Similar Nodes Research Articles

Graph semantic similarity-based automatic assessment for programming exercises

This paper proposes an algorithm for the automatic assessment of programming exercises. The algorithm assigns assessment scores based on the program dependency graph structure and the program semantic similarity, but does not actually need to run the student’s program. By calculating the node similarity between the student’s program and the teacher’s reference programs in terms of structure and program semantics, a similarity matrix is generated and the optimal similarity node path of this matrix is identified. The proposed algorithm achieves improved computational efficiency, with a time complexity of O(n2)\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$O(n^2)$$\\end{document} for a graph with n nodes. The experimental results show that the assessment algorithm proposed in this paper is more reliable and accurate than several comparison algorithms, and can be used for scoring programming exercises in C/C++, Java, Python, and other languages.

Supervised contrastive learning for graph representation enhancement

Graph Neural Networks (GNNs) have exhibited significant success in various applications, but they face challenges when labeled nodes are limited. A novel self-supervised learning paradigm has emerged, enabling GNN training without labeled nodes and even surpassing GNNs with limited labeled data. However, self-supervised methods lack class-discriminative node representations due to the absence of labeled information during training. In this paper, we exploit a supervised graph contrastive learning approach (SGCL) framework to tackle the issue of limited labeled nodes, ensuring coherent grouping of nodes within the same class. We propose augmentation techniques based on a novel centrality function to highlight important topological structures. Additionally, we introduce a supervised contrastive learning method that removes the necessity for negative samples and simplifies complex elements effortlessly. Our approach combines supervised contrastive loss and node similarity regularization while achieving consistent grouping of unlabeled nodes with labeled ones. Furthermore, we utilize the pseudo-labeling technique to propagate label information to distant nodes and address the underfitting problem, especially with low-degree nodes. Experimental results on real-world graphs demonstrate that SGCL outperforms both semi-supervised and self-supervised methods in node classification.

ProtoMGAE: Prototype-Aware Masked Graph Auto-Encoder for Graph Representation Learning

Graph self-supervised representation learning has gained considerable attention and demonstrated remarkable efficacy in extracting meaningful representations from graphs, particularly in the absence of labeled data. Two representative methods in this domain are graph auto-encoding and graph contrastive learning. However, the former methods primarily focus on global structures, potentially overlooking some fine-grained information during reconstruction. The latter methods emphasize node similarity across correlated views in the embedding space, potentially neglecting the inherent global graph information in the original input space. Moreover, handling incomplete graphs in real-world scenarios, where original features are unavailable for certain nodes, poses challenges for both types of methods. To alleviate these limitations, we integrate masked graph auto-encoding and prototype-aware graph contrastive learning into a unified model to learn node representations in graphs. In our method, we begin by masking a portion of node features and utilize a specific decoding strategy to reconstruct the masked information. This process facilitates the recovery of graphs from a global or macro level and enables handling incomplete graphs easily. Moreover, we treat the masked graph and the original one as a pair of contrasting views, enforcing the alignment and uniformity between their corresponding node representations at a local or micro level. Last, to capture cluster structures from a meso level and learn more discriminative representations, we introduce a prototype-aware clustering consistency loss that is jointly optimized with the preceding two complementary objectives. Extensive experiments conducted on several datasets demonstrate that the proposed method achieves significantly better or competitive performance on downstream tasks, especially for graph clustering, compared with the state-of-the-art methods, showcasing its superiority in enhancing graph representation learning.

Interpretable answer retrieval based on heterogeneous network embedding

Community question answering is a rising technology based on users' autonomous interactive behaviors, such as posting their issues, answering questions based on their experience, and commenting on existing questions. As a result of its use of natural language for communication and stimulation of user interest in information sharing, it has increasingly taken the place of other channels as the main way that people learn new things. Multi-type entity characteristics fusion and poor answer interpretability are the two major concerns that currently plague community answer prediction research. The Interpretable Answer Retrieval Method Based on Heterogeneous Network Embedding (IARHNE) is what we present in this work. It combines complex entity features and generates interpretable predicted answers. In order to incorporate the interactions of several kinds of individuals in answer social retrieval, we first build a heterogeneity graph. In order to acquire entity embeddings, we secondly use the heterogeneous graph neural network. We then adopt the vector distance to convert the entity matching problem in the heterogeneous information network into a homogeneous node similarity job. Finally, using entity correlation to predict answers, we provide a list of answers to the new query and interpret them using meta-paths. Comparative studies using three authentic datasets demonstrate the benefits of IARHNE for interpretative question-answering research.

