Graph Datasets Research Articles

Multi-grained Semantics-aware Graph Neural Networks

Graph Neural Networks (GNNs) are powerful techniques in representation learning for graphs and have been increasingly deployed in a multitude of different applications that involve node- and graph-wise tasks. Most existing studies solve either the node-wise task or the graph-wise task independently while they are inherently correlated. This work proposes a unified model, AdamGNN, to interactively learn node and graph representations in a mutual-optimisation manner. Compared with existing GNN models and graph pooling methods, AdamGNN enhances the node representation with the learned multi-grained semantics and avoids losing node features and graph structure information during pooling. Specifically, a differentiable pooling operator is proposed to adaptively generate a multi-grained structure that involves meso- and macro-level semantic information in the graph. We also devise the unpooling operator and the <i>flyback</i> aggregator in AdamGNN to better leverage the multi-grained semantics to enhance node representations. The updated node representations can further adjust the graph representation in the next iteration. Experiments on 14 real-world graph datasets show that AdamGNN can significantly outperform 17 competing models on both node- and graph-wise tasks. The ablation studies confirm the effectiveness of AdamGNN&#x0027;s components, and the last empirical analysis further reveals the ingenious ability of AdamGNN in capturing long-range interactions.

Towards PageRank Update in a Streaming Graph by Incremental Random Walk

As the internet and the Internet of Things (IoT) have been widely applied in many application fields, a large number of graphs are continuously produced and change over time, which leads to difficulties in graph analysis and utilization. This paper studies a PageRank update algorithm for a streaming graph using incremental random walk. We focus on the information about the local changes of nodes and edges in the current graph, analyze the impact of such local changes on this current graph, and then use the idea behind wave propagation theory to seek and determine all affected nodes that need to be updated their PageRank in the new graph. For new nodes, the existing nodes in the current graph that are connected with these new nodes are aggregated into a supernode, and the PageRank of the new nodes is solved in the new graph with the supernode. Finally, we conduct a series of experiments on real-world and synthetic graph datasets. Compared with the state-of-the-art incremental computing algorithm, our algorithm not only ensures the accuracy of calculating the PageRank in a large streaming graph, but also speeds up the computational process by avoiding many redundant computations.

Database Translation Mechanism: Generating Data Dictionary for Relational Database

PDF HTML XML Export Cite reminder Database Translation Mechanism: Generating Data Dictionary for Relational Database DOI: 10.21655/ijsi.1673-7288.00291 Author: Affiliation: Clc Number: Fund Project: Article | Figures | Metrics | Reference | Related | Cited by | Materials | Comments Abstract:In order to optimize workflow and improve efficiency, modern enterprises usually entrust software providers to build the Enterprise Information System (EIS). However, the software providers generally do not provide the data dictionary for the EIS relational database, which brings great difficulties for enterprises to use the data stored in the EIS database. This paper proposes a method named database translation mechanism for generating the data dictionary of the EIS relational database which only utilizes the data collected from the interfaces of EIS. Inspired by the great success that Graph Neural Networks (GNNs) have achieved, the study builds a graph structure for the EIS relational database by mining the relationships between columns and then train a GNN-based classifier to predict to which column the value belongs. In addition, a table-based sampling method is designed to construct graph datasets for mini-batch training on the large-scale graph structure. Furthermore, a uniform encoding method and a hybrid aggregator function are proposed to improve the performance of the GNN-based classifier. The trained GNN-based classifier can be used to predict the matching relationships between the columns of the EIS database and the tables extracted from the EIS interfaces given the fact that the data in the database is entered at the interfaces. In this way, the detailed information at the interface to translate the database can be used. Experimental results on a real-world ERP relational database demonstrate the superior performance of the proposed method, which efficiently exploits and utilizes the graph structure information in the relational database. Reference Related Cited by

Estimating the Bot Population on Twitter via Random Walk Based Sampling

The rise of social bots, which contribute to marketing, political intervention, and the spread of fake news, has been noted. Analysis methods for the characteristics of Twitter bots have been developed for third-party researchers who have access limitations to Twitter data. Here, we propose a method for estimating the bot population on Twitter based on a random walk. The proposed method addresses two major problems in estimating the bot population on Twitter based on a random walk. First, the maximum number of retrievable friends or followers of a user per query is limited. Second, there is a certain percentage of private users who do not publish personal content, e.g., friends, followers, and tweets. We conduct a simulation analysis using directed social graph datasets to validate whether the proposed estimator is effective on the real Twitter follow graph. Then, we present three different estimates of the bot population on Twitter using the proposed estimator based on the three sample sequences of 25,000 users collected in 2.5 weeks each. The three estimates consistently suggest that 8%–18% of Twitter users during April–June 2021 are bots.

