Graph Embedding Techniques Research Articles

Research on English Foreign Propaganda Translation and External Communication Paths Based on Multimodal Analysis Approach

Abstract In this paper, a multimodal phrase corpus is created, enabling phrases to be searched automatically. The phrase structure is constructed through phrase centroids, and multilevel linguistic measurements are obtained for vocabulary, syntax, and parts of speech styles. A joint feature analysis model for the automatic conversion of English-Chinese machine translation is constructed through distributed feature fusion and joint parameter analysis. Linear statistical features and feature analysis detection are utilized to compute the optimal solution for English-Chinese machine automatic translation text. The graph embedding technique was used to pretrain the knowledge graph and obtain information about the network structure. Combined with the graph convolution technique, deep semantic information mining was carried out to achieve efficient content matching and cultural dissemination. It has been proved that the method of this paper has an AUC value of 0.921 and a satisfaction rate between 80% and 95% in English-translated movie data. The proposed method can accurately translate information from English to foreign propaganda content, which further promotes the development of international cultural exchange and communication.

Semisupervised regression in latent structure networks on unknown manifolds

Random graphs are increasingly becoming objects of interest for modeling networks in a wide range of applications. Latent position random graph models posit that each node is associated with a latent position vector, and that these vectors follow some geometric structure in the latent space. In this paper, we consider random dot product graphs, in which an edge is formed between two nodes with probability given by the inner product of their respective latent positions. We assume that the latent position vectors lie on an unknown one-dimensional curve and are coupled with a response covariate via a regression model. Using the geometry of the underlying latent position vectors, we propose a manifold learning and graph embedding technique to predict the response variable on out-of-sample nodes, and we establish convergence guarantees for these responses. Our theoretical results are supported by simulations and an application to Drosophila brain data.

A community detection approach based on network representation learning for repository mining

In this paper, we propose a novel heterogeneous graph-based model for capturing and handling all the complex and strongly-correlated information of a software Developer Social Network (DSN) to support several analytic tasks. In particular, we challenge the problem of automatically discovering communities of software developers sharing interests for similar projects by relying on Social Network Analysis (SNA) findings. To overcome the huge graph-size issue, we leverage different graph embedding techniques. Eventually, we evaluate the proposed approach with respect to state-of-the-art approaches from an efficiency and an effectiveness point of view by carrying out an experiment involving the GitHub dataset.

GE-DDRL: Graph Embedding and Deep Distributional Reinforcement Learning for Reliable Shortest Path: A Universal and Scale Free Solution

This paper studies the reliable shortest path (RSP) problem in stochastic transportation networks. State-of-the-art RSP solutions usually target one specific RSP problem; moreover, the corresponding algorithm’s computational complexity scales at least linearly with the size of the underlying transportation network. While in this paper, we propose a graph embedding and deep distributional reinforcement learning (GE-DDRL) method, which serves as a universal and scale-free solution to the RSP problem. GE-DDRL uses deep distributional reinforcement learning (DDRL) to estimate the full travel-time distribution of a given routing policy, and improves the given routing policy with the generalized policy iteration (GPI) scheme. Further, in order to achieve the generalization ability to new destination nodes, we employ one of the canonical graph embedding techniques (Skip-Gram) to compress the nodes’ representation into <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$d$</tex-math> </inline-formula> -dimensional real-valued vectors. With the properly compressed node features, GE-DDRL is able to generalize its estimation of the routing policy’s travel-time distribution to untrained destination nodes, and hence achieve the ‘all-to-all’ navigation functionality. To the best of our knowledge, GE-DDRL serves as the first RSP planner, which applies simultaneously to almost all RSP objectives and in the meanwhile, is scale free with the size of the transportation network in terms of the online decision-making time and memory complexity. Experimental results and comparisons with state of the arts show the efficacy and efficiency of GE-DDRL in a range of transportation networks.

