Local Node Research Articles

Identifying neural network structures explained by personality traits: combining unsupervised and supervised machine learning techniques in translational validity assessment

AbstractThere have been studies previously the neurobiological underpinnings of personality traits in various paradigms such as psychobiological theory and Eysenck’s model as well as five-factor model. However, there are limited results in terms of co-clustering of the functional connectivity as measured by functional MRI, and personality profiles. In the present study, we have analyzed resting-state connectivity networks and character type with the Lowen bioenergetic test in 66 healthy subjects. There have been identified direct correspondences between network metrics such as eigenvector centrality (EC), clustering coefficient (CC), node strength (NS) and specific personality characteristics. Specifically, N Acc L and OFCmed were associated with oral and masochistic traits in terms of EC and CC, while Insula R is associated with oral traits in terms of NS and EC. It is noteworthy that we observed significant correlations between individual items and node measures in specific regions, suggesting a more targeted relationship. However, the more relevant finding is the correlation between metrics (NS, CC, and EC) and overall traits. A hierarchical clustering algorithm (agglomerative clustering, an unsupervised machine learning technique) and principal component analysis were applied, where we identified three prominent principal components that cumulatively explain 76% of the psychometric data. Furthermore, we managed to cluster the network metrics (by unsupervised clustering) to explore whether neural connectivity patterns could be grouped based on combined average network metrics and psychometric data (global and local efficiencies, node strength, eigenvector centrality, and node strength). We identified three principal components, where the cumulative amount of explained data reaches 99%. The correspondence between network measures (CC and NS) and predictors (responses to Lowen’s items) is 62% predicted with a precision of 90%.

A novel droop coefficient to realize rapid SOC balance for distributed energy storage systems

In the realm of isolated direct-current microgrids with varying distributed energy storage unit capacities, a new energy equalization strategy is proposed. This method involves an innovative approach that integrates an improved state-of-charge equalization control integrated with a sigmoid function to adaptively adjust the droop coefficient, aiming to accelerate the state-of-charge equalization rate. Furthermore, a virtual voltage drop equalization control is designed to dynamically adjust the output current of each distributed energy storage unit through a simple proportional–integral controller. This eliminates the influence of line impedance on accurate current distribution, improving overall accuracy. Additionally, a dynamic consistency algorithm is employed to gather average information about the distributed energy storage system, reducing communication line pressure as local nodes only exchange information with neighboring nodes. Integrating the aforementioned modules, the strategy proposed in this paper achieves rapid state-of-charge equalization, precise distribution of output current, and stable maintenance of the bus voltage. Finally, rigorous analysis of experimental results under various operating conditions verifies the feasibility and effectiveness of this control strategy by using the RT-LAB.

A polynomial proxy model approach to verifiable decentralized federated learning

Decentralized Federated Learning improves data privacy and eliminates single points of failure by removing reliance on centralized storage and model aggregation in distributed computing systems. Ensuring the integrity of computations during local model training is a significant challenge, especially before sharing gradient updates from each local client. Current methods for ensuring computation integrity often involve patching local models to implement cryptographic techniques, such as Zero-Knowledge Proofs. However, this approach becomes highly complex and sometimes impractical for large-scale models that use techniques such as random dropouts to improve training convergence. These random dropouts create non-deterministic behavior, making it challenging to verify model updates under deterministic protocols. We propose ProxyZKP, a novel framework combining Zero-Knowledge Proofs with polynomial proxy models to provide computation integrity in local training to address this issue. Each local node combines a private model for online deep learning applications and a proxy model that mediates decentralized model training by exchanging gradient updates. The multivariate polynomial nature of proxy models facilitates the application of Zero-Knowledge Proofs. These proofs verify the computation integrity of updates from each node without disclosing private data. Experimental results indicate that ProxyZKP significantly reduces computational load. Specifically, ProxyZKP achieves proof generation times that are 30–50% faster compared to established methods like zk-SNARKs and Bulletproofs. This improvement is largely due to the high parallelization potential of the univariate polynomial decomposition approach. Additionally, integrating Differential Privacy into the ProxyZKP framework reduces the risk of Gradient Inversion attacks by adding calibrated noise to the gradients, while maintaining competitive model accuracy. The results demonstrate that ProxyZKP is a scalable and efficient solution for ensuring training integrity in decentralized federated learning environments, particularly in scenarios with frequent model updates and the need for strong model scalability.