Graph Neural Networks With Lifting-Based Adaptive Graph Wavelets

Spectral-based graph neural networks (SGNNs) have been attracting increasing attention in graph representation learning. However, existing SGNNs are limited in implementing graph filters with rigid transforms and cannot adapt to signals residing on graphs and tasks at hand. In this paper, we propose a novel class of graph neural networks that realizes graph filters with adaptive graph wavelets. Specifically, the adaptive graph wavelets are learned with neural network-parameterized lifting structures, where structure-aware attention-based lifting operations are developed to jointly consider graph structures and node features. We propose to lift based on diffusion wavelets to alleviate the structural information loss induced by partitioning non-bipartite graphs. By design, the locality and sparsity of the resulting wavelet transform as well as the scalability of the lifting structure are guaranteed. We further derive a soft-thresholding filtering operation by learning sparse graph representations in terms of the learned wavelets, yielding a localized, efficient, and scalable wavelet-based graph filters. To ensure that the learned graph representations are invariant to node permutations, a layer is employed at the input of the networks to reorder the nodes according to their local topology information. We evaluate the proposed networks in both node-level and graph-level representation learning tasks on benchmark citation and bioinformatics graph datasets. Extensive experiments demonstrate the superiority of the proposed networks over existing SGNNs in terms of accuracy, efficiency, and scalability.

Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study.

Training deep graph neural networks (GNNs) is notoriously hard. Besides the standard plights in training deep architectures such as vanishing gradients and overfitting, it also uniquely suffers from over-smoothing, information squashing, and so on, which limits their potential power for encoding the high-order neighbor structure in large-scale graphs. Although numerous efforts are proposed to address these limitations, such as various forms of skip connections, graph normalization, and random dropping, it is difficult to disentangle the advantages brought by a deep GNN architecture from those "tricks" necessary to train such an architecture. Moreover, the lack of a standardized benchmark with fair and consistent experimental settings poses an almost insurmountable obstacle to gauge the effectiveness of new mechanisms. In view of those, we present the first fair and reproducible benchmark dedicated to assessing the "tricks" of training deep GNNs. We categorize existing approaches, investigate their hyperparameter sensitivity, and unify the basic configuration. Comprehensive evaluations are then conducted on tens of representative graph datasets including the recent large-scale Open Graph Benchmark, with diverse deep GNN backbones. We demonstrate that an organic combo of initial connection, identity mapping, group and batch normalization attains the new state-of-the-art results for deep GNNs on large datasets. Codes are available: https://github.com/VITA-Group/Deep_GCN_Benchmarking.

Semisupervised Classification with High-Order Graph Learning Attention Neural Network

At present, the graph neural network has achieved good results in the semisupervised classification of graph structure data. However, the classification effect is greatly limited in those data without graph structure, incomplete graph structure, or noise. It has no high prediction accuracy and cannot solve the problem of the missing graph structure. Therefore, in this paper, we propose a high-order graph learning attention neural network (HGLAT) for semisupervised classification. First, a graph learning module based on the improved variational graph autoencoder is proposed, which can learn and optimize graph structures for data sets without topological graph structure and data sets with missing topological structure and perform regular constraints on the generated graph structure to make the optimized graph structure more reasonable. Then, in view of the shortcomings of graph attention neural network (GAT) that cannot make full use of the graph high-order topology structure for node classification and graph structure learning, we propose a graph classification module that extends the attention mechanism to high-order neighbors, in which attention decays according to the increase of neighbor order. HGLAT performs joint optimization on the two modules of graph learning and graph classification and performs semisupervised node classification while optimizing the graph structure, which improves the classification performance. On 5 real data sets, by comparing 8 classification methods, the experiment shows that HGLAT has achieved good classification results on both a data set with graph structure and a data set without graph structure.

DyGA: A Hardware-Efficient Accelerator With Traffic-Aware Dynamic Scheduling for Graph Convolutional Networks

With the growing applications of Graph Convolutional Networks (GCN), there is also an increasing demand for its efficient hardware acceleration. Compared with CNN tasks, GCN tasks have new challenges such as randomness, sparsity, and nonuniformity, which will lead to poor performance of previous AI accelerators. In this paper, we propose DyGA, a hardware-efficient GCN accelerator, which is featured by strategies of graph partitioning, customized storage policy, traffic-aware dynamic scheduling, and out-of-order execution. Synthesized and evaluated under TSMC 28-nm, the accelerator achieves an average throughput of over 95% of its peak performance with full utilization of hardware on representative graph data sets. Having a high area-efficiency with 0.217 GOPS/K-logic-gates and 8.06 GOPS/KB-PE-buffer, and thus an energy-efficiency of 384GOPS/W, the proposed accelerator outperforms previous state-of-the-art works in the sparse data processing.