Identifying critical nodes via link equations and deep reinforcement learning

Identifying an optimal set of nodes that can maximize the spread of influence in a network is a crucial challenge in network science. It has numerous applications such as epidemic control and rumor containment. However, most existing techniques are limited by their high computational costs, making them impractical for graphs with millions of nodes. Moreover, the previous approaches have primarily focused on the structural characteristics of the network while the characteristics of information diffusion are ignored. This paper proposes a deep reinforcement learning framework, DeepELE, to bridge these gaps. DeepELE incorporates a graph embedding technique to represent the graph states and applies a deep reinforcement learning method to learn the policy automatically. Note that we assess the contribution of links to spreading processes and further account for the diffusion-related contribution along with the graph structure information into convolutional neural and the Q network. Extensive experiments on both synthetic and real-world networks validate the efficiency and efficacy of DeepELE. The results demonstrate that DeepELE significantly outperforms the state-of-the-art methods, especially for large-scale networks with millions of nodes.

Detecting Pseudo-Manipulated Citations in Scientific Literature through Perturbations of the Citation Graph

Ensuring the integrity of scientific literature is essential for advancing knowledge and research. However, the credibility and trustworthiness of scholarly publications are compromised by manipulated citations. Traditional methods, such as manual inspection and basic statistical analyses, have limitations in detecting intricate patterns and subtle manipulations of citations. In recent years, network-based approaches have emerged as promising techniques for identifying and understanding citation manipulation. This study introduces a novel method to identify potential citation manipulation in academic papers using perturbations of a deep embedding model. The key idea is to reconstruct meaningful connections represented by citations within a network by exploring, to some extent, longer alternative paths. These indirect pathways enable the recovery of reliable citations while estimating their trustworthiness. The investigation takes a comprehensive approach to link prediction, leveraging the consistent behavior of prominent connections when exposed to network perturbations. Through numerical experiments, the method demonstrates a high capability to identify reliable citations as the core of the analyzed data and to raise suspicions about unreliable references that may have been manipulated. This research presents a refined method for tackling the urgent problem of citation manipulation in academic papers. It harnesses statistical sampling and graph-embedding techniques to evaluate the credibility of scholarly publications with a substantial assessment of the whole citation graph.

Leveraging Minimum Nodes for Optimum Key Player Identification in Complex Networks: A Deep Reinforcement Learning Strategy with Structured Reward Shaping

The problem of finding key players in a graph, also known as network dismantling, or network disintegration, aims to find an optimal removal sequence of nodes (edges, substructures) through a certain algorithm, ultimately causing functional indicators such as the largest connected component (GCC) or network pair connectivity in the graph to rapidly decline. As a typical NP-hard problem on graphs, recent methods based on reinforcement learning and graph representation learning have effectively solved such problems. However, existing reinforcement-learning-based key-player-identification algorithms often need to remove too many nodes in order to achieve the optimal effect when removing the remaining network until no connected edges remain. The use of a minimum number of nodes while maintaining or surpassing the performance of existing methods is a worthwhile research problem. To this end, a novel algorithm called MiniKey was proposed to tackle such challenges, which employs a specific deep Q-network architecture for reinforcement learning, a novel reward-shaping mechanism based on network functional indicators, and the graph-embedding technique GraphSage to transform network nodes into latent representations. Additionally, a technique dubbed ‘virtual node technology’ is integrated to grasp the overarching feature representation of the whole network. This innovative algorithm can be effectively trained on small-scale simulated graphs while also being scalable to large-scale real-world networks. Importantly, experiments from both six simulated datasets and six real-world datasets demonstrates that MiniKey can achieve optimal performance, striking a perfect balance between the effectiveness of key node identification and the minimization of the number of nodes that is utilized, which holds potential for real-world applications such as curbing misinformation spread in social networks, optimizing traffic in transportation systems, and identifying key targets in biological networks for targeted interventions.

MultiGML: Multimodal graph machine learning for prediction of adverse drug events

Adverse drug events constitute a major challenge for the success of clinical trials. Several computational strategies have been suggested to estimate the risk of adverse drug events in preclinical drug development. While these approaches have demonstrated high utility in practice, they are at the same time limited to specific information sources. Thus, many current computational approaches neglect a wealth of information which results from the integration of different data sources, such as biological protein function, gene expression, chemical compound structure, cell-based imaging and others. In this work we propose an integrative and explainable multi-modal Graph Machine Learning approach (MultiGML), which fuses knowledge graphs with multiple further data modalities to predict drug related adverse events and general drug target-phenotype associations. MultiGML demonstrates excellent prediction performance compared to alternative algorithms, including various traditional knowledge graph embedding techniques. MultiGML distinguishes itself from alternative techniques by providing in-depth explanations of model predictions, which point towards biological mechanisms associated with predictions of an adverse drug event. Hence, MultiGML could be a versatile tool to support decision making in preclinical drug development.

