Network Interactions Research Articles

Few-Shot Relation Extraction With Dual Graph Neural Network Interaction.

Recent advances in relation extraction with deep neural architectures have achieved excellent performance. However, current models still suffer from two main drawbacks: 1) they require enormous volumes of training data to avoid model overfitting and 2) there is a sharp decrease in performance when the data distribution during training and testing shift from one domain to the other. It is thus vital to reduce the data requirement in training and explicitly model the distribution difference when transferring knowledge from one domain to another. In this work, we concentrate on few-shot relation extraction under domain adaptation settings. Specifically, we propose DUAL GRAPH, a novel graph neural network (GNN) based approach for few-shot relation extraction. DUAL GRAPH leverages an edge-labeling dual graph (i.e., an instance graph and a distribution graph) to explicitly model the intraclass similarity and interclass dissimilarity in each individual graph, as well as the instance-level and distribution-level relations across graphs. A dual graph interaction mechanism is proposed to adequately fuse the information between the two graphs in a cyclic flow manner. We extensively evaluate DUAL GRAPH on FewRel1.0 and FewRel2.0 benchmarks under four few-shot configurations. The experimental results demonstrate that DUAL GRAPH can match or outperform previously published approaches. We also perform experiments to further investigate the parameter settings and architectural choices, and we offer a qualitative analysis.

Модели сетевого адаптивного взаимодействия организаций в условиях принятия решения доминирующим собственником о реализации проекта

In modern business conditions, the network interaction of organizations is one of the most effective forms of cooperation within the framework of the project. The ability of the network to adapt to changing factors and conditions of the external and internal environment based on the reactive management of business processes of project interaction ensures not only the achievement of project goals, but also the satisfaction of the complementary interests of all counterparties. The process of developing the author's model includes an analysis of existing models of network interaction between organizations, the study of methods and approaches to evaluating the effectiveness of such interaction, as well as the identification of key factors influencing the success of the project. The results obtained will improve the understanding of the processes of networking between organizations in the implementation of projects, as well as develop recommendations to improve the effectiveness of such interaction. The results can also be useful both for the scientific community and for practitioners involved in project management and business processes in a network context. The methodological basis of the study was the methods of comparative and logical analysis, induction and deduction, analysis and synthesis. As a result of the work carried out, the author's model of network adaptive interaction of organizations was formed in the conditions of decision-making by the dominant owner on the implementation of the project.

Dynamic Reorganization Patterns of Brain Modules after Stroke Reflecting Motor Function.

Advancements in neuroimaging technologies have significantly deepened our understanding of the neural physiopathology associated with stroke. Nevertheless, the majority of studies ignored the characteristics of dynamic changes in brain networks. The relationship between dynamic changes in brain networks and the severity of motor dysfunction after stroke needs further investigation. From the perspective of multilayer network module reconstruction, we aimed to explore the dynamic reorganization of the brain and its relationship with motor function in subcortical stroke patients. We recruited 35 healthy individuals and 50 stroke patients with unilateral limb motor dysfunction (further divided into mild-moderate group and severe group). Using dynamic multilayer network modularity analysis, we investigated changes in the dynamic modular reconfiguration of brain networks. Additionally, we assessed longitudinal clinical scale changes in stroke patients. Correlation and regression analyses were employed to explore the relationship between characteristic dynamic indicators and impairment and recovery of motor function, respectively. We observed increased temporal flexibility in the Default Mode Network (DMN) and decreased recruitment of module reconfiguration in the Attention Network (AN), Sensorimotor Network (SMN), and DMN after stroke. We also observed reduced module loyalty following stroke. Additionally, correlation analysis showed that hyper-flexibility of the DMN was associated with better lower limb motor function performance in stroke patients with mild-to-moderate impairment. Regression analysis indicated that increased flexibility within the DMN and decreased recruitment coefficient within the AN may predict good lower limb function prognosis in patients with mild to moderate motor impairment. Our study revealed more frequent modular reconfiguration and hyperactive interaction of brain networks after stroke. Notably, dynamic modular remodeling was closely related to the impairment and recovery of motor function. Understanding the temporal module reconfiguration patterns in multilayer networks after stroke can provide valuable information for more targeted treatments.