Exploring graph neural networks for semantic enrichment: Room type classification

Semantic enrichment of Building Information Modeling (BIM) models supplements models with the implicit semantics for further applications. In this paper, we use the room classification task to develop, test and illustrate a novel approach to semantic enrichment of BIM models - representation of models as graphs and application of graph neural networks (GNNs). A dedicated graph dataset consisting of 224 apartment layouts with nine room types and node/edge features was compiled. An improved GNN algorithm, SAGE-E, was developed for processing both node and edge features and a batch method was used to improve efficiency. The experiments showed that (1) The novel approach of adopting graphs and GNNs was feasible. (2) SAGE-E achieved higher accuracy (79%) and more balanced prediction (F1 = 0.79) when compared with other machine learning algorithms. (3) SAGE-E shortened the training and validation process. This work11A part of EU CBIM project at https://cbim2020.net.technion.ac.il/ (accessed on 17/8/2021). pioneers the application of GNNs for semantic enrichment and opens the door to other possible applications.

Subgraph matching over graph federation

Many real-life applications require processing graph data across heterogeneous sources. In this paper, we define the graph federation that indicates that the graph data sources are temporarily federated and offer their data for users. Next, we propose a new framework FedGraph to efficiently and effectively perform subgraph matching, which is a crucial application in graph federation. FedGraph consists of three phases, including query decomposition, distributed matching, and distributed joining. We also develop new efficient approximation algorithms and apply them in each phase to attack the NP-hard problem. The evaluations are conducted in a real test bed using both real-life and synthetic graph datasets. FedGraph outperforms the state-of-the-art methods, reducing the execution time and communication cost by 37.3 × and 61.8 ×, respectively.

Graph kernels based on linear patterns: Theoretical and experimental comparisons

Graph kernels are powerful tools to bridge the gap between machine learning and data encoded as graphs. Most graph kernels are based on the decomposition of graphs into a set of patterns. The similarity between two graphs is then deduced to the similarity between corresponding patterns. Kernels based on linear patterns constitute a good trade-off between accuracy and computational complexity. In this work, we propose a thorough investigation and comparison of graph kernels based on different linear patterns, namely walks and paths. First, all these kernels are explored in detail, including their mathematical foundations, structures of patterns and computational complexity. After that, experiments are performed on various benchmark datasets exhibiting different types of graphs, including labeled and unlabeled graphs, graphs with different numbers of vertices, graphs with different average vertex degrees, linear and non-linear graphs. Finally, for regression and classification tasks, accuracy and computational complexity of these kernels are compared and analyzed, in the light of baseline kernels based on non-linear patterns. Suggestions are proposed to choose kernels according to the types of graph datasets. This work leads to a clear comparison of strengths and weaknesses of these kernels. An open-source Python library containing an implementation of all discussed kernels is publicly available on GitHub to the community, thus allowing to promote and facilitate the use of graph kernels in machine learning problems.

A novel top‐k key node query problem in subgraph matching and its greedy strategy

AbstractTop‐k node selection in graph data is an essential problem in computer science and applications. In view of an important issue in the field of graph data, subgraph matching issue, we define the problem and propose its method for the top‐k key node query w.r.t. the subgraph matching. Unlike the general top‐k query problem, we aim to find out k nodes that make the matching subgraphs in data graph G that are covered by the k nodes as more as possible. This is a problem of the maximum coverage of subgraph matching, which belongs to the NP‐hard problem. We study the problem based on a greedy algorithm and give an intuitive solution. Considering the characteristics of the top‐k problem, we propose an improved and more efficient greedy algorithm. Experiments on real social network graph data set (Twitter) show that the related results represent the key nodes that can better reveal the essential characteristics of the query graph in the data graph G. The key node query problem in subgraph matching proposed in this article may have extensive applications in reality, such as the assessment of the influence of specific group members in social network, the detection of abnormal communication in a computer communication network, the road traffic evaluation and load balance problem in a road traffic network, and so on.