Generic network sparsification via hybrid edge sampling

Network (or graph) sparsification benefits downstream graph mining tasks. Finding a sparsified subgraph Gˆ similar to the original graph G is, however, challenging due to the requirement of preserving various (or at least representative) network properties. In this paper, we propose a general hybrid edge sampling scheme named LOGA, as the combination of the Local-filtering-based Random Edge sampling (LRE) (Hamann et al., 2016) and the Game-theoretic Sparsification with Tolerance (GST) (Su et al., 2022). LOGA fully utilizes the advantages of GST — in preserving complex structural properties by preserving local node properties in expectation – and LRE – in preserving the connectivity of a given network. Specifically, we first prove the existence of multiple equilibria in GST. This insight leads us to propose LOGA and its variant LOGAsc by refining GST. LOGA is obtained by regarding LRE as an empirically good initializer for GST, while LOGAsc is obtained by further including a constrained update for GST. In this way, LOGA/LOGAsc generalize the work on GST to graphs with weights and different densities, without increasing the asymptotic time complexity. Extensive experiments on 26 weighted and unweighted networks with different densities demonstrate that LOGAsc performs best for all 26 instances, i.e., they preserve representative network properties better than state-of-the-art sampling methods alone.

A new modification to the A* path-finding algorithm to improve its space and time performance

<p>We propose a new modification to the A* algorithm named AA* that significantly improves space and time complexities. In AA*’s forward pass, the node sets (open and closed) are not used, and only the local node neighborhood is saved to take the next move decision. AA* needs a backward pass to bridge and correct gaps and bad decisions made in the forward pass. The work of the backward pass is far less than that of the forward pass, as most of the task has been done. It is shown via empirical experimental work that our proposed AA* algorithm is superior to the classical A* algorithm in the typical three metrics: running time, number of probed nodes, and length of path. Furthermore, our experimental work showed that AA* is suboptimal in terms of length of path compared to the original Dijkstra’s algorithm with an accuracy of 96.95%.</p>

OGC SO13 - Recurrence Patterns after Minimally Invasive vs. Left Thoracoabdominal Oesophagectomy for distal oesophageal and junctional adenocarcinomas

Abstract Background Oesophageal cancer is a leading cause of cancer-related death worldwide, with oesophagec-tomy being the primary treatment for curable disease. This study compares loco-regional and distal disease recurrence patterns between minimally invasive oesophagectomy (MIO) and left thoracoabdominal oesophagectomy (LTAO) using a matched dataset. The definition of loco-regional recurrence remains unclear in the literature. In this study, loco-regional recur-rence is categorised as recurrence in the oesophageal bed, anastomosis, or local nodes in the mediastinum and upper abdomen. Method Patients from 2014 to 2021 were identified and followed until 31/12/2023. Data on MIOs and LTAO were collected from a prospectively maintained database. Gastroesophageal junction and distal oesophagus adenocarcinomas were included, and all received neoadjuvant chemotherapy. Out of 302 eligible patients, 104 were successfully matched. The primary outcome was overall cancer recurrence. Categorical variables were compared using chi-square tests, and non-parametric contin-uous variables with Mann-Whitney U tests. Propensity score matching, accounted for baseline differences. Logistic regression generated propensity scores for age, gender, and tumour stage. Operative approach was the dependant variable. The groups were then selected using ‘nearest neighbour’ matching. Results The study compared 52 cases each of LTAO and MIO. Postoperative complications were similar, LTAO (58%) and MIO (52%) P=0.554. The R0 resection rate was higher in LTAO (90%) compared to MIO (81%) P=0.163. Recurrence was significantly higher in LTAO (42%) than MIO (23%) P=0.037. Local recurrence rates were 15% for LTAO and 8% for MIO P=0.22. Distant recurrence was 35% for LTAO and 21% for MIO P=0.111. Notably, peritoneal recurrence was significantly higher in LTAO (12%) P=0.012. There was no difference in median time to recurrence. Mortality rate was similar: 38% for LTAO and 35% for MIO P=0.684. Conclusion The study found that while postoperative complications and mortality rates were similar between LTAO and MIO, LTAO had a significantly higher overall recurrence rate and notably higher peritoneal recurrence. There was no significant difference in median time to recurrence between the two groups. These findings suggest that MIO may be associated with better long-term outcomes in terms of recurrence.