From single tube to multi-channel configuration: Constructing nanofiltration membranes with superior adhesion strength on the ceramic support by interfacial polymerization

Ceramic membranes with multi-channel configurations exhibit superior mechanical strength, high packing density, and high separation efficiency, making them more suitable for industrial applications than single tube and hollow fiber membranes. However, the preparation of thin-film composite (TFC) membranes on multi-channel ceramic supports remains a challenge because of the poor compatibility between organic and inorganic materials and their special configuration. In this study, nanofiltration membranes with a stabilized structure supported by 19-channel ceramic membranes were successfully prepared with improved adhesion strength and dynamic interfacial polymerization. TFC membranes with different channels exhibited uniform microstructure and stable performance. Specifically, polyethyleneimine, which served as a polymerization reactant, can be tightly wound on the surface of ceramic membranes via hydrogen bonding and van der Waals forces during interfacial polymerization. Owing to the enhanced cross-linked network interactions between the support and separation layers, the adhesion strength was significantly improved. Consequently, the optimized membranes maintained excellent rejection to MgCl2 of ∼94 % after the back-flush test under the pressure of 4 bar. Additionally, the multi-channel TFC membranes exhibited stable performance, with a pure water permeance of ∼14.9 LMH/bar and a molecular weight cut-off of 450 Da. When filtering sunset yellow for 10 h, the prepared membranes exhibited stable permeance and excellent rejection performance.

Predictive modeling of evoked intracranial EEG response to medial temporal lobe stimulation in patients with epilepsy

Despite promising advancements, closed-loop neurostimulation for drug-resistant epilepsy (DRE) still relies on manual tuning and produces variable outcomes, while automated predictable algorithms remain an aspiration. As a fundamental step towards addressing this gap, here we study predictive dynamical models of human intracranial EEG (iEEG) response under parametrically rich neurostimulation. Using data from n = 13 DRE patients, we find that stimulation-triggered switched-linear models with ~300 ms of causal historical dependence best explain evoked iEEG dynamics. These models are highly consistent across different stimulation amplitudes and frequencies, allowing for learning a generalizable model from abundant STIM OFF and limited STIM ON data. Further, evoked iEEG in nearly all subjects exhibited a distance-dependent pattern, whereby stimulation directly impacts the actuation site and nearby regions (≲ 20 mm), affects medium-distance regions (20 ~ 100 mm) through network interactions, and hardly reaches more distal areas (≳ 100 mm). Peak network interaction occurs at 60 ~ 80 mm from the stimulation site. Due to their predictive accuracy and mechanistic interpretability, these models hold significant potential for model-based seizure forecasting and closed-loop neurostimulation design.

Differential spatial responses and assembly mechanisms of soil microbial communities across region-scale Taiga ecosystems

Different soil microbial communities play distinct key roles in regulating forest ecosystem processes and functions. However, the differences in spatial variability and assembly mechanisms of various taiga forest soil microbial taxa remain poorly understood. Here, we assessed the spatial patterns of bacterial and fungal communities, their assembly processes, and the influencing factors in taiga forest ecosystems in Xinjiang, China. A significant distance decay pattern was observed in the similarity of bacterial and fungal communities, with bacterial communities exhibiting a more pronounced pattern than fungal communities. Stochastic and deterministic processes governed together to drive soil bacterial community assembly, whereas stochastic processes dominated fungal community assembly. The coexistence networks revealed that the interactions of bacterial and fungal networks in the four regions are primarily based on interspecies symbiosis, with fungal coexistence networks demonstrating greater stability than bacterial networks. Additionally, the study identified a positive relationship between the modularity of bacterial networks and dispersal limitation. Analysis of environmental factors revealed that soil pH primarily affects the characteristics and assembly mechanisms of bacterial communities, while vegetation conditions primarily affect fungal diversity and composition, with other unconsidered environmental variables influencing the fungal community assembly process. This study emphasized the distinct ways in which bacteria and fungi respond to environmental factors and interspecies interactions. Our results suggested that distinct restoration measures should be implemented for bacteria and fungi in future conservation efforts for forest soil microorganisms.

Understanding destination marketing processes through film tourism: local and global networks

ABSTRACT This study employs actor-network theory to examine the dynamics of destination marketing in Hokkaido, Japan, where countless films are shot. It is among the first to adopt the local/global network framework in tourism studies, and examine tourism processes through the mobilization, interaction, and disintegration of networks. Networks are understood vis-à-vis actors, and not by the static notion of “power over,” but through the dynamic enactment of the notion of “power to.” The findings show that networks exercise power within them instead of top-down control, and can help practitioners market destinations successfully.

Dynamic Malware Analysis Using a Sandbox Environment, Network Traffic Logs, and Artificial Intelligence.