Mix-Key: graph mixup with key structures for molecular property prediction.

Molecular property prediction faces the challenge of limited labeled data as it necessitates a series of specialized experiments to annotate target molecules. Data augmentation techniques can effectively address the issue of data scarcity. In recent years, Mixup has achieved significant success in traditional domains such as image processing. However, its application in molecular property prediction is relatively limited due to the irregular, non-Euclidean nature of graphs and the fact that minor variations in molecular structures can lead to alterations in their properties. To address these challenges, we propose a novel data augmentation method called Mix-Key tailored for molecular property prediction. Mix-Key aims to capture crucial features of molecular graphs, focusing separately on the molecular scaffolds and functional groups. By generating isomers that are relatively invariant to the scaffolds or functional groups, we effectively preserve the core information of molecules. Additionally, to capture interactive information between the scaffolds and functional groups while ensuring correlation between the original and augmented graphs, we introduce molecular fingerprint similarity and node similarity. Through these steps, Mix-Key determines the mixup ratio between the original graph and two isomers, thus generating more informative augmented molecular graphs. We extensively validate our approach on molecular datasets of different scales with several Graph Neural Network architectures. The results demonstrate that Mix-Key consistently outperforms other data augmentation methods in enhancing molecular property prediction on several datasets.

Gramformer: Learning Crowd Counting via Graph-Modulated Transformer

Transformer has been popular in recent crowd counting work since it breaks the limited receptive field of traditional CNNs. However, since crowd images always contain a large number of similar patches, the self-attention mechanism in Transformer tends to find a homogenized solution where the attention maps of almost all patches are identical. In this paper, we address this problem by proposing Gramformer: a graph-modulated transformer to enhance the network by adjusting the attention and input node features respectively on the basis of two different types of graphs. Firstly, an attention graph is proposed to diverse attention maps to attend to complementary information. The graph is building upon the dissimilarities between patches, modulating the attention in an anti-similarity fashion. Secondly, a feature-based centrality encoding is proposed to discover the centrality positions or importance of nodes. We encode them with a proposed centrality indices scheme to modulate the node features and similarity relationships. Extensive experiments on four challenging crowd counting datasets have validated the competitiveness of the proposed method. Code is available at https://github.com/LoraLinH/Gramformer.

Data-model-interactive enhancement-based Francis turbine unit health condition assessment using graph driven health benchmark model

As the data-driven Francis turbine units (FTUs) deterioration assessment method is widely investigated, the data quality in actual industrial scene has become an important prerequisite to restrict the method performance. However, existing data augmentation methods often lie in simply mixing real data and simulated data, ignoring the inherent cross-domain state relationships. In this paper, a data-model-interactive enhancement-based FTU health condition assessment using graph driven health benchmark model (HBM) is proposed. First, the pseudo-signals outputs of the mechanism digital twin (DT) model by calculative fluid dynamics (CFD) calculation are modified by critical working condition parameters, extending the theoretical assessment domain. To achieve data-model-interaction through cross-domain state coordination of digital and real data, a digital-reality hybrid graph is constructed from nodes mixing both actual and pseudo through node similarity. The hybrid spatial condition structure created by capture node status association explicitly enhances the sample representation ability. Avoiding excess noise effects, a knowledge-based unsupervised graph pruning regulation is adopted to refine the original graph considering noise and data reality. Finally, the spatial–temporal dependencies hidden in the refined graphs are mined by the designed hybrid graph neural network-based HBM, and output the assessed degradation label values. Verification experiments show that the proposed assessment method can effectively fit FTU deterioration under low-quality onsite data, and is more robust than the comparison methods.

Power system topological node tamper detection method based on fuzzy graph theory

Power system involves a large number of nodes and lines, and the topology is very complex. In such a complex network, node tamper detection needs to consider a variety of combinations and connection modes, which increases the complexity of the problem. Therefore, a new method of topological node tamper detection based on fuzzy graph theory is proposed. The feature difference values of topological nodes are extracted according to the node tampering feature vector. Detection of topological node similarity based on fuzzy graph-neural network. Based on this, the cost function of topological node tampering is established to obtain the Bayesian estimate of the tampering coefficient of the topological node transmission channel, and the detection of topological node tampering is completed. The experimental results show that the application time of the research method is shorter, the detection of power node tampering behavior is more comprehensive, and the tampering success rate is higher.