Graph contextualized self-attention network for software service sequential recommendation

With the broad application of software services, an increasing number of developers are turning to social coding sites for constructing their applications or conducting further research. These software services generate spatiotemporal data with numerous unique features. GitHub, being the world’s largest code hosting platform, is essential to efficiently provide recommendation services for its users. In order to make accurate recommendations and establish effective user–item and item–item relationships, we propose a Graph Contextualized Self-attention Network for Software Service Sequential Recommendation (GCSAN). This model captures global repository-to-repository relationships based on contextual information and recommends suitable repositories to users. Specifically, we leverage the relationships between repositories in all behavior sequences and graph embedding technique to alleviate the data sparsity problem. Moreover, we employ a self attention mechanism to capture user’s repository preferences at different time points, assigning varying weights accordingly. Finally, the experimental results on real-world datasets demonstrate the superior performance of our proposed model compared to benchmark recommendation methods.

Cross-modal knowledge guided model for abstractive summarization

ive summarization (AS) aims to generate more flexible and informative descriptions than extractive summarization. Nevertheless, it often distorts or fabricates facts in the original article. To address this problem, some existing approaches attempt to evaluate or verify factual consistency, or design models to reduce factual errors. However, most of the efforts either have limited effects or result in lower rouge scores while reducing factual errors. In other words, it is challenging to promote factual consistency while maintaining the informativeness of generated summaries. Inspired by the knowledge graph embedding technique, in this paper, we propose a novel cross-modal knowledge guided model (CKGM) for AS, which embeds a multimodal knowledge graph (MKG) combining image entity-relationship information and textual factual information (FI) into BERT to accomplish cross-modal information interaction and knowledge expansion. The pre-training method obtains rich contextual semantic information, while the knowledge graph supplements the textual information. In addition, an entity memory embedding algorithm is further proposed to improve information fusion efficiency and model training speed. We elaborately conducted ablation experiments and evaluated our model on the Visual Genome, FewRel, MSCOCO, and CNN/DailyMail datasets. Experimental results demonstrate that our model can significantly improve the FI consistency and informativeness of generated summaries.

A survey on graph embedding techniques for biomedical data: Methods and applications

As a result of the expeditious advancement of biomedical technologies, a plethora of relational data linking biomedical entities such as genes, proteins, and drugs have been collected for modern biomedical research. Biomedical graphs, one of the most popular ways to represent relational data, can easily describe different complex biomedical systems, including molecular-level, multi-omics-level, therapeutics-level, and healthcare-level interactions. However, traditional graph analysis methods still suffer from two difficulties (i.e., heterogeneities and dynamic properties of biomedical graphs) when handling high-dimensional, multi-modal, and sparsely interconnected biomedical data. To address these issues, graph embedding methods that can effectively analyze biomedical graphs have received a significant amount of attention recently. Generally, graph-based data is converted into a low-dimensional vector space with its structural properties and well-reserved information. These vectorized representations are used for further computation in various downstream biomedical tasks, such as gene function prediction and drug–target interaction prediction. In this article, we focus on the application of graph data in the biomedical domain and mainly introduce recent developments of graph embedding techniques (homogeneous, heterogeneous, and dynamic graph embedding techniques), including methodologies and related biomedical tasks. We also summarize relevant biomedical datasets and open-source implementations. We further discuss existing limitations and potential solutions. We hope this survey can provide useful directions for researchers who are interested in using graph embedding methods to solve problems in the biomedical field.

Supporting secure dynamic alert zones using searchable encryption and graph embedding

Location-based alerts have gained increasing popularity in recent years, whether in the context of healthcare (e.g., COVID-19 contact tracing), marketing (e.g., location-based advertising), or public safety. However, serious privacy concerns arise when location data are used in clear in the process. Several solutions employ searchable encryption (SE) to achieve secure alerts directly on encrypted locations. While doing so preserves privacy, the performance overhead incurred is high. We focus on a prominent SE technique in the public-key setting–hidden vector encryption, and propose a graph embedding technique to encode location data in a way that significantly boosts the performance of processing on ciphertexts. We show that the optimal encoding is NP-hard