Dynamic malware analysis plays a pivotal role in modern cybersecurity, offering insights into malware behavior through dynamic execution and network traffic analysis. In this study, we present a comprehensive approach to dynamic malware analysis using a sandbox environment and network traffic logs. Our methodology involves the extraction of relevant features from network traffic captured in pcap files. We conducted experiments using a virtualized Oracle VirtualBox environment, where benign and malicious software samples were executed within a Windows virtual machine controlled by Python scripts. For network emulation, we utilized tools from the REMnux distribution, including InetSim and FakeDNS, to simulate realistic network interactions during malware execution. The collected pcap data underwent preprocessing and feature extraction to capture essential behavioral patterns and network indicators. Machine learning and artificial intelligence models were developed to classify malware based on these extracted features. Our findings underscore the efficacy of dynamic analysis coupled with machine learning in detecting and classifying malware variants based on their network behavior. This research contributes to advancing techniques for real-time threat detection and response in cybersecurity, emphasizing the importance of dynamic malware analysis in mitigating evolving cyber threats.

Electrophysiological dynamics of salience, default mode, and frontoparietal networks during episodic memory formation and recall: A multi-experiment iEEG replication.

Dynamic interactions between large-scale brain networks underpin human cognitive processes, but their electrophysiological mechanisms remain elusive. The triple network model, encompassing the salience (SN), default mode (DMN), and frontoparietal (FPN) networks, provides a framework for understanding these interactions. We analyzed intracranial EEG recordings from 177 participants across four diverse episodic memory experiments, each involving encoding as well as recall phases. Phase transfer entropy analysis revealed consistently higher directed information flow from the anterior insula (AI), a key SN node, to both DMN and FPN nodes. This directed influence was significantly stronger during memory tasks compared to resting-state, highlighting the AI's task-specific role in coordinating large-scale network interactions. This pattern persisted across externally-driven memory encoding and internally-governed free recall. Control analyses using the inferior frontal gyrus (IFG) showed an inverse pattern, with DMN and FPN exerting higher influence on IFG, underscoring the AI's unique role. We observed task-specific suppression of high-gamma power in the posterior cingulate cortex/precuneus node of the DMN during memory encoding, but not recall. Crucially, these results were replicated across all four experiments spanning verbal and spatial memory domains with high Bayes replication factors. Our findings advance understanding of how coordinated neural network interactions support memory processes, highlighting the AI's critical role in orchestrating large-scale brain network dynamics during both memory encoding and retrieval. By elucidating the electrophysiological basis of triple network interactions in episodic memory, our study provides insights into neural circuit dynamics underlying memory function and offer a framework for investigating network disruptions in memory-related disorders.

Comparative Analysis: Machine vs Human Translation of Educational Scientific Texts. Challenges and Solutions

Introduction. The purpose of this article is to analyze the features of identity formation and identification processes in postmodern society and in digital society. The article explores various approaches to the concept of «identity» within the framework of socio-humanitarian theories. The interrelation of real and virtual identity, the emergence of new forms and models of identity are considered. Two approaches to the analysis of identity in a digital society are analyzed and compared: digital optimism and digital pessimism.Methodology and sources. The article uses a comparative analysis of various theoretical approaches to identity formation. An interdisciplinary approach is used to understand the features of identity in the era of digitalization. As the main sources for the study of the phenomenon of identity there were used works of classics of sociology and psychology E. Erickson, J.G. Meade, E. Durkheim, as well as studies of representatives of modern philosophical and sociological theories Z. Bauman, A. Giddens, S. Turkle, A.A. Lisenkova, T.G. Leshkevich.Results and discussion. It is shown that in postmodern society, identity is characterized by the processes of individualization, fragmentation and the absence of a single cultural center. In a digital society, along with the processes of individualization, there are processes of standardization and unification of person. It is concluded that in a digital society, identity has positive and negative sides. On the one hand, there is a positive vector for the use of online communications, network interaction of people, which destroys spatial and temporal boundaries, as well as social barriers. On the other hand, new types of virtual identity are being formed, challenging a person's own identity.Conclusion. It is concluded that the digital society changes human identity, identification practices and strategies. The consequence of these processes is the formation of a person fused with digital technologies, which leads to the transformation of the social order, social norms and society as a whole.