A Radial Basis Function-Based Graph Attention Network With Squeeze Loss Optimization for Link Prediction

Graph attention networks is a popular method to deal with link prediction tasks, but the weight assigned to each sample is not focusing on the sample's own performance in training. Moreover, since the number of links is much larger than nodes in a graph, mapping functions are usually used to map the learned node features to link features, whose expression of node similarity determines the quality of link feature learning. To tackle the above issues, a new model graph attention networks based on Radial Basis Function (RBF) with squeeze loss is proposed, including two improvements. Firstly, RBF function with extended parameters is used to transform the node features output by attention layer into link features. The result of link feature embedding can be improved by shortening the distance of nodes with links and enlarging the distance of nodes without links in vector space. Secondly, squeeze loss is designed to adjust the loss according to the performance of samples in training and change the proportion of sample loss in the loss function to allocate training resources reasonably. The link prediction task performed on datasets shows that the performance of proposed method is better than baselines.

Preserving node similarity adversarial learning graph representation with graph neural network

AbstractIn recent years, graph neural networks (GNNs) have showcased a strong ability to learn graph representations and have been widely used in various practical applications. However, many currently proposed GNN‐based representation learning methods do not retain neighbor‐based node similarity well, and this structural information is crucial in many cases. To address this issue, drawing inspiration from generative adversarial networks (GANs), we propose PNS‐AGNN (i.e., Preserving Node Similarity Adversarial Graph Neural Networks), a novel framework for acquiring graph representations, which can preserve neighbor‐based node similarity of the original graph and efficiently extract the nonlinear structural features of the graph. Specifically, we propose a new positive sample allocation strategy based on a node similarity index, where the generator can generate vector representations that satisfy node similarity through adversarial training. In addition, we also adopt an improved GNN as the discriminator, which utilizes the original graph structure for recursive neighborhood aggregation to maintain the local structure and feature information of nodes, thereby enhancing the graph representation's ability. Finally, we experimentally demonstrate that PNS‐AGNN significantly improves various tasks, including link prediction, node classification, and visualization.

Less is More: Removing Redundancy of Graph Convolutional Networks for Recommendation

While Graph Convolutional Networks (GCNs) have shown great potential in recommender systems and collaborative filtering (CF), they suffer from expensive computational complexity and poor scalability. On top of that, recent works mostly combine GCNs with other advanced algorithms which further sacrifice model efficiency and scalability. In this work, we unveil the redundancy of existing GCN-based methods in three aspects: (1) Feature redundancy . By reviewing GCNs from a spectral perspective, we show that most spectral graph features are noisy for recommendation, while stacking graph convolution layers can suppress but cannot completely remove the noisy features, which we mostly summarize from our previous work; (2) Structure redundancy . By providing a deep insight into how user/item representations are generated, we show that what makes them distinctive lies in the spectral graph features, while the core idea of GCNs (i.e., neighborhood aggregation) is not the reason making GCNs effective; and (3) Distribution redundancy . Following observations from (1), we further show that the number of required spectral features is closely related to the spectral distribution, where important information tends to be concentrated in more (fewer) spectral features on a flatter (sharper) distribution. To make important information be concentrated in as few features as possible, we sharpen the spectral distribution by increasing the node similarity without changing the original data, thereby reducing the computational cost. To remove these three kinds of redundancies, we propose a Simplified Graph Denoising Encoder (SGDE) only exploiting the top- K singular vectors without explicitly aggregating neighborhood, which significantly reduces the complexity of GCN-based methods. We further propose a scalable contrastive learning framework to alleviate data sparsity and to boost model robustness and generalization, leading to significant improvement. Extensive experiments on three real-world datasets show that our proposed SGDE not only achieves state-of-the-art but also shows higher scalability and efficiency than our previously proposed GDE as well as traditional and GCN-based CF methods.

基于节点相似性的时序网络节点重要性识别算法

基于节点相似性的时序网络节点重要性识别算法

Research on teaching reform and practice of architectural design courses in colleges and universities based on big data analysis

Abstract In this paper, we carry out an innovative reform of architectural design professional courses in colleges and universities, focusing on improving the effect of practical teaching by combining knowledge maps and new technological means. Aiming at the problems of long practice cycle, high cost and difficulty verifying the effect in traditional teaching, it promotes the transformation of teaching mode to immersion, interaction and autonomy. The article discusses the application of knowledge maps in optimizing the course content, improving the effect of teaching organization, such as the association model of knowledge elements and learning resources, and calculating the ontological conceptual similarity of knowledge nodes. Meanwhile, the introduction of augmented reality technology and the Analysis of the correlation between learning styles and academic performance highlight the critical role of technology in enhancing the efficiency and quality of learning. The difference in average grades before and after the teaching reform in the experimental class was significant, with the most enormous difference of 10.76 points in the second round of test results. The most significant improvement was observed in the knowledge part of the course, with an increase of 0.72, and in the practical part, with an increase of 0.39. The students’ architectural design and practice skills were significantly improved in all dimensions. The teaching reform program proposed in this paper effectively enhances the architectural design program’s teaching quality and students’ practical ability.