Research on Weighted Network Model Construction and Layout Structure of New Energy Vehicle Charging Station

(1) Background: Spatial layout is the key to the construction and development of new energy vehicle charging stations; (2) Methods: A network analysis method is used to build the new energy vehicle charging station network, design network indicators, analyze the structural characteristics of new energy vehicle charging stations based on the local nodes and the overall structure of the network, and identify the key nodes and important parts of the network; (3) Results: Taking the new energy vehicle charging station in Jinan City of Shandong Province as an example, the empirical analysis is carried out. The empirical results show that the new energy vehicle charging station network constructed in this paper and the network indicators designed can effectively describe the layout of new energy vehicle charging stations, identifying key stations and important parts of the network; (4) Conclusions: This provides a theoretical basis for further improving the utilization rate of charging stations and the reasonable planning of new energy vehicle charging stations. It provides an idea and method for the research on the layout of charging stations for new energy vehicles.

Higher-order structure based node importance evaluation in directed networks

Evaluating the significance of objects with possible relevant information is a crucial topic in information science. Due to the fact that objects related to each other can often be described using complex networks, this topic also forms a fundamental theme in network science. Most traditional methods for characterizing the importance of nodes in complex networks only utilize the binary relationships between node pairs, neglecting the influence brought by higher-order structures. Considering the specific interaction modes between local nodes in the network, this paper associates the higher-order structural characteristics of the network with the importance of the nodes. It constructs an evaluation framework for the importance of nodes in directed networks based on higher-order structures. Experimental analysis on both artificial data and scientific citation data from the APS dataset has validated the effectiveness of the proposed algorithms. Compared with PageRank and eigenvector centrality, the proposed algorithms demonstrated higher accuracy, revealing the role of higher-order structures in node importance evaluation. Finally, a robustness analysis of several algorithms indicated that the proposed algorithms exhibited good robustness.

Heterogeneous graph representation learning via mutual information estimation for fraud detection

In the fraud detection, fraudsters frequently engage with numerous benign users to disguise their activities. Consequently, the fraud graph exhibits not only homogeneous connections between the fraudsters and the same labelled nodes, but also heterogeneous connections, where fraudsters interact with the legitimate nodes. Heterogeneous graph representation learning aims at extracting the structural and semantic information and embed it into the low-dimensional node representation. Recently, maximizing the mutual information between the local node embedding and the summary representation has achieved the promising results on node classification tasks. However, existing deep graph infomax methods still have the following limitations. Firstly, attribute information of nodes in the graph is not fully utilized for capturing the semantic relationships between nodes. Secondly, the local and global supervision signal are not simultaneously exploited for the node embedding learning. Thirdly, the multiplex heterogeneous relations among nodes are ignored. To address these issues, a heterogeneous graph representation learning model by mutual information estimation (MIE-HetGRL) is proposed in this paper to identify the fraudsters in the fraud review graph. Concretely, a high-order mutual information estimation is proposed to integrate the local and global mutual information as the supervision signal. Then we devise a semantic attention fusion module to aggregate the relation-aware node embeddings into a compact node representation. Finally, a joint contrastive learning is designed for facilitating the training and optimization of model. The experimental results show that our proposed model significantly outperforms state-of-the-art baselines for fraud detection.