Digital Technologies and Society: Identity Transformation

Introduction. The purpose of this article is to analyze the features of identity formation and identification processes in postmodern society and in digital society. The article explores various approaches to the concept of «identity» within the framework of socio-humanitarian theories. The interrelation of real and virtual identity, the emergence of new forms and models of identity are considered. Two approaches to the analysis of identity in a digital society are analyzed and compared: digital optimism and digital pessimism.Methodology and sources. The article uses a comparative analysis of various theoretical approaches to identity formation. An interdisciplinary approach is used to understand the features of identity in the era of digitalization. As the main sources f or the study of the phenomenon of identity there were used works of classics of sociology and psychology E. Erickson, J.G. Meade, E. Durkheim, as well as studies of representatives of modern philosophical and sociological theories Z. Bauman, A. Giddens, S. Turkle, A.A. Lisenkova, T.G. Leshkevich.Results and discussion. It is shown that in postmodern society, identity is characterized by the processes of individualization, fragmentation and the absence of a single cultural center. In a digital society, along with the processes of individualization, there are processes of standardization and unification of person. It is concluded that in a digital society, identity has positive and negative sides. On the one hand, there is a positive vector for the use of online communications, network interaction of people, which destroys spatial and temporal boundaries, as well as social barriers. On the other hand, new types of virtual identity are being formed, challenging a person's own identity.Conclusion. It is concluded that the digital society changes human identity, identification practices and strategies. The consequence of these processes is the formation of a person fused with digital technologies, which leads to the transformation of the social order, social norms and society as a whole.

BioPathNet: Enhancing Link Prediction in Biomedical Knowledge Graphs through Path Representation Learning.

Understanding complex interactions in biomedical networks is crucial for advancements in biomedicine, but traditional link prediction (LP) methods are limited in capturing this complexity. Representation-based learning techniques improve prediction accuracy by mapping nodes to low-dimensional embeddings, yet they often struggle with interpretability and scalability. We present BioPathNet, a novel graph neural network framework based on the Neural Bellman-Ford Network (NBFNet), addressing these limitations through path-based reasoning for LP in biomedical knowledge graphs. Unlike node-embedding frameworks, BioPathNet learns representations between node pairs by considering all relations along paths, enhancing prediction accuracy and interpretability. This allows visualization of influential paths and facilitates biological validation. BioPathNet leverages a background regulatory graph (BRG) for enhanced message passing and uses stringent negative sampling to improve precision. In evaluations across various LP tasks, such as gene function annotation, drug-disease indication, synthetic lethality, and lncRNA-mRNA interaction prediction, BioPathNet consistently outperformed shallow node embedding methods, relational graph neural networks and task-specific state-of-the-art methods, demonstrating robust performance and versatility. Our study predicts novel drug indications for diseases like acute lymphoblastic leukemia (ALL) and Alzheimer's, validated by medical experts and clinical trials. We also identified new synthetic lethality gene pairs and regulatory interactions involving lncRNAs and target genes, confirmed through literature reviews. BioPathNet's interpretability will enable researchers to trace prediction paths and gain molecular insights, making it a valuable tool for drug discovery, personalized medicine and biology in general.

Label-free and TMT-labeled Proteomics Methods to Compare Differences on Normal and Attached Livers of Glyptosternum maculatum

Background: The aim of this study is to compare the molecular differences between the normal liver (NG) and attached liver (WG) of Glyptosternum maculatum (G. maculatum) based on label-free and TMT-labeled proteomics data. It provides a theoretical basis for the adaptation of G. maculatum in the plateau area with low temperature and low oxygen Methods: The differentially expressed proteins (DEPs) of label-free and TMT-labeled proteomics data were analyzed by Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway, and protein structural domain (PSD) enrichment, and protein network interactions were constructed to reveal protein characteristics. Results: detected a total of 643 and 107 DEPs; 7 common DEPs (co-DEPs) were selected through PPI network information. Higher expression of evm.model.chr5.73, evm.model.chr18.610, evm.model.chr10.1201, and HIF-1 signaling pathway were associated with a hypoxic environment. evm.model.chr15.573, evm.model .chr5.320, evm.- model.chr6.360, and evm.model.chr18.610 were associated with WG production. Significant expression of Ubiquitin-like protein 4A and Heat shock 70 kDa protein protects liver cells from injury in a hypothermic and hypoxic environment. Conclusion: In terms of the number of DEPs, the labelling-free method is superior to the TMT-labeled method. The TMT-labeled method is better in terms of repeatability and accuracy. The myosin11 not only responds to low temperature and low oxygen but may also lead to WG production through Tight junctions. The NG may be more sensitive than WG in stress response to cancer and viral infections.

