Node Representations Research Articles

ClusterLP: A novel Cluster-aware Link Prediction model in undirected and directed graphs

Link prediction models endeavor to understand the distribution of links within graphs and forecast the presence of potential links. With the advancements in deep learning, prevailing methods typically strive to acquire low-dimensional representations of nodes in networks, aiming to capture and retain the structure and inherent characteristics of networks. However, the majority of these methods primarily focus on preserving the microscopic structure, such as the first- and second-order proximities of nodes, while largely disregarding the mesoscopic cluster structure, which stands out as one of the network's most prominent features. Following the homophily principle, nodes within the same cluster exhibit greater similarity to each other compared to those from different clusters, suggesting that they should possess analogous vertex representations and higher probabilities of linkage. In this study, we develop a straightforward yet efficient Cluster-aware Link Prediction framework (ClusterLP), with the objective of directly leveraging cluster structures to predict links among nodes with maximum accuracy in both undirected and directed graphs. Specifically, we posit that establishing links between nodes with similar representation vectors and cluster tendencies is more feasible in undirected graphs, whereas nodes in directed graphs are inclined to point towards nodes with akin representation vectors and greater influence. We tailor the implementation of ClusterLP for undirected and directed graphs, respectively, and experimental findings using multiple real-world networks demonstrate the high competitiveness of our models in the realm of link prediction tasks. The code utilized in our implementation is accessible at https://github.com/ZINUX1998/ClusterLP.

RepFTI: Representation-Fused Function-Type Inference for Vehicular Secure Software Systems

To enhance the security of vehicular software systems, inversely identifying the underlying function types of binary files plays a key role in threat discovery. However, existing function-type inference (FTI) methods can only provide a suboptimal performance because of splitting binary files into multiple sub-blocks as inputs, which results in breaking the program context logic and complete data dependency. To solve this problem, we propose a novel representation-fused function-type inference (RepFTI) framework for secure vehicular software systems. First, the RepFTI learns semantic representations of assembly codes and then extracts node representations in the function call graph by the multi-head attention mechanism of Graph-Attention Transformer (GAT) models. Second, the RepFTI fuses these representations to accurately infer the function type. With RepFTI, the specific limits of in-vehicle software will be bypassed, which proposes a promising direction for other work that relies on reverse engineering to improve software security.

Developing explainable models for lncRNA-Targeted drug discovery using graph autoencoders

The application of explainable artificial intelligence technology is crucial in lncRNA-targeted drug discovery, given lncRNA’s role in regulating a broad spectrum of diseases, including cancer. Current advanced deep learning models efficiently predict the association between lncRNA and disease, facilitating the discovery of potential lncRNA-targeted drug. However, these models have notable limitations, including a tendency to overfit due to their focus on integrating various similarity networks for feature extraction of lncRNA and diseases. Additionally, they employ complex classifiers to predict unknown lncRNA-disease associations (LDAs), resulting in reduced interpretability. We designed an explainable model named EM-LTDD, utilizing graph autoencoders (GAE) and self-supervised learning strategies, aimed at identifying potential drugs targeting lncRNA. The EM-LTDD model improves self-supervised training by employing a novel strategy that masks parts of the known lncRNA-disease network. This approach not only enhances the model’s interpretability but also mitigates the impact of noise. Furthermore, the EM-LTDD model reconstructs the lncRNA-disease network with a robust collaborative decoder, minimizing information loss caused by occlusion and improving node representation. Experimental results demonstrate the effectiveness of our model compared to existing leading models, promising to significantly aid in the discovery and design of lncRNA-targeted drugs. Our code and data are available at: https://github.com/huiyingliulevy/EM-LTDD.

IMNE: Maximizing influence through deep learning-based node embedding in social network

Influence Maximization (IM) is a critical problem in social network analysis and marketing. It involves identifying a subset of nodes in a social network whose activation or influence can lead to the maximal spread of information, ideas, or behaviors within the network. Although many approaches have been developed in the literature to deal with this problem, most of these approaches are ineffective in dealing with large-scale social networks due to free parameters and computational complexity. Embeddings are used to learn low-dimensional representations of nodes in a social network. These embeddings capture the structural and semantic information of nodes and their relationships within the network. By training deep learning models on graph-structured data, node embeddings can capture complex patterns and dependencies in social networks, enabling more effective downstream tasks such as IM. Accordingly, this paper proposes an efficient algorithm to address the IM problem in social networks using deep learning-based Node Embedding (IMNE), which includes shell decomposition, graph/node embedding, and search space reduction as well as the use of local structural features. Our approach combines the power of deep learning for representation learning with the rich structural information present in social networks to address the challenge of IM in complex and dynamic social networks. IMNE uses the Independent Cascade (IC) information diffusion model to determine the labels needed to train the model by calculating the influence of nodes. Experimental results on several real-world networks considering different performance metrics show that IMNE performs better compared to existing baseline and state-of-the-art methods.