New Strategies for Boosting Localization Accuracy in Wireless Sensor Nodes

Wireless Sensor Networks (WSNs), accurate and energy-efficient localization of sensor nodes remains a challenging task despite significant advancements. Current geolocation algorithms often struggle with scalability, adaptability, and energy efficiency, particularly in large-scale, dynamic environments where node failures or random shifts occur. This paper proposes a novel Secure Node Localization (SABWP-NL) approach, combining Self-Adaptive Binary Waterwheel Plant Optimization (SABWP) and Bayesian optimization to enhance localization accuracy, scalability, energy efficiency, and robustness. The method evaluates node trust using Dempster-Shafer Evidence Theoryto secure localization against rogue nodes and optimizes the localization process through trilateral and multilateration systems. The SABWP-NL approach demonstrates superior performance in terms of localized nodes and localization error compared to existing techniques like BWP, ROA, and AO. Results show that SABWP-NL achieves the highest number of localized nodes and the lowest localization error, making it a promising solution for efficient and secure node localization in WSNs.

Maximizing Influence in Social Networks Using Combined Local Features and Deep Learning-Based Node Embedding.

The influence maximization problem has several issues, including low infection rates and high time complexity. Many proposed methods are not suitable for large-scale networks due to their time complexity or free parameter usage. To address these challenges, this article proposes a local heuristic called Embedding Technique for Influence Maximization (ETIM) that uses shell decomposition, graph embedding, and reduction, as well as combined local structural features. The algorithm selects candidate nodes based on their connections among network shells and topological features, reducing the search space and computational overhead. It uses a deep learning-based node embedding technique to create a multidimensional vector of candidate nodes and calculates the dependency on spreading for each node based on local topological features. Finally, influential nodes are identified using the results of the previous phases and newly defined local features. The proposed algorithm is evaluated using the independent cascade model, showing its competitiveness and ability to achieve the best performance in terms of solution quality. Compared with the collective influence global algorithm, ETIM is significantly faster and improves the infection rate by an average of 12%.

Federated Node Classification over Distributed Ego-Networks with Secure Contrastive Embedding Sharing.

Federated learning on graphs (a.k.a., federated graph learning- FGL) has recently received increasing attention due to its capacity to enable collaborative learning over distributed graph datasets without compromising local clients' data privacy. In previous works, clients of FGL typically represent institutes or organizations that possess sets of entire graphs (e.g., molecule graphs in biochemical research) or parts of a larger graph (e.g., sub-user networks of e-commerce platforms). However, another natural paradigm exists where clients act as remote devices retaining the graph structures of local neighborhoods centered around the device owners (i.e., ego-networks), which can be modeled for specific graph applications such as user profiling on social ego-networks and infection prediction on contact ego-networks. FGL in such novel yet realistic ego-network settings faces the unique challenge of incomplete neighborhood information for non-ego local nodes since they likely appear and have different sets of neighbors in multiple ego-networks. To address this challenge, we propose an FGL method for distributed ego-networks in which clients obtain complete neighborhood information of local nodes through sharing node embeddings with other clients. A contrastive learning mechanism is proposed to bridge the gap between local and global node embeddings and stabilize the local training of graph neural network models, while a secure embedding sharing protocol is employed to protect individual node identity and embedding privacy against the server and other clients. Comprehensive experiments on various distributed ego-network datasets successfully demonstrate the effectiveness of our proposed embedding sharing method on top of different federated model sharing frameworks, and we also provide discussions on the potential efficiency and privacy drawbacks of the method as well as their future mitigation.

Hypergraph animals.

Here we introduce simple structures for the analysis of complex hypergraphs, hypergraph animals. These structures are designed to describe the local node neighborhoods of nodes in hypergraphs. We establish their relationships to lattice animals and network motifs, and we develop their combinatorial properties for sparse and uncorrelated hypergraphs. We make use of the tight link of hypergraph animals to partition numbers, which opens up a vast mathematical framework for the analysis of hypergraph animals. We then study their abundances in random hypergraphs. Two transferable insights result from this analysis: (i) it establishes the importance of high-cardinality edges in ensembles of random hypergraphs that are inspired by the classical Erdös-Renyí random graphs; and (ii) there is a close connection between degree and hyperedge cardinality in random hypergraphs that shapes animal abundances and spectra profoundly. Both findings imply that hypergraph animals can have the potential to affect information flow and processing in complex systems. Our analysis also suggests that we need to spend more effort on investigating and developing suitable conditional ensembles of random hypergraphs that can capture real-world structures and their complex dependency structures.