Risk‐Aware SDN Defense Framework Against Anti‐Honeypot Attacks Using Safe Reinforcement Learning

ABSTRACTThe development of multiple attack methods by external attackers in recent years poses a huge challenge to the security and efficient operation of software‐defined networks (SDN), which are the core of operational controllers and data storage. Therefore, it is critical to ensure that the normal process of network interaction between SDN servers and users is protected from external attacks. In this paper, we propose a risk‐aware SDN defense framework based on safe reinforcement learning (SRL) to counter multiple attack actions. Specifically, the defender uses SRL to maximize the utility by choosing to provide a honeypot service or pseudo‐honeypot service within predefined security constraints, while the external attacker maximizes the utility by choosing an anti‐honeypot attack or masquerade attack. To describe the system risk in detail, we introduce the risk level function to model the simultaneous dynamic attack and defense processes. Simulation results demonstrate that our proposed risk‐aware scheme improves the defense utility by 17.5% and 142.4% and reduces the system risk by 42.7% and 59.6% compared to the QLearning scheme and the Random scheme, respectively.

Crystal structure-mechanical property relationship in succinic acid and L- alanine probed by nanoindentation

Establishing structure–mechanical property relationships is crucial for understanding and engineering the performance of pharmaceutical molecular crystals. In this study, we employed nanoindentation, a powerful technique that can probe mechanical properties at the nanoscale, to investigate the hardness and elastic modulus of single crystals of succinic acid and L-alanine. Nanoindentation results reveal distinct mechanical behaviors between the two compounds, with L-alanine exhibiting significantly higher hardness and elastic modulus compared to succinic acid. These differences are attributed to the underlying variations in molecular crystal structures − the three-dimensional bonding network and high intermolecular interaction energies of L-alanine molecules leads to its stiffness compared to the layered and weakly bonded crystal structure of succinic acid. Furthermore, the anisotropic nature of succinic acid is reflected in the directional dependence of the mechanical responses where it has been found that the (111) plane is more resistant to indentation than (100). By directly correlating the nanomechanical properties obtained from nanoindentation with the detailed crystal structures, this study provides important insights into how differences in molecular arrangements can translate into different macroscopic mechanical performance. These findings have implications on the selection of molecular crystals for optimized drug manufacturability.

Film-forming modifications and mechanistic studies of soybean protein isolate by glycerol plasticization and thermal denaturation: A molecular interaction perspective

Plasticizer and thermal denaturation are indeed important factors for soybean protein film formation. The objective of the study was to investigate the effects of glycerol and thermal denaturation on the film-forming performances of soybean protein isolate (SPI) and elucidate the underlying mechanisms. From the results, glycerol had almost no effect on the protein’s secondary and tertiary structures. Indeed, the dispersion of glycerol diminished the intra- or intermolecular hydrogen bonding of SPI and interacted with the amino acids of subunits through hydrogen bonding and van der Waals forces. By interfering with protein network interactions, the glycerol molecule achieved a plasticizing effect on SPI films. The effects of heat treatment on SPI film properties were mainly realized through the changes in molecular conformation caused by protein denaturation, which manifested in the enhancement of light barrier and mechanical capabilities, and markedly altered the distribution of water states within the film network. This study provided valuable insights to clarify the mechanism of protein film formation.

The Use of Identified Hypoxia-related Genes to Generate Models for Predicting the Prognosis of Cerebral Ischemia‒reperfusion Injury and Developing Treatment Strategies.

Cerebral ischemia‒reperfusion injury (CIRI) is a type of secondary brain damage caused by reperfusion after ischemic stroke due to vascular obstruction. In this study, a CIRI diagnostic model was established by identifying hypoxia-related differentially expressed genes (HRDEGs) in patients with CIRI. The ischemia‒reperfusion injury (IRI)-related datasets were downloaded from the Gene Expression Omnibus (GEO) database ( http://www.ncbi.nlm.nih.gov/geo ), and hypoxia-related genes in the Gene Cards database were identified. After the datasets were combined, hypoxia-related differentially expressed genes (HRDEGs) expressed in CIRI patients were identified. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analyses of the HRDEGs were performed using online tools. Gene set enrichment analysis (GSEA) and gene set variation analysis (GSVA) were performed with the combined gene dataset. CIRI diagnostic models based on HRDEGs were constructed via least absolute shrinkage and selection operator (LASSO) regression analysis and a support vector machine (SVM) algorithm. The efficacy of the 9 identified hub genes for CIRI diagnosis was evaluated via mRNA‒microRNA (miRNA) interaction, mRNA-RNA-binding protein (RBP) network interaction, immune cell infiltration, and receiver operating characteristic (ROC) curve analyses. We then performed logistic regression analysis and constructed logistic regression models based on the expression of the 9 HRDEGs. We next established a nomogram and calibrated the prediction data. Finally, the clinical utility of the constructed logistic regression model was evaluated via decision curve analysis (DCA). This study revealed 9 critical genes with high diagnostic value, offering new insights into the diagnosis and selection of therapeutic targets for patients with CIRI. : Not applicable.