Node classification in complex networks based on multi-view debiased contrastive learning

In complex networks, contrastive learning has emerged as a crucial technique for acquiring discriminative representations from graph data. Maximizing the similarity among relevant sample pairs while minimizing that among irrelevant pairs is pivotal in contrastive learning. Therefore, careful consideration must be given to the design of sample pairs in contrastive learning. However, existing node-level self-supervised contrastive learning often treats the enhanced representation of a central node as a positive sample, while considering representations of all other nodes as negative samples. This approach can lead to conflicts in downstream tasks on some graph data, as nodes of the same class are treated as negatives during learning. Precision in sample pair design is essential for enhancing the performance of contrastive learning. To address this issue, this paper introduces a negative sample debiased sampling contrastive learning (NDSCL), specifically tailored for node classification tasks. In particular, this method integrates contrastive learning with semi-supervised learning. A trained classifier assigns pseudo-labels to unlabeled data, and debiased sampling is applied to negative samples. Unlike other methods that focus on negative sample selection, NDSCL also addresses the imbalance in pseudo-label distribution by employing debiasing techniques. Finally, in conjunction with diffusion augmentation, the model is provided with diverse views as inputs to maximize the retention of underlying semantic information. Experimental results demonstrate that the proposed model significantly outperforms baseline models in node-level classification tasks across multiple network datasets. Moreover, the model not only enhances accuracy but also improves computational speed and memory requirements for handling large-scale graph data structures.

KNN-GNN: A powerful graph neural network enhanced by aggregating K-nearest neighbors in common subspace

It has been proven that graph neural networks (GNNs) are effective for a variety of graph learning-based applications. Typical GNNs iteratively aggregate messages from immediate neighbors under the homophily assumption. However, there are a larger number of heterophilous networks in our daily life, where the ability of these GNNs is limited. Recently, some GNN models have been proposed to handle networks with heterophily via some key designs like aggregating higher-order neighbors and combining immediate representations. But ”noise” information transmitted from different-order neighbors will be injected into the representations of nodes. In this paper, we propose a new GNN model, called KNN-GNN, to effectively perform the node classification task for networks with various homophily levels. The main idea of KNN-GNN is to learn a comprehensive and accurate representation for each node by integrating not only the local information from its neighborhood but also the non-local information held by its similar nodes decentralized in the network. Specifically, the local information of a node is generated from itself and its 1-hop neighbor. Then, we project all nodes into a common subspace, where similar nodes are desired to be close to each other. The non-local information of a node is gathered by aggregating its K-Nearest Neighbors searched in the common subspace. We evaluate the performance of KNN-GNN on both real and synthetic datasets including networks with diverse homophily levels. The results demonstrate that KNN-GNN outstrips the state-of-the-art baselines. Moreover, the ablation experiments show that the core designs in KNN-GNN play a critical role in node representation learning.

Three-way graph convolutional network for multi-label classification in multi-label information system

The Graph Convolutional Neural Networks (GCNs) have demonstrated a powerful capacity for relation processing. To improve the representation learning capability of GCNs, numerous studies have begun to excavate latent topological graphs based on node features, aiming to obtain richer representations of nodes. However, these graph mining methods based on global metrics, such as Euclidean distance, lack descriptions of uncertainty and fine granularity, leading to the loss of structural information, which affects the final representation of nodes. Therefore, this paper proposes the Three-way Graph Convolutional Neural Network (TW-GCN), which is based on multi-granularity and three-way decision. First, from the perspective of multi-granularity, each attribute is analyzed as a granule, and we establish relations of advantage, disadvantage, and uncertainty for objects under each attribute granule. Three-way relation captures the complex connections between nodes from multiple perspectives, improves the comprehensive understanding of graph data, and avoids the information loss caused by traditional two-way processing. Second, a three-way graph convolutional layer is constructed to capture uncertainty and ambiguity by performing graph convolution on different topological graphs. The final node representation is obtained through message passing on the node’s neighbor graph, which considers not only the global structure, but also effectively captures local structural features. Finally, we employ the TW-GCN for multi-label classification within information systems to validate the model’s validity based on multiple indicators.