A New Approach for Mining Correlated Frequent Subgraphs

Nowadays graphical datasets are having a vast amount of applications. As a result, graph mining—mining graph datasets to extract frequent subgraphs—has proven to be crucial in numerous aspects. It is important to perform correlation analysis among the subparts (i.e., elements) of the frequent subgraphs generated using graph mining to observe interesting information. However, the majority of existing works focuses on complexities in dealing with graphical structures, and not much work aims to perform correlation analysis. For instance, a previous work realized in this regard, operated with a very naive raw approach to fulfill the objective, but dealt only on a small subset of the problem. Hence, in this article, a new measure is proposed to aid in the analysis for large subgraphs, mined from various types of graph transactions in the dataset. These subgraphs are immense in terms of their structural composition, and thus parallel the entire set of graphs in real-world. A complete framework for discovering the relations among parts of a frequent subgraph is proposed using our new method. Evaluation results show the usefulness and accuracy of the newly defined measure on real-life graphical datasets.

Unsupervised Adversarial Network Alignment with Reinforcement Learning

Network alignment, which aims at learning a matching between the same entities across multiple information networks, often suffers challenges from feature inconsistency, high-dimensional features, to unstable alignment results. This article presents a novel network alignment framework, Unsupervised Adversarial learning based Network Alignment(UANA), that combines generative adversarial network (GAN) and reinforcement learning (RL) techniques to tackle the above critical challenges. First, we propose a bidirectional adversarial network distribution matching model to perform the bidirectional cross-network alignment translations between two networks, such that the distributions of real and translated networks completely overlap together. In addition, two cross-network alignment translation cycles are constructed for training the unsupervised alignment without the need of prior alignment knowledge. Second, in order to address the feature inconsistency issue, we integrate a dual adversarial autoencoder module with an adversarial binary classification model together to project two copies of the same vertices with high-dimensional inconsistent features into the same low-dimensional embedding space. This facilitates the translations of the distributions of two networks in the adversarial network distribution matching model. Finally, we develop an RL based optimization approach to solve the vertex matching problem in the discrete space of the GAN model, i.e., directly select the vertices in target networks most relevant to the vertices in source networks, without unstable similarity computation that is sensitive to discriminative features and similarity metrics. Extensive evaluation on real-world graph datasets demonstrates the outstanding capability of UANA to address the unsupervised network alignment problem, in terms of both effectiveness and scalability.

Exploring graph capsual network for graph classification

Graph Neural Network (GNN) has received tremendous attention due to their power in learning graph representations by modeling the topological structure and aggregating feature information. However, the scalar node representations learned from GNN may not be sufficient to effectively preserve the attributes of the node/graph features, resulting in sub-optimal graph representation. Repeated averaging gathers too much noise, which makes the features of nodes in different classes over-mixed and leads to the problem of over smoothing. Inspired by the concept of capsule network proposed by Hinton, we propose a new framework for graph classification, named CapsualGNN, which takes full advantage of Graph Neural Network and Capsule Network. Specifically, we firstly represent nodes as groups of capsules, in which each capsule extracts distinctive features of its corresponding node. Then, we exploit routing mechanism to capture important information and properties at the graph level by the generated multiple embeddings for each graph, and utilize attention mechanism to focus on important features. Finally, to solve the problem of over smoothing, we introduce class residual connection for GCN. In addition, we also introduce parameter for distinguishing self-connected nodes and other nodes. We evaluate the framework by using six graph datasets on biological information and social networks, and demonstrate that CapsualGNN outperforms other SOTA techniques on the task of graph classification.

Answering regular path queries through exemplars

Regular simple path query (RPQ) is one of the fundamental operators in graph analytics. In an RPQ, the input is a graph, a source node and a regular expression. The goal is to identify all nodes that are connected to the source through a simple path whose label sequence satisfies the given regular expression. The regular expression acts as a formal specification of the search space that is of interest to the user. Although regular expressions have high expressive power, they act as barrier to non-technical users. Furthermore, to fully realize the power of regular expressions, the user must be familiar with the domain of the graph dataset. In this study, we address this bottleneck by bridging RPQs with the query-by-example paradigm. More specifically, we ask the user for an exemplar pair that characterizes the paths of interest, and the regular expression is automatically inferred from this exemplar. This novel problem introduces several new challenges. How do we infer the regex? Given that answering RPQs is NP-hard, how do we scale to large graphs? We address these challenges through a unique combination of Biermann and Feldman's algorithm with NFA-guided random walks with restarts. Extensive experiments on multiple real, million-scale datasets establish that RQuBE is at least 3 orders of magnitude faster than baseline strategies with an average accuracy in excess of 90%.