Deep Graph Reinforcement Learning for Solving Multicut Problem.

The multicut problem, also known as correlation clustering, is a classic combinatorial optimization problem that aims to optimize graph partitioning given only node (dis)similarities on edges. It serves as an elegant generalization for several graph partitioning problems and has found successful applications in various areas such as data mining and computer vision. However, the multicut problem with an exponentially large number of cycle constraints proves to be NP-hard, and existing solvers either suffer from exponential complexity or often give unsatisfactory solutions due to inflexible heuristics driven by hand-designed mechanisms. In this article, we propose a deep graph reinforcement learning method to solve the multicut problem within a combinatorial decision framework involving sequential edge contractions. The customized subgraph neural network adapts to the dynamically edge-contracted graph environment by extracting bilevel connected features from both contracted and original graphs. Our method can learn to infer feasible multicut solutions end-to-end toward optimization of the multicut objective in a data-driven manner. More specifically, by exploring the decision space adaptively, it implicitly gains heuristic knowledge from topological patterns of instances and thereby generates more targeted heuristics overcoming the short-sightedness inherent in the hand-designed ones. During testing, the learned heuristics iteratively contract graphs to construct high-quality solutions within polynomial time. Extensive experiments on synthetic and real-world multicut instances show the superiority of our method over existing combinatorial solvers, while also maintaining a certain level of out-of-distribution generalization ability.

Multiresolution Interpretable Contourlet Graph Network for Image Classification.

Modeling contextual relationships in images as graph inference is an interesting and promising research topic. However, existing approaches only perform graph modeling of entities, ignoring the intrinsic geometric features of images. To overcome this problem, a novel multiresolution interpretable contourlet graph network (MICGNet) is proposed in this article. MICGNet delicately balances graph representation learning with the multiscale and multidirectional features of images, where contourlet is used to capture the hyperplanar directional singularities of images and multilevel sparse contourlet coefficients are encoded into graph for further graph representation learning. This process provides interpretable theoretical support for optimizing the model structure. Specifically, first, the superpixel-based region graph is constructed. Then, the region graph is applied to code the nonsubsampled contourlet transform (NSCT) coefficients of the image, which are considered as node features. Considering the statistical properties of the NSCT coefficients, we calculate the node similarity, i.e., the adjacency matrix, using Mahalanobis distance. Next, graph convolutional networks (GCNs) are employed to further learn more abstract multilevel NSCT-enhanced graph representations. Finally, the learnable graph assignment matrix is designed to get the geometric association representations, which accomplish the assignment of graph representations to grid feature maps. We conduct comparative experiments on six publicly available datasets, and the experimental analysis shows that MICGNet is significantly more effective and efficient than other algorithms of recent years.

Knowledge-Aware Graph Self-Supervised Learning for Recommendation

Collaborative filtering (CF) based on graph neural networks (GNN) can capture higher-order relationships between nodes, which in turn improves recommendation performance. Although effective, GNN-based methods still face the challenges of sparsity and noise in real scenarios. In recent years, researchers have introduced graph self-supervised learning (SSL) techniques into CF to alleviate the sparse supervision problem. The technique first augments the data to obtain contrastive views and then utilizes the mutual information maximization to provide self-supervised signals for the contrastive views. However, the existing approaches based on graph self-supervised signals still face the following challenges: (i) Most of the works fail to effectively mine and exploit the supervised information from the item knowledge graph, resulting in suboptimal performance. (ii) Existing data augmentation methods are unable to fully exploit the potential of contrastive learning, because they primarily focus on the contrastive view of data structure changes and neglect the adjacent relationship among users and items. To address these issues, we propose a novel self-supervised learning approach, namely Knowledge-aware Graph Self-supervised Learning (KGSL). Specifically, we calculate node similarity based on semantic relations between items in the knowledge graph to generate a semantic-based item similarity graph. Then, the self-supervised learning contrast views are generated from both the user–item interaction graph and the item similarity graph, respectively. Maximization of the information from these contrastive views provides additional self-supervised signals to enhance the node representation capacity. Finally, we establish a joint training strategy for the self-supervised learning task and the recommendation task to further optimize the learning process of KGSL. Extensive comparative experiments as well as ablation experiments are conducted on three real-world datasets to verify the effectiveness of KGSL.