Quintuple-based Representation Learning for Bipartite Heterogeneous Networks

Recent years have seen rapid progress in network representation learning, which removes the need for burdensome feature engineering and facilitates downstream network-based tasks. In reality, networks often exhibit heterogeneity, which means there may exist multiple types of nodes and interactions. Heterogeneous networks raise new challenges to representation learning, as the awareness of node and edge types is required. In this article, we study a basic building block of general heterogeneous networks, the heterogeneous networks with two types of nodes. Many problems can be solved by decomposing general heterogeneous networks into multiple bipartite ones. Recently, to overcome the demerits of non-metric measures used in the embedding space, metric learning-based approaches have been leveraged to tackle heterogeneous network representation learning. These approaches first generate triplets of samples, in which an anchor node, a positive counterpart, and a negative one co-exist, and then try to pull closer positive samples and push away negative ones. However, when dealing with heterogeneous networks, even the simplest two-typed ones, triplets cannot simultaneously involve both positive and negative samples from different parts of networks. To address this incompatibility of triplet-based metric learning, in this article, we propose a novel quintuple-based method for learning node representations in bipartite heterogeneous networks. Specifically, we generate quintuples that contain positive and negative samples from two different parts of networks. And we formulate two learning objectives that accommodate quintuple-based learning samples, a proximity-based loss that models the relations in quintuples by sigmoid probabilities and an angular loss that more robustly maintains similarity structures. In addition, we also parameterize feature learning by using one-dimensional convolution operators around nodes’ neighborhoods. Compared with eight methods, extensive experiments on two downstream tasks manifest the effectiveness of our approach.

Self-supervised Bipartite Graph Representation Learning: A Dirichlet Max-margin Matrix Factorization Approach

Bipartite graph representation learning aims to obtain node embeddings by compressing sparse vectorized representations of interactions between two types of nodes, e.g., users and items. Incorporating structural attributes among homogeneous nodes, such as user communities, improves the identification of similar interaction preferences, namely, user/item embeddings, for downstream tasks. However, existing methods often fail to proactively discover and fully utilize these latent structural attributes. Moreover, the manual collection and labeling of structural attributes is always costly. In this article, we propose a novel approach called Dirichlet Max-margin Matrix Factorization (DM3F), which adopts a self-supervised strategy to discover latent structural attributes and model discriminative node representations. Specifically, in self-supervised learning, our approach generates pseudo group labels (i.e., structural attributes) as a supervised signal using the Dirichlet process without relying on manual collection and labeling, and employs them in a max-margin classification. Additionally, we introduce a Variational Markov Chain Monte Carlo algorithm (Variational MCMC) to effectively update the parameters. The experimental results on six real datasets demonstrate that, in the majority of cases, the proposed method outperforms existing approaches based on matrix factorization and neural networks. Furthermore, the modularity analysis confirms the effectiveness of our model in capturing structural attributes to produce high-quality user embeddings.

Dispelling the Fake: Social Bot Detection Based on Edge Confidence Evaluation.

Social bot detection is essential for maintaining the safety and integrity of online social networks (OSNs). Graph neural networks (GNNs) have emerged as a promising solution. Mainstream GNN-based social bot detection methods learn rich user representations by recursively performing message passing along user-user interaction edges, where users are treated as nodes and their relationships as edges. However, these methods face challenges when detecting advanced bots interacting with genuine accounts. Interaction with real accounts results in the graph structure containing camouflaged and unreliable edges. These unreliable edges interfere with the differentiation between bot and human representations, and the iterative graph encoding process amplifies this unreliability. In this article, we propose a social Bot detection method based on Edge Confidence Evaluation (BECE). Our model incorporates an edge confidence evaluation module that assesses the reliability of the edges and identifies the unreliable edges. Specifically, we design features for edges based on the representation of user nodes and introduce parameterized Gaussian distributions to map the edge embeddings into a latent semantic space. We optimize these embeddings by minimizing Kullback-Leibler (KL) divergence from the standard distribution and evaluate their confidence based on edge representation. Experimental results on three real-world datasets demonstrate that BECE is effective and superior in social bot detection. Additionally, experimental results on six widely used GNN architectures demonstrate that our proposed edge confidence evaluation module can be used as a plug-in to improve detection performance.