GNS: Forge High Anonymity Graph by Nonlinear Scaling Spectrum

It is crucial to generate random graphs with specific structural properties from real graphs, which could anonymize graphs or generate targeted graph data sets. The state-of-the-art method called spectral graph forge (SGF) was proposed at INFOCOM 2018. This method uses a low-rank approximation of the matrix by throwing away some spectrums, which provides privacy protection after distributing graphs while ensuring data availability to a certain extent. As shown in SGF, it needs to discard at least 20% spectrum to defend against deanonymous attacks. However, the data availability will be significantly decreased after more spectrum discarding. Thus, is there a way to generate a graph that guarantees maximum spectrum and anonymity at the same time? To solve this problem, this paper proposes graph nonlinear scaling (GNS). We firmly prove that GNS can preserve all eigenvectors meanwhile providing high anonymity for the forged graph. Precisely, the GNS scales the eigenvalues of the original spectrum and constructs the forged graph with scaled eigenvalues and original eigenvectors. This approach maximizes the preservation of spectrum information to guarantee data availability. Meanwhile, it provides high robustness towards deanonymous attacks. The experimental results show that when SGF discards only 10% of the spectrum, the forged graph has high data availability. At this time, if the distance vector deanonymity algorithm is used to attack the forged graph, almost 100% of the nodes can be identified, while when achieving the same availability, only about 20% of the nodes in the forged graph obtained from GNS can be identified. Moreover, our method is better than SGF in capturing the real graph’s structure in terms of modularity, the number of partitions, and average clustering.

Graph Clustering via Variational Graph Embedding

Graph clustering based on embedding aims to divide nodes with higher similarity into several mutually disjoint groups, but it is not a trivial task to maximumly embed the graph structure and node attributes into the low dimensional feature space. Furthermore, most of the current advanced methods of graph nodes clustering adopt the strategy of separating graph embedding technology and clustering algorithm, and ignore the potential relationship between them. Therefore, we propose an innovative end-to-end graph clustering framework with joint strategy to handle the complex problem in a non-Euclidean space. In terms of learning the graph embedding, we propose a new variational graph auto-encoder algorithm based on the Graph Convolution Network (GCN), which takes into account the boosting influence of joint generative model of graph structure and node attributes on the embedding output. On the basis of embedding representation, we implement a self-training mechanism through the construction of auxiliary distribution to further enhance the prediction of node categories, thereby realizing the unsupervised clustering mode. In addition, the loss contribution of each cluster is normalized to prevent large clusters from distorting the embedding space. Extensive experiments on real-world graph datasets validate our design and demonstrate that our algorithm has highly competitive in graph clustering over state-of-the-art methods.

Dynamic graph exploration by interactively linked node-link diagrams and matrix visualizations

The visualization of dynamic graphs is a challenging task owing to the various properties of the underlying relational data and the additional time-varying property. For sparse and small graphs, the most efficient approach to such visualization is node-link diagrams, whereas for dense graphs with attached data, adjacency matrices might be the better choice. Because graphs can contain both properties, being globally sparse and locally dense, a combination of several visual metaphors as well as static and dynamic visualizations is beneficial. In this paper, a visually and algorithmically scalable approach that provides views and perspectives on graphs as interactively linked node-link and adjacency matrix visualizations is described. As the novelty of this technique, insights such as clusters or anomalies from one or several combined views can be used to influence the layout or reordering of the other views. Moreover, the importance of nodes and node groups can be detected, computed, and visualized by considering several layout and reordering properties in combination as well as different edge properties for the same set of nodes. As an additional feature set, an automatic identification of groups, clusters, and outliers is provided over time, and based on the visual outcome of the node-link and matrix visualizations, the repertoire of the supported layout and matrix reordering techniques is extended, and more interaction techniques are provided when considering the dynamics of the graph data. Finally, a small user experiment was conducted to investigate the usability of the proposed approach. The usefulness of the proposed tool is illustrated by applying it to a graph dataset, such as e co-authorships, co-citations, and a Comprehensible Perl Archive Network distribution.

Macroeconomic forecasting with statistically validated knowledge graphs

This study leverages narrative from global newspapers to construct theme-based knowledge graphs about world events, demonstrating that features extracted from such graphs improve forecasts of industrial production in three large economies compared to a number of benchmarks. Our analysis relies on a filtering methodology that extracts “backbones” of statistically significant edges from large graph data sets. We find that changes in the eigenvector centrality of nodes in such backbones capture shifts in relative importance between different themes significantly better than graph similarity measures. We supplement our results with an interpretability analysis, showing that the theme categories “disease” and “economic” have the strongest predictive power during the time period that we consider. Our work serves as a blueprint for the construction of parsimonious – yet informative – theme-based knowledge graphs to monitor in real time the evolution of relevant phenomena in socio-economic systems.