Information Propagation Research Articles

Source localization in signed networks based on dynamic message passing algorithm

Sign characteristics of social networks play a crucial role in the process of information dissemination, and structural balance theory is a significant property of signed networks. Despite some progress in source localization, the sign features of network structures are widely overlooked. Furthermore, the impact of structural balance on tracing remains unclear. In this paper, we explore a model of information propagation in signed networks and investigate source localization in the context of a given network state snapshot. We first propose a modified signed susceptibility-infection-recovery (S-SIR) propagation model, combining the positive/negative transmission rates based on structural balance theory, which is designed to better approximate the real-world social network structure. Next, a signed dynamic message passing algorithm (S-DMP) is proposed for source localization. Simulation experiments show that the S-DMP algorithm can fully utilize both the positive and negative attributes of the edges in the signed network and outperforms other methods in terms of source localization accuracy. These experiments prove that the proposed method can be used for source localization in the early stage of information transmission. Furthermore, we find that the accuracy of source localization is highest when there is a balance between the number of positive and negative edges.

DMHANT: DropMessage Hypergraph Attention Network for Information Propagation Prediction.

Predicting propagation cascades is crucial for understanding information propagation in social networks. Existing methods always focus on structure or order of infected users in a single cascade sequence, ignoring the global dependencies of cascades and users, which is insufficient to characterize their dynamic interaction preferences. Moreover, existing methods are poor at addressing the problem of model robustness. To address these issues, we propose a predication model named DropMessage Hypergraph Attention Networks, which constructs a hypergraph based on the cascade sequence. Specifically, to dynamically obtain user preferences, we divide the diffusion hypergraph into multiple subgraphs according to the time stamps, develop hypergraph attention networks to explicitly learn complete interactions, and adopt a gated fusion strategy to connect them for user cascade prediction. In addition, a new drop immediately method DropMessage is added to increase the robustness of the model. Experimental results on three real-world datasets indicate that proposed model significantly outperforms the most advanced information propagation prediction model in both MAP@k and Hits@K metrics, and the experiment also proves that the model achieves more significant prediction performance than the existing model under data perturbation.

UPI-LT: Enhancing Information Propagation Predictions in Social Networks Through User Influence and Temporal Dynamics

The TEST pervasive use of social media has highlighted the importance of developing sophisticated models for early information warning systems within online communities. Despite the advancements that have been made, existing models often fail to adequately consider the pivotal role of network topology and temporal dynamics in information dissemination. This results in suboptimal predictions of content propagation patterns. This study introduces the User Propagation Influence-based Linear Threshold (UPI-LT) model, which represents a novel approach to the simulation of information spread. The UPI-LT model introduces an innovative approach to consider the number of active neighboring nodes, incorporating a time decay factor to account for the evolving influence of information over time. The model’s technical innovations include the incorporation of a homophily ratio, which assesses the similarity between users, and a dynamic adjustment of activation thresholds, which reflect a deeper understanding of social influence mechanisms. Empirical results on real-world datasets validate the UPI-LT model’s enhanced predictive capabilities for information spread.

Interweaving Insights: High-Order Feature Interaction for Fine-Grained Visual Recognition

AbstractThis paper presents a novel approach for Fine-Grained Visual Classification (FGVC) by exploring Graph Neural Networks (GNNs) to facilitate high-order feature interactions, with a specific focus on constructing both inter- and intra-region graphs. Unlike previous FGVC techniques that often isolate global and local features, our method combines both features seamlessly during learning via graphs. Inter-region graphs capture long-range dependencies to recognize global patterns, while intra-region graphs delve into finer details within specific regions of an object by exploring high-dimensional convolutional features. A key innovation is the use of shared GNNs with an attention mechanism coupled with the Approximate Personalized Propagation of Neural Predictions (APPNP) message-passing algorithm, enhancing information propagation efficiency for better discriminability and simplifying the model architecture for computational efficiency. Additionally, the introduction of residual connections improves performance and training stability. Comprehensive experiments showcase state-of-the-art results on benchmark FGVC datasets, affirming the efficacy of our approach. This work underscores the potential of GNN in modeling high-level feature interactions, distinguishing it from previous FGVC methods that typically focus on singular aspects of feature representation. Our source code is available at https://github.com/Arindam-1991/I2-HOFI.

The Role of Public Figures amidst Indonesia’s Early Social Restrictions Policy on Twitter (X): A Social Network Analysis

The Government of Indonesia implemented large-scale social restrictions (Indonesian: Pembatasan Sosial Berskala Besar, abbreviated as PSBB) following the first confirmed cases of COVID-19. Due to social media role in information propagation, this decision quickly became a trending topic on Twitter. This study investigates the main actors and the dynamics of these discussions surrounding PSBB. Utilizing RStudio software, tweets containing the keyword „psbb“ and the hashtag #psbb were mined as of May 6, 2020. The data were analyzed and compared with research conducted during May 2020. Key findings include the significant role of the musician Fiersa Besari in shaping discussions about social restrictions, the emergence of seven major opinion leaders, and the prominence of online news outlets like detikcom and CNN Indonesia in the conversation. Additionally, the study highlights critical commentary from actors affiliated with the Democratic Faction of the Indonesian House of Representatives regarding the government‘s social restrictions policies. These findings provide insights into the network dynamics and public opinion on social restrictions during the early social restrictions policy in Indonesia.

Border Gateway Protocol Route Leak Detection Technique Based on Graph Features and Machine Learning

In the Internet, ASs are interconnected using BGP. However, due to a lack of security considerations in the design of BGP, a series of security issues arise during the propagation of routing information, such as prefix hijacking, route leakage, and AS path tampering. Therefore, this paper conducts research on the detection of route leakage. By analyzing BGP routing information, we abstract the routing propagation relationship between ASs into a network topology graph, and extract graph features from the graph abstracted from routing data at certain time intervals. Based on the structural robustness features and centrality measurement features of the graph, we determine whether a route leakage has occurred during the current time period. To this end, we use machine learning methods and propose a weighted voting model. This model trains multiple single models and assigns weights to them, and through the weighted analysis of the results of multiple models, it can determine whether a route leakage has occurred. In addition, to determine the corresponding weights, we use genetic algorithms for identifying route leaks. The experimental results show that the method used in this paper has a high accuracy rate, and compared with a single model, it performs better on multiple datasets.

Influence maximization based on discrete particle swarm optimization on multilayer network

Influence maximization (IM) aims to strategically select influential users to maximize information propagation in social networks. Most of the existing studies focus on IM in single-layer networks. However, we have observed that individuals often engage in multiple social platforms to fulfill various social needs. To make better use of this observation, we consider an extended problem of how to maximize influence spread in multilayer networks. The Multilayer Influence Maximization (MLIM) problem is different from the IM problem because information propagation behaves differently in multilayer networks compared to single-layer networks: users influenced on one layer may trigger the propagation of information on another layer. Our work successfully models the information propagation process as a Multilayer Independent Cascade model in multilayer networks. Based on the characteristics of this model, we introduce an approximation function called Multilayer Expected Diffusion Value (MLEDV) for it. However, the NP-hardness of the MLIM problem has posed significant challenges to our work. To tackle the issue, we devise a novel algorithm based on Discrete Particle Swarm Optimization. Our algorithm consists of two stages: 1) the candidate node selection, where we devise a novel centrality metric called Random connectivity Centrality to select candidate nodes, which assesses the importance of nodes from a connectivity perspective. 2)the seed selection, where we employ a discrete particle swarm algorithm to find seed nodes from the candidate nodes. We use MLEDV as a fitness function to measure the spreading power of candidate solutions in our algorithm. Additionally, we introduce a Neighborhood Optimization strategy to increase the convergence of the algorithm. We conduct experiments on four real-world networks and two self-built networks and demonstrate that our algorithms are effective for the MLIM problem.

Higher-order network information propagation model based on social impact theory

User relationships are becoming increasingly diverse in current online social networks. This paper utilizes simplicial complexes in higher-order networks to depict multiple user relationships and characterize the topology of social networks. By employing social impact theory and factors such as user interest and information aging to define state transition rules among users, we establish a UAPR information propagation model based on simplicial complexes to simulate the information propagation process in higher-order social networks. The proposed model is simulated on three types of synthetic networks and four real-world simplicial complexes, demonstrating its ability to accurately describe the dynamics and influences of information propagation. Furthermore, our results indicate that different network structures, user interest values, information aging speeds, and intimacy levels significantly influence the information transmission process.

A lighter hybrid feature fusion framework for polyp segmentation

Colonoscopy is widely recognized as the most effective method for the detection of colon polyps, which is crucial for early screening of colorectal cancer. Polyp identification and segmentation in colonoscopy images require specialized medical knowledge and are often labor-intensive and expensive. Deep learning provides an intelligent and efficient approach for polyp segmentation. However, the variability in polyp size and the heterogeneity of polyp boundaries and interiors pose challenges for accurate segmentation. Currently, Transformer-based methods have become a mainstream trend for polyp segmentation. However, these methods tend to overlook local details due to the inherent characteristics of Transformer, leading to inferior results. Moreover, the computational burden brought by self-attention mechanisms hinders the practical application of these models. To address these issues, we propose a novel CNN-Transformer hybrid model for polyp segmentation (CTHP). CTHP combines the strengths of CNN, which excels at modeling local information, and Transformer, which excels at modeling global semantics, to enhance segmentation accuracy. We transform the self-attention computation over the entire feature map into the width and height directions, significantly improving computational efficiency. Additionally, we design a new information propagation module and introduce additional positional bias coefficients during the attention computation process, which reduces the dispersal of information introduced by deep and mixed feature fusion in the Transformer. Extensive experimental results demonstrate that our proposed model achieves state-of-the-art performance on multiple benchmark datasets for polyp segmentation. Furthermore, cross-domain generalization experiments show that our model exhibits excellent generalization performance.

CDAN: Convolutional dense attention-guided network for low-light image enhancement

Low-light images, characterized by inadequate illumination, pose challenges of diminished clarity, muted colors, and reduced details. Low-light image enhancement, an essential task in computer vision, aims to rectify these issues by improving brightness, contrast, and overall perceptual quality, thereby facilitating accurate analysis and interpretation. This paper introduces the Convolutional Dense Attention-guided Network (CDAN), a novel solution for enhancing low-light images. CDAN integrates an autoencoder-based architecture with convolutional and dense blocks, complemented by an attention mechanism and skip connections. This architecture ensures efficient information propagation and feature learning. During training, we utilize a composite loss function that merges L2 and VGG losses for improved numeric and perceptual results. Furthermore, a dedicated post-processing phase refines color balance and contrast. Our approach demonstrates notable progress compared to state-of-the-art results in low-light image enhancement, showcasing its robustness across a wide range of challenging scenarios. Our model performs remarkably on benchmark datasets, effectively mitigating under-exposure and proficiently restoring textures and colors in diverse low-light scenarios. This achievement underscores CDAN's potential for diverse computer vision tasks, notably enabling robust object detection and recognition in challenging low-light conditions.

Vul-LMGNNs: Fusing language models and online-distilled graph neural networks for code vulnerability detection

Code Language Models (codeLMs) and Graph Neural Networks (GNNs) are widely used in code vulnerability detection. However, a critical yet often overlooked issue is that GNNs primarily rely on aggregating information from adjacent nodes, limiting structural information transfer to single-layer updates. In code graphs, nodes and relationships typically require cross-layer information propagation to fully capture complex program logic and potential vulnerability patterns. Furthermore, while some studies utilize codeLMs to supplement GNNs with code semantic information, existing integration methods have not fully explored the potential of their collaborative effects.To address these challenges, we introduce Vul-LMGNNs that integrates pre-trained CodeLMs with GNNs, leveraging knowledge distillation to facilitate cross-layer propagation of both code semantic knowledge and structural information. Specifically, Vul-LMGNNs utilizes Code Property Graphs (CPGs) to incorporate code syntax, control flow, and data dependencies, while employing gated GNNs to extract structural information in the CPG. To achieve cross-layer information transmission, we implement an online knowledge distillation (KD) program that enables a single student GNN to acquire structural information extracted from a simultaneously trained counterpart through an alternating training procedure. Additionally, we leverage pre-trained CodeLMs to extract semantic features from code sequences. Finally, we propose an ”implicit-explicit” joint training framework to better leverage the strengths of both CodeLMs and GNNs. In the implicit phase, we utilize CodeLMs to initialize the node embeddings of each student GNN. Through online knowledge distillation, we facilitate the propagation of both code semantics and structural information across layers. In the explicit phase, we perform linear interpolation between the CodeLM and the distilled GNN to learn a late fusion model. The proposed method, evaluated across four real-world vulnerability datasets, demonstrated superior performance compared to 17 state-of-the-art approaches. Our source code can be accessed via GitHub: https://github.com/Vul-LMGNN/vul-LMGGNN.

Rumor Detection With Hierarchical Representation on Bipartite Ad Hoc Event Trees.

The rapid growth of social media has caused tremendous effects on information propagation, raising extreme challenges in detecting rumors. Existing rumor detection methods typically exploit the reposting propagation of a rumor candidate for detection by regarding all reposts to a rumor candidate as a temporal sequence and learning semantics representations of the repost sequence. However, extracting informative support from the topological structure of propagation and the influence of reposting authors for debunking rumors is crucial, which generally has not been well addressed by existing methods. In this article, we organize a claim post in circulation as an ad hoc event tree, extract event elements, and convert it into bipartite ad hoc event trees in terms of both posts and authors, i.e., author tree and post tree. Accordingly, we propose a novel rumor detection model with hierarchical representation on the bipartite ad hoc event trees called BAET. Specifically, we introduce word embedding and feature encoder for the author and post tree, respectively, and design a root-aware attention module to perform node representation. Then we adopt the tree-like RNN model to capture the structural correlations and propose a tree-aware attention module to learn tree representation for the author tree and post tree, respectively. Extensive experimental results on two public Twitter datasets demonstrate the effectiveness of BAET in exploring and exploiting the rumor propagation structure and the superior detection performance of BAET over state-of-the-art baseline methods.

Spatial context non-uniformly modulates inter-laminar information flow in the primary visual cortex.

Our visual experience is a result of the concerted activity of neuronal ensembles in the sensory hierarchy. Yet, how the spatial organization of objects influences this activity remains poorly understood. We investigate how inter-laminar information flow within the primary visual cortex (V1) is affected by visual stimuli in isolation or with flankers at spatial configurations that are known to cause non-uniform degradation of perception. By employing dimensionality reduction approaches to simultaneous, layer-specific population recordings, we establish that information propagation between cortical layers occurs along a structurally stable communication subspace. The spatial configuration of contextual stimuli differentially modulates inter-laminar communication efficacy, the balance of feedforward and effective feedback signaling, and contextual signaling in the superficial layers. Remarkably, these modulations mirror the spatially non-uniform aspects of perceptual degradation. Our results suggest a model of retinotopically non-uniform cortical connectivity in the output layers of V1 that influences information flow in the sensory hierarchy.

Adaptive multi-graph contrastive learning for bundle recommendation

Recently, recommending bundles - sets of items that complement each other - instead of individual items to users has drawn much attention in both academia and industry. Models based on Graph Neural Networks (GNNs) for bundle recommendation have achieved great success in capturing users’ preferences by modeling pairwise correlations among users, bundles, and items via information propagation on graphs. However, a notable limitation lies in their insufficient focus on explicitly modeling intricate ternary relationships. Additionally, the loose combination of node embeddings from different graphs tends to introduce noise, as it fails to consider disparities among the graphs. To this end, we propose a novel approach called Adaptive Multi-Graph Contrastive Learning for Bundle Recommendation (AMCBR). Specifically, AMCBR models ternary interactions by constructing multiple graphs, including a bundle preference graph based on direct user-bundle interactions, a collaborative neighborhoods graph featuring user-level and bundle-level subgraphs, and an item-level preference hypergraph capturing indirect user-bundle relationships through items. Then, (hyper)graph convolution is applied to each (hyper)graph to encode diverse potential preferences into node embeddings. To enhance the model’s robustness, an adaptive aggregation module is employed to assign varying weights to node embeddings from different graphs during the fusion process, which enriches the semantic and comprehensive information in the embeddings while mitigating potential noise. Finally, a contrastive learning strategy is proposed to jointly optimize the model, strengthening collaborative links between individual graphs. Extensive experiments on three real datasets demonstrate that AMCBR can outperform the state-of-the-art baselines on the Top-K recommendations.

Research on the characteristics of information propagation dynamic on the weighted multiplex Weibo networks

In order to simulate the forwarding situation of different categories of Weibo and discover interesting propagation phenomena in different layers of Weibo networks, this paper proposes the retweeting weighted multiplex networks and propagation model coupled with multi-class Weibo. Firstly, the weighted multiplex social network is constructed through the processing of Weibo network data. Secondly, a new information propagation model is established by using the weight and interlayer information of the Weibo multiplex network combined with the coupling factors in the propagation. Finally, the information propagation simulated by the propagation model is compared with the real data, so as to summarize different information propagation phenomena in multiplex social multiplex network. At the same time, by comparing the structure of the forwarding weighted multiplex network constructed by the short time data and the long time data, we find the self-similarity of the forwarding weighted multiplex network, which proves the generalization of the experiment. Through the above research, the mystery of the Weibo social network has been deeply explored, and a new perspective has been opened up for the exploration of social media information propagation.

RAM-YOLOv8: A multi-fault detection method for photovoltaic module

ABSTRACT Given the constraints in fault type identification, localization precision, and detection efficiency inherent in current photovoltaic fault detection methodologies, this paper introduces an innovative detection approach integrating RAM-YOLOv8 with the Swin Transformer. To mitigate the limitations in model extraction capabilities during the detection process and circumvent the vanishing gradient issue encountered during backward information propagation, this study introduces a residual aggregation module as a substitute for the original C2F module, thereby augmenting feature extraction efficiency. Furthermore, within the feature fusion network, the Swin attention mechanism fusion module is designed by integrating the Swin Transformer’s architectural concept to minimize the loss of weak defect information and suppress irrelevant background interference. The model achieves a detection accuracy of 88.5% on the dataset, representing a 7% improvement over the original YOLOv8 algorithm, with a detection rate of 83.33 FPS on an RTX2080 GPU. This method offers a robust and efficient fault detection solution for PV systems, rendering it a practical approach for enhancing system performance and reducing maintenance costs.

Revisiting elastic string models of forward interest rates

Twenty five years ago, several authors proposed to describe the forward interest rate curve (FRC) as an elastic string along which idiosyncratic shocks propagate, accounting for the peculiar structure of the return correlation across different maturities. In this paper, we revisit the specific ‘stiff’ elastic string field theory of Baaquie and Bouchaud [Stiff field theory of interest rates and psychological future time. Wilmott Mag., 2004, 2–6] in a way that makes its micro-foundation more transparent. Our model can be interpreted as capturing the effect of market forces that set the rates of nearby tenors in a self-referential fashion. The model is parsimonious and accurately reproduces the whole correlation structure of the FRC over the time period 1994–2023, with an error around 1% and with only one adjustable parameter, the value of which being very stable across the last three decades. The dependence of correlation on time resolution (also called the Epps effect) is also faithfully reproduced within the model and leads to a cross-tenor information propagation time on the order of 30 minutes. Finally, we confirm that the perceived time in interest rate markets is a strongly sub-linear function of real time, as surmised by Baaquie and Bouchaud [Stiff field theory of interest rates and psychological future time. Wilmott Mag., 2004, 2–6]. In fact, our results are fully compatible with hyperbolic discounting, in line with the recent behavioral Finance literature Farmer and Geanakoplos [Hyperbolic Discounting is Rational: Valuing the Far Future with Uncertain Discount Rates, Cowles Foundation Discussion Papers, 2009 (Cowles Foundation for Research in Economics, Yale University)].

A graph network-based learnable simulator for spatial-temporal prediction of rigid projectile penetration

Predicting plate penetration by rigid projectiles (PPRP) is crucial in terminal ballistics, with broad applications in civil and military engineering. Empirical and analytical methods face challenges in predicting field variables like displacement and stress in target plates. Although numerical methods offer high accuracy, they suffer from low computational efficiency. Herein, we introduce an efficient data-driven machine learning (ML) method based on graph neural networks (GNNs), named PGN, specifically tailored to address the PPRP problem. Unlike traditional ML methods that establish direct input-output mappings, PGN predicts comprehensive spatial-temporal information pertaining to the projectile-target interaction process. A thorough analysis of PGN's performance in terms of accuracy, computational efficiency and generalization ability was performed. Compared to validated results of numerical simulations, PGN maintained high precision with RMSE for displacement, stress, and strain predictions below 0.5 %, 9.5 %, and 2.1 %, respectively. It also achieved R2 values exceeding 0.92 for the time history of projectile velocity and acceleration, while requiring only 9.8 % of the computation time compared to LS-DYNA. In generalization tests, PGN exhibited remarkable adaptability in tackling challenging scenarios that extend far beyond the training data distribution, with overall RMSE between 11 % and 13 %. Furthermore, we find that the maximum information propagation capacity of a simulated physical system must meet or exceed the information propagation need of the real-world physical phenomenon it aims to replicate. Consequently, an approach was proposed to determine the critical connectivity radius of the massage passing method directly from the wave speed in the target medium, which greatly improved the accuracy and efficiency of PGN.

ES-GNN: Generalizing Graph Neural Networks Beyond Homophily With Edge Splitting.

While Graph Neural Networks (GNNs) have achieved enormous success in multiple graph analytical tasks, modern variants mostly rely on the strong inductive bias of homophily. However, real-world networks typically exhibit both homophilic and heterophilic linking patterns, wherein adjacent nodes may share dissimilar attributes and distinct labels. Therefore, GNNs smoothing node proximity holistically may aggregate both task-relevant and irrelevant (even harmful) information, limiting their ability to generalize to heterophilic graphs and potentially causing non-robustness. In this work, we propose a novel Edge Splitting GNN (ES-GNN) framework to adaptively distinguish between graph edges either relevant or irrelevant to learning tasks. This essentially transfers the original graph into two subgraphs with the same node set but complementary edge sets dynamically. Given that, information propagation separately on these subgraphs and edge splitting are alternatively conducted, thus disentangling the task-relevant and irrelevant features. Theoretically, we show that our ES-GNN can be regarded as a solution to a disentangled graph denoising problem, which further illustrates our motivations and interprets the improved generalization beyond homophily. Extensive experiments over 11 benchmark and 1 synthetic datasets not only demonstrate the effective performance of ES-GNN but also highlight its robustness to adversarial graphs and mitigation of the over-smoothing problem.

Using Multi-Encoder Semi-Implicit Graph Variational Autoencoder to Analyze Single-Cell RNA Sequencing Data.

Rapid advances in single-cell RNA sequencing (scRNA-seq) have made it possible to characterize cell states at a high resolution view for large scale library. scRNA-seq data contains a great deal of biological information, which can be mainly used to discover cell subtypes and track cell development. However, traditional methods face many challenges in addressing scRNA-seq data with high dimensions and high sparsity. For better analysis of scRNA-seq data, we propose a new framework called MSVGAE based on variational graph auto-encoder and graph attention networks. Specifically, we introduce multiple encoders to learn features at different scales and control for uninformative features. Moreover, different noises are added to encoders to promote the propagation of graph structural information and distribution uncertainty. Therefore, some complex posterior distributions can be captured by our model. MSVGAE maps scRNA-seq data with high dimensions and high noise into the low-dimensional latent space, which is beneficial for downstream tasks. In particular, MSVGAE can handle extremely sparse data. Before the experiment, we create 24 simulated datasets to simulate various biological scenarios and collect 8 real-world datasets. The experimental results of clustering, visualization and marker genes analysis indicate that MSVGAE model has excellent accuracy and robustness in analyzing scRNA-seq data.