Protein features fusion using attributed network embedding for predicting protein-protein interaction

BackgroundProtein-protein interactions (PPIs) hold significant importance in biology, with precise PPI prediction as a pivotal factor in comprehending cellular processes and facilitating drug design. However, experimental determination of PPIs is laborious, time-consuming, and often constrained by technical limitations.MethodsWe introduce a new node representation method based on initial information fusion, called FFANE, which amalgamates PPI networks and protein sequence data to enhance the precision of PPIs’ prediction. A Gaussian kernel similarity matrix is initially established by leveraging protein structural resemblances. Concurrently, protein sequence similarities are gauged using the Levenshtein distance, enabling the capture of diverse protein attributes. Subsequently, to construct an initial information matrix, these two feature matrices are merged by employing weighted fusion to achieve an organic amalgamation of structural and sequence details. To gain a more profound understanding of the amalgamated features, a Stacked Autoencoder (SAE) is employed for encoding learning, thereby yielding more representative feature representations. Ultimately, classification models are trained to predict PPIs by using the well-learned fusion feature.ResultsWhen employing 5-fold cross-validation experiments on SVM, our proposed method achieved average accuracies of 94.28%, 97.69%, and 84.05% in terms of Saccharomyces cerevisiae, Homo sapiens, and Helicobacter pylori datasets, respectively.ConclusionExperimental findings across various authentic datasets validate the efficacy and superiority of this fusion feature representation approach, underscoring its potential value in bioinformatics.

A Construction Method for a Dynamic Weighted Protein Network Using Multi-Level Embedding

The rapid development of high-throughput technology has generated a large amount of protein–protein interaction (PPI) data, which provide a large amount of data support for constructing dynamic protein–protein interaction networks (PPINs). Constructing dynamic PPINs and applying them to recognize protein complexes has become a hot research topic. Most existing methods for complex recognition cannot fully mine the information of PPINs. To address this problem, we propose a construction method of dynamic weighted protein network by multi-level embedding (DWPNMLE). It can reflect the protein network’s dynamics and the protein network’s higher-order proximity. Firstly, the protein active period is calculated to divide the protein subnetworks at different time points. Then, the connection probability is used for the proteins possessing the same time points to judge whether there is an interaction relationship between them. Then, the corresponding protein subnetworks (multiple adjacency matrices) are constructed. Secondly, the multiple feature matrices are constructed using one-hot coding with the gene ontology (GO) information. Next, the first embedding is performed using variational graph auto-encoders (VGAEs) to aggregate features efficiently, followed by the second embedding using deep attributed network embedding (DANE) to strengthen the node representations learned in the first embedding and to maintain the first-order and higher-order proximity of the original network; finally, we compute the cosine similarity to obtain the final dynamic weighted PPIN. To evaluate the effectiveness of DWPNMLE, we apply four classical protein-complex-recognition algorithms on the DWPNMLE and compare them with two other dynamic protein network construction methods. The experimental results demonstrate that DWPNMLE significantly enhances the accuracy of complex recognition with high robustness, and the algorithms’ efficiency is also within a reasonable range.

GA-GGD: Improving semantic discriminability in graph contrastive learning via Generative Adversarial Network

Graph contrastive learning has garnered considerable research interest due to its ability to effectively embed graph data without manual labels. Among them, methods based on Deep Graph Infomax (DGI) have been widely studied and favored in the industry because of their fast training speed, applicability to large-scale data. DGI-based methods usually obtain a noise graph through node shuffling. The proxy task of these methods encourages the encoder to distinguish whether the nodes come from the original graph or the noise graph, thereby maximizing the mutual information between the node representation and the graph it belongs to, while also maximizing the Jenson–Shannon divergence between the nodes of original graph and noise graph. However, we argue that these approaches only enable the encoder to differentiate between semantically meaningful graphs and noise graphs, but not to effectively identify different semantic graphs. This leads to the inability of the encoder to effectively embed information between different semantics, significantly reducing the robustness and affecting the performance of downstream tasks. In addition, this training mode makes the model more sensitive to attacks. To improve their semantic discriminability, we take advantage of the natural ability of generative adversarial networks to generate semantic data, proposing a method called Generative Adversarial Graph Group Discrimination (GA-GGD). Specifically, it consists of a graph group discriminator and a semantic attack generator. The discriminator aims to encode the graph and identify whether nodes originate from the original graph. The goal of the generator is to use random features and graph structure to find vulnerabilities of discriminator and generate node representations with similar but wrong semantic to confuse the discriminator. GA-GGD can improve the model’s semantic information embedding without significantly increasing computational overhead and memory occupancy. We test the effectiveness of the proposed model on commonly used data sets and large-scale datasets, as well as in various downstream tasks such as classification, clustering, and adversarial attacks defence. A wealth of experimental results confirm the efficacy of the proposed model.