Optimizing Virtual Network Embedding for Avionics with Time-Triggered Traffic Scheduling

Network virtualization technology abstracts the nodes and links resources in the physical network, and enables multiple virtual networks (VNs) to share the substrate network (SN) resources through the Virtual Netw ork Embedding (VNE) method. For time-triggered Ethernet (TTE) used in avionics, a time-triggered traffic scheduling oriented virtual network embedding (TT-VNE) method is proposed. While meeting the total resource constraints of traditional VNE problem, it ensures the strict periodicity of time-triggered (TT) traffic. During the solution process, the method sorts the virtual nodes according to the TT traffic bandwidth requirements and the total bandwidth requirements of the links connected to the virtual nodes, embeds the virtual nodes using the breadth first search algorithm, and plans the virtual links in candidate shortest path aggregation. If the TT traffic in the current virtual link is not schedulable, the iterative design of local virtual node re embedding and path planning is carried out. The simulation shows that the request acceptance rate of TT-VNE is not lower than that of existing methods, and when the number of virtual network requests in the star topology exceeds 30 , its request acceptance rate is about 14.3%higher than the VNE-NTANRC-D method which only considers the network topology and resource attributes.

Bayesian Federated Learning with Hamiltonian Monte Carlo: Algorithm and Theory

This work introduces a novel and efficient Bayesian federated learning algorithm, namely, the Federated Averaging stochastic Hamiltonian Monte Carlo (FA-HMC), for parameter estimation and uncertainty quantification. We establish rigorous convergence guarantees of FA-HMC on non-iid distributed datasets, under the strong convexity and Hessian smoothness assumptions. Our analysis investigates the effects of parameter space dimension, noise on gradients and momentum, and the frequency of communication (between the central node and local nodes) on the convergence and communication costs of FA-HMC. Beyond that, we establish the tightness of our analysis by showing that the convergence rate cannot be improved even for continuous FA-HMC process. Moreover, extensive empirical studies demonstrate that FA-HMC outperforms the existing Federated Averaging-Langevin Monte Carlo (FA-LD) algorithm. Supplementary materials for this article are available online.

SP6.1 - Use of Endomag (Magseed® and Magtrace®): our initial experience at Midyorks trust

Abstract Introduction WLE is a cornerstone in breast surgery post MILAN trail. Breast lesions undergo wire guided localisation. Drawbacks are scheduling, patient dissatisfaction, wire movement and discomfort, SLNB: Combined technique. Radioactive (TcM99m) labelled nanocolloid and 2mls of diluted Patent V blue dye. NEWSTART and ALMANAC, largest UK SLNB datasets- 1% allergy rate Whereas in endomag, Magseed® Marker- Tiny Magnetic seed Less intrusive than guide-wire- flexible and precise. Can be inserted anytime before surgery. Only becomes detectable when Sentimag Probe passes over it. Magtrace® Lymphatic Tracer Non radioactive and non toxic- safer compared to blue-dye Can be injected up to 28 days prior to surgery. Aim Demonstrate the feasibility of Magseed® marker localisation and Magtrace® tracer injection for breast lesions and sentinel lymph nodes in our unit. Methods All patients who underwent breast WLE from 12/21 to 03/22 using endomag. Sample size identified 63 Total number of procedures: 64 Diagnostic excisions 8 WLE 16 WLE and SNB 39 WLE and ANC 1 Technique of magseed insertion: Stereo 41, U/S 22. Eight patients had clear margin after second surgery One patient needed third surger Magseed not retrieved in original specimen but retrieved via intra-operative shave during same surgery: 4/ 64 (6.25%) Magseed not retrieved during surgery: 3/ 64 (4.68%) Two patients required redo surgery and one completion mastectomy.Magtrace Tracer Failed SNB requiring sampling: 7 / 39 (17.9%). Conclusion Endomag is safe and accurate with comparable surgical endpoints (margins) to traditional localisation. With time (learning curve) intra-operative magseed localisation and sentinel node detection will improve.

Training-free approach to constructing ensemble of local experts

Conventional machine learning methods assume that a central server holds the entire training dataset for training a global model. However, in many real-world situations, datasets are collected from individual local nodes in distributed environments. Gathering these datasets often poses challenges owing to various practical constraints such as data security and privacy issues, storage limits, and transmission costs. When data distributions differ among local nodes, local experts trained on individual local nodes exhibit poor generalization performance for new instances. In this study, we propose a training-free method for constructing an ensemble of local experts without accessing datasets. For a query instance, we apply uncertainty quantification and out-of-distribution (OOD) detection to calculate the uncertainty and OOD scores of the predictions from individual models. We then determine the weights of the models by assigning a lower weight to those with higher uncertainty and OOD scores. Using these weights, the predictions of the individual models are aggregated to obtain a final prediction. In contrast to existing methods that impose specific application requirements, the proposed method can be applied in situations in which only individual predictions from local models are available for use when making a prediction for a query instance. We evaluate the effectiveness of the proposed method using image classification benchmark datasets.

Continuous Dictionary of Nodes Model and Bilinear-Diffusion Representation Learning for Brain Disease Analysis.

Brain networks based on functional magnetic resonance imaging (fMRI) provide a crucial perspective for diagnosing brain diseases. Representation learning has recently attracted tremendous attention due to its strong representation capability, which can be naturally applied to brain disease analysis. However, traditional representation learning only considers direct and local node interactions in original brain networks, posing challenges in constructing higher-order brain networks to represent indirect and extensive node interactions. To address this problem, we propose the Continuous Dictionary of Nodes model and Bilinear-Diffusion (CDON-BD) network for brain disease analysis. The CDON model is innovatively used to learn the original brain network, with its encoder weights directly regarded as latent features. To fully integrate latent features, we further utilize Bilinear Pooling to construct higher-order brain networks. The Diffusion Module is designed to capture extensive node interactions in higher-order brain networks. Compared to state-of-the-art methods, CDON-BD demonstrates competitive classification performance on two real datasets. Moreover, the higher-order representations learned by our method reveal brain regions relevant to the diseases, contributing to a better understanding of the pathology of brain diseases.

Microwave ablation for lymph node metastasis in thyroid cancer: the impact of lymph node diameter.

To explore the impact of lymph node diameter on the efficacy and safety of ultrasound-guided microwave ablation (MWA) in the treatment of cervical metastatic lymph nodes (CMLNs) from thyroid cancer. A total of 32 patients with 58 CMLNs from thyroid cancer underwent ultrasound-guided MWA and were included in the retrospective study. Patients were divided into three groups based on the mean largest diameter of the CMLNs: Group A (diameter ≤10mm), Group B (10mm < diameter ≤20mm), and Group C (diameter >20mm). The research involved comparing changes in cervical metastatic lymph nodes and serum thyroglobulin (sTg) levels, as well as the incidence of complications, before and after microwave ablation across three groups of patients. The technical success rate of this study was 100% (32/32), and they showed no major complications. Compared with measurements taken before MWA, the mean largest diameter and volume of CMLNs, as well as the sTg level, showed significant reductions (p <0.05) at the last follow-up in all three patient groups. Group A and B exhibited higher lymph node volume reduction rates and complete disappearance rates compared to Group C. However, the recurrence rate in the three groups were in the following order: Group C > Group B > Group A. The occurrence rate of mild complications was Group A > Group C > Group B. MWA is a safe and effective method for treating CMLNs, with advantages for localized nodes but limitations for larger ones. Careful consideration and personalized plans are advised, based on comprehensive evidence assessment.

An Efficient Modified Black Widow Optimized Node Localization in Wireless Sensor Network

Wireless Sensor Network (WSN) is an encouraging technology in various applications like atmosphere monitoring, vehicular systems, and targeting devices. Localization in WSN is performed to identify the current position or coordinates of sensor nodes. The crucial task of localization is to find coordinates without manual configuration and expensive hardware like GPS. This work proposes a new localization algorithm using Modified Black Widow Optimization (MBWO). The proposed method involves an optimal selection of anchor nodes to reduce localization errors. Black Widow Optimization (BWO) is a naturally inspired optimization algorithm encouraged by the unique coupling behaviour of black widow spiders. The performance of black widow optimization is improved by levy flight distribution to escape from local minima. Experimental results show that the proposed MBWO-optimized localization achieves a higher localized node count with minimized localized error compared to other optimization algorithms.