A novel trajectory similarity measurement method based on node‐sequence hierarchical digraph

AbstractTrajectory similarity measurement is a basic and vital task in trajectory data mining, which has attracted extensive research in the past decades. Recent works focused on the sequence and hierarchy property of trajectories to construct similarity measurements. However, these methods ignore the user information on the visiting locations, such as semantic and time distribution. In light of this, a novel trajectory similarity measurement based on Node‐Sequence Hierarchical Digraph (NSHD) framework is proposed in this article. We first propose a Time‐Weighted Stay Point Detection (TWSPD) method to extract real visiting locations of users more accurately. Then, the nodes of digraph are obtained by clustering users' stay points and the edges of digraph are sequence information that users move between these nodes. An Advanced Earth Mover's Distance (AEMD) is proposed to measure the node similarity between users, considering visiting time distribution and semantic information simultaneously. Both node and sequence similarities are used to calculate the similarity score to obtain the final trajectory similarity measurement. Experiments on Geolife and T‐Drive datasets show that our proposed method offers competitive performance with mean reciprocal rank values reaching 96.01 and 81.26%, which outperforms related trajectory similarity measurements by more than 10 and 15%.

Brain-inspired GCN: Modularity-based Siamese simple graph convolutional networks

In graph representation learning, Graph Convolutional Networks (GCNs) and their variants have received much attention. However, GCNs encounter oversmoothing as the models get deeper, limiting their ability to aggregate node representations within high-order neighborhood. Inspired by the modular structure of the brain network, we propose Modularity-based Siamese Simple Graph Convolution (MS-SGC), a Siamese network architecture that incorporates the characteristics of brain modular structure into graph convolutional networks. Spectral clustering is leveraged to detect the modular structure in the graph, and then the weight of cross edges between modules is lowered. Siamese network is adopted to combine the modularity-preserved graph representation with the original graph representation, improving classification performance and reducing oversmoothing. Furthermore, a graph convolution method that functions as a linear low-pass graph filter is elaborated through spectral analysis to preserve the similarity of nodes within the same module and further alleviate the oversmoothing problem. We validate the effectiveness of MS-SGC on citation networks and extend our experimental analysis to various downstream tasks. Extensive experiments demonstrate that MS-SGC outperforms state-of-the-arts while reducing the time and computation complexity for node classification. Moreover, MS-SGC achieves competitive performance compared to other state-of-the-arts in node clustering, community prediction and text classification tasks.

A Link Prediction Algorithm Based on Weighted Local and Global Closeness.

Link prediction aims to identify unknown or missing connections in a network. The methods based on network structure similarity, known for their simplicity and effectiveness, have garnered widespread attention. A core metric in these methods is "proximity", which measures the similarity or linking probability between two nodes. These methods generally operate under the assumption that node pairs with higher proximity are more likely to form new connections. However, the accuracy of existing node proximity-based link prediction algorithms requires improvement. To address this, this paper introduces a Link Prediction Algorithm Based on Weighted Local and Global Closeness (LGC). This algorithm integrates the clustering coefficient to enhance prediction accuracy. A significant advantage of LGC is its dual consideration of a network's local and global features, allowing for a more precise assessment of node similarity. In experiments conducted on ten real-world datasets, the proposed LGC algorithm outperformed eight traditional link prediction methods, showing notable improvements in key evaluation metrics, namely precision and AUC.

Factors influencing communication power in new media innovation combined with multi-source data fusion analysis

Abstract This paper combines multi-source data and obtains effective data collection with higher value and richer knowledge connotations by cleaning, integrating, filtering, and transforming the original data. It also calculates the propagation characteristics of new media innovation, proposes the similarity of nodes, combines the propagation probability to construct the centrality degree and the near centrality expression, and analyzes the relationship of the propagation term that affects the new media innovation. The results show that when p takes 0.1, it is 13.8 and 14.15 seconds at 100 nodes and 500 nodes of new media innovations, indicating that the propagation time starts to extend gradually with the increase of p-value. The correlation between dissemination power and time in new media innovation incorporating multi-source data is demonstrated.