Self-supervised graph representations with generative adversarial learning

Graph Neural Networks (GNNs) are powerful neural models for representation learning on graphs. In this work we study a self-supervised learning GNN method GraphSSGAN (Graph Self-Supervised Generative Adversarial Network) that learns generalized node representations using only unlabeled data. The core idea lies in learning representations that capture both the local information of the links and the global information of the plausibility of the subgraph samples. Specifically, node features of the original graph are first encoded into latent representations by optimizing a link prediction objective. Then the generator converts noise vectors to node representations in the latent space and predicts the link probabilities from the generated node representations. The discriminator leverages the graph convolutional network (GCN) architecture to produce permutation-invariant graph-level embeddings, and the intermediate node representations are used by simple classifiers in the downstream tasks. In addition, we introduce several technical tricks including Gumbel-Top-k trick, Gumbel-Softmax trick and mini-batch training via subgraph sampling to improve the training process. Through extensive experiments on node classification and link prediction tasks, we demonstrate the effectiveness of the proposed model and the contribution of GAN framework on graph representation learning.

Cross-domain contrastive graph neural network for lncRNA–protein interaction prediction

Identifying lncRNA–protein interactions (LPIs) is an important biomedical task, facilitating the comprehension of the biological functions and mechanisms of lncRNAs. Many computational methods have been developed for this task, especially graph neural network (GNN)-based methods have attracted increasing attention. Typically, the LPI network involves two types of interaction domains: the interactive domain capturing the direct interaction information between lncRNAs and proteins, and the collaborative domain reflecting the collaboration information among lncRNAs or proteins. However, existing GNN-based methods only leverage one of them to obtain topological information, which cannot fully characterize lncRNAs and proteins, resulting in suboptimal node representations. Moreover, each domain contains task-irrelevant redundant information, posing a challenge in effectively integrating information from different domains. To address these issues, we propose a novel Cross-domain Contrastive Graph Neural Network (CCGNN) for predicting potential LPIs. CCGNN employs a multi-domain encoder that consists of an interactive domain encoder and two collaborative domain encoders to capture valuable information from each interaction domain. Subsequently, domain-adaptive fusion is designed to integrate information from different domains to acquire comprehensive node representations. Furthermore, cross-domain contrastive learning is devised to enrich the node representations, drawing inspiration from the information bottleneck principle by retaining as much task-relevant information as possible within each domain and minimizing mutual information between representations across different domains. Extensive experiments on four real-world datasets demonstrate the superiority of CCGNN over state-of-the-art methods, and a further case study and generalization analysis illustrate the effectiveness of CCGNN in the biomedical link prediction tasks.

Adversarial regularized attributed network embedding for graph anomaly detection

Graph anomaly detection aims to identify the nodes that display significantly different behavior from the majority. However, existing methods neglect the combined interaction between the network structure and node attributes, resulting in suboptimal latent representations of nodes due to network noise. In this paper, we introduce a novel approach called adversarial regularized attributed network embedding (ARANE) for graph anomaly detection. ARANE addresses this issue by forcing normal nodes to inhabit a compact manifold in the latent space, taking into account both the network structure and node attributes. It ensures that data points from the normal class, originating from different distributions, are distributed within a single compact latent space, while excluding anomalies from this region. ARANE employs a dual-encoder architecture consisting of an attribute encoder and a structure encoder. The attribute encoder learns node attribute embeddings, while the structure encoder focuses on learning structure embeddings. To obtain high-quality node embeddings for effective anomaly detection, we apply adversarial learning to regularize the learned embeddings separately in both the structure and attribute spaces. Furthermore, we introduce a fusion module that combines the final node embeddings derived from the structure and attribute spaces. These joint embeddings serve as inputs to a dual-decoder for graph reconstruction, where the resulting reconstruction errors are utilized as anomaly scores for anomaly detection. Extensive experiments conducted on real-world attributed networks demonstrate the superior effectiveness of our proposed method compared to state-of-the-art approaches.

