing or neglecting initial node information as the layers of graph convolutional neural networks increase, thus affecting traffic prediction performance, this paper proposes a prediction model based on Adaptive Multi-channel Graph Convolutional Neural Networks (AMGCN). The model utilizes an adaptive adjacency matrix to automatically learn implicit graph structures from data, introduces a mixed skip propagation graph convolutional neural network model, which retains the original node states and selectively acquires outputs of convolutional layers, thus avoiding the loss of node initial states and comprehensively capturing spatial correlations of traffic flow. Finally, the output is fed into Long Short-Term Memory networks to capture temporal correlations. Comparative experiments on two real datasets validate the effectiveness of the proposed model.

Fault diagnosis of helicopter tail-drive system using a multi-grained hierarchical message graph convolutional networks

ABSTRACT The fault diagnosis of the tail-drive of helicopter is a crucial task for helicopter system operation and maintenance. Recently, graph convolution network (GCN) has been the focus in fault diagnosis for its powerful representational ability in relationship mining. However, with the difficulty of obtaining node and edge information in the high-order domain, the stable performance of the long-range message-passing process of the deep GCN is unknown limits the application of GCN in fault diagnosis. To address these issues, a multi-grained hierarchical message graph convolutional network (MHGCN) is proposed to diagnose faults of helicopter tail-drive system. First, time-frequency characteristics of the original vibration signals are extracted to construct the graph nodes. The original graph nodes are aggregated by Louvain community detection, which can effectively learn the multi-grained features. Then, the hierarchical graph is introduced to learn the features of high-order neighbourhoods. Finally, a particular message-passing method is used to encode long-range information spanning the graph structure and realise accurate classification. Experiments on a test rig of helicopter tail-drive system are performed to verify the efficacy of the proposed method.

Node Embedding Preserving Graph Summarization

Graph summarization is a useful tool for analyzing large-scale graphs. Some works tried to preserve original node embeddings encoding rich structural information of nodes on the summary graph. However, their algorithms are designed heuristically and not theoretically guaranteed. In this article, we theoretically study the problem of preserving node embeddings on summary graph. We prove that three matrix-factorization-based node embedding methods of the original graph can be approximated by that of the summary graph, and we propose a novel graph summarization method, named HCSumm , based on this analysis. Extensive experiments are performed on real-world datasets to evaluate the effectiveness of our proposed method. The experimental results show that our method outperforms the state-of-the-art methods in preserving node embeddings.

A Dual Robust Graph Neural Network Against Graph Adversarial Attacks

Graph Neural Networks (GNNs) have gained widespread usage and achieved remarkable success in various real-world applications. Nevertheless, recent studies reveal the vulnerability of GNNs to graph adversarial attacks that fool them by modifying graph structure. This vulnerability undermines the robustness of GNNs and poses significant security and privacy risks across various applications. Hence, it is crucial to develop robust GNN models that can effectively defend against such attacks. One simple approach is to remodel the graph. However, most existing methods cannot fully preserve the similarity relationship among the original nodes while learning the node representation required for reweighting the edges. Furthermore, they lack supervision information regarding adversarial perturbations, hampering their ability to recognize adversarial edges. To address these limitations, we propose a novel Dual Robust Graph Neural Network (DualRGNN) against graph adversarial attacks. DualRGNN first incorporates a node-similarity-preserving graph refining (SPGR) module to prune and refine the graph based on the learned node representations, which contain the original nodes’ similarity relationships, weakening the poisoning of graph adversarial attacks on graph data. DualRGNN then employs an adversarial-supervised graph attention (ASGAT) network to enhance the model’s capability in identifying adversarial edges by treating these edges as supervised signals. Through extensive experiments conducted on four benchmark datasets, DualRGNN has demonstrated remarkable robustness against various graph adversarial attacks.

Topological Structure and Control Strategy of E-UPFC

This article proposes a unified power flow controller with energy (E-UPFC) installed at the renewable energy grid connection node of the transmission network. Compared with other unified power flow controllers (UPFCs), the proposed E-UPFC can not only regulate the power flow on its connected transmission lines, but also suppress the power fluctuations of grid-connected nodes injected with large-scale renewable energy. At the same time, with the installation position of E-UPFC transferred from the transmission line to the node, the original stiff node can be transformed into a flexible node that can regulate the injected power flexibly. First, the PV grid-connected system with E-UPFC is introduced, and its principle of power flow regulation is detailed. In addition, the topology, mathematical modeling, and control strategies of E-UPFC are discussed. Finally, the E-UPFC is applied to the IEEE 3-generator 9-bus system with large-scale renewable energy integration in Matlab/Simulink in order to verify the correctness and feasibility of E-UPFC and its control strategies.