Quantifying the Complexity of Nodes in Higher-Order Networks Using the Infomap Algorithm

Accurately quantifying the complexity of nodes in a network is crucial for revealing their roles and network complexity, as well as predicting network emergent phenomena. In this paper, we propose three novel complexity metrics for nodes to reflect the extent to which they participate in organized, structured interactions in higher-order networks. Our higher-order network is built using the BuildHON+ model, where communities are detected using the Infomap algorithm. Since a physical node may contain one or more higher-order nodes in higher-order networks, it may simultaneously exist in one or more communities. The complexity of a physical node is defined by the number and size of the communities to which it belongs, as well as the number of higher-order nodes it contains within the same community. Empirical flow datasets are used to evaluate the effectiveness of the proposed metrics, and the results demonstrate their efficacy in characterizing node complexity in higher-order networks.

Maintenance of delay-period activity in working memory task is modulated by local network structure.

Revealing the relationship between neural network structure and function is one central theme of neuroscience. In the context of working memory (WM), anatomical data suggested that the topological structure of microcircuits within WM gradient network may differ, and the impact of such structural heterogeneity on WM activity remains unknown. Here, we proposed a spiking neural network model that can replicate the fundamental characteristics of WM: delay-period neural activity involves association cortex but not sensory cortex. First, experimentally observed receptor expression gradient along the WM gradient network is reproduced by our network model. Second, by analyzing the correlation between different local structures and duration of WM activity, we demonstrated that small-worldness, excitation-inhibition balance, and cycle structures play crucial roles in sustaining WM-related activity. To elucidate the relationship between the structure and functionality of neural networks, structural circuit gradients in brain should also be subject to further measurement. Finally, combining anatomical data, we simulated the duration of WM activity across different brain regions, its maintenance relies on the interaction between local and distributed networks. Overall, network structural gradient and interaction between local and distributed networks are of great significance for WM.

Noise-imitation learning: unpaired speckle noise reduction for optical coherence tomography

Objective.Optical coherence tomography (OCT) is widely used in clinical practice for its non-invasive, high-resolution imaging capabilities. However, speckle noise inherent to its low coherence principle can degrade image quality and compromise diagnostic accuracy. While deep learning methods have shown promise in reducing speckle noise, obtaining well-registered image pairs remains challenging, leading to the development of unpaired methods. Despite their potential, existing unpaired methods suffer from redundancy in network structures or interaction mechanisms. Therefore, a more streamlined method for unpaired OCT denoising is essential.Approach.In this work, we propose a novel unpaired method for OCT image denoising, referred to as noise-imitation learning (NIL). NIL comprises three primary modules: the noise extraction module, which extracts noise features by denoising noisy images; the noise imitation module, which synthesizes noisy images and generates fake clean images; and the adversarial learning module, which differentiates between real and fake clean images through adversarial training. The complexity of NIL is significantly lower than that of previous unpaired methods, utilizing only one generator and one discriminator for training.Main results.By efficiently fusing unpaired images and employing adversarial training, NIL can extract more speckle noise information to enhance denoising performance. Building on NIL, we propose an OCT image denoising pipeline, NIL-NAFNet. This pipeline achieved PSNR, SSIM, and RMSE values of 31.27 dB, 0.865, and 7.00, respectively, on the PKU37 dataset. Extensive experiments suggest that our method outperforms state-of-the-art unpaired methods both qualitatively and quantitatively.Significance.These findings indicate that the proposed NIL is a simple yet effective method for unpaired OCT speckle noise reduction. The OCT denoising pipeline based on NIL demonstrates exceptional performance and efficiency. By addressing speckle noise without requiring well-registered image pairs, this method can enhance image quality and diagnostic accuracy in clinical practice.