Efficient Unsupervised Community Search with Pre-Trained Graph Transformer

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

SA-GNN: Prediction of material properties using graph neural network based on multi-head self-attention optimization

With the development of science and technology and the improvement of hardware computing power, the application of large models in the field of artificial intelligence (AI) has become a current research hotspot Among the focal points in the field of deep learning, AI for science is one of the highlighted areas, utilizing deep learning methods for pattern recognition, anomaly detection, predictive analysis, and more on a large scale of scientific data. In the realm of materials science, the structure of crystals is composed of edges and nodes, making it readily representable as a graph. In previous research, some typical models, such as the MEGNet model, utilized their graph neural network features to fit computational results based on density functional theory for predicting various material properties. Building on this concept, the authors propose a novel graph neural network (GNN) model, optimized with a Multi-Head Self-Attention (MHSA) mechanism, for predicting materials data with crystal structures. This model is named self-attention enhanced graph neural network. The model segments the input data into three parts: edges, nodes, and global features. The graph convolutional layer module is primarily used for aggregating node, edge, and global features, learning node representations, and capturing higher-order neighborhood information through multiple layers of GNN. The MHSA component allows nodes to learn global dependencies, providing different representation subspaces for the nodes. In comparison with other machine learning and deep learning models, the results indicate an improvement in the predictive accuracy of this model. A new graph neural network (GNN) model called Self-Attention Enhanced Graph Neural Network (SA-GNN) is proposed for predicting the properties of materials with crystal structures. This model incorporates multi-head self-attention to allow nodes to learn global dependencies and generate different representational subspaces. Compared to other machine learning and deep learning models, the results show improved predictive accuracy, demonstrating the potential of graph networks combined with self-attention for modeling crystal material data.

Neighborhood convolutional graph neural network

Graph convolutional networks (GCNs) have emerged as powerful tools for learning representations of graph structured data. A recent advancement is a decoupled GCN, which separates neighborhood aggregation from feature transformation within each graph convolutional layer and yields promising results. However, our investigation on node-level operations reveals its limitations in terms of modeling capacity and scalability, which hinder effective learning of rich node representations of diverse graphs. To address these challenges, we introduce a new paradigm of decoupled GCNs, called a neighborhood convolutional graph neural network (NCGNN). The NCGNN uses a novel neighborhood aggregator to generate a feature matrix of multi-hop neighborhoods of each node before model training. This avoids training the model via the adjacency matrix, effectively controls the training cost, and enhances scalability. Additionally, the NCGNN integrates advanced feature learning components, including a dedicated convolutional neural network for rich neighborhood information extraction and a feature fusion module to seamlessly integrate the raw attributes with the extracted features. Extensive experiments validate the superiority of the NCGNN over representative graph neural networks in node classification tasks, demonstrating its effectiveness and scalability for diverse graph structures.

MF-DAT: a stock trend prediction of the double-graph attention network based on multisource information fusion

Stock forecasting research, which aims to predict the future price movement of stocks, has been the focus of investors and scholars. This is important for practical applications related to human-centric computing and information sciences. Previous research has generally only considered market information other than the relationship between stocks, and it is challenging to learn a better representation of stock characteristics by considering the relationship between stocks. In the existing methods of combining market information with stock relationship modeling, most of them use predefined industry relationships to construct stock relationship diagrams, which inevitably ignores the potential interactions between stocks, especially the hidden relationships between stock groups. To this end, a new dual-graph attention model (MF-DAT) based on multisource information fusion is designed. Specifically, first, multiple features are fused by the LMF module, then the long-term and short-term state characteristics of stocks are learned through the first layer of the graph attention layer, and finally the node representation of the stock relationship network constructed by the mining stock cluster structure through community detection is updated. Our model takes into account both stock time-series information and potential relationships between stocks. Experiments on the S &P 500 and NASDAQ datasets show that our MF-DAT has better performance than the 8 SOTA methods that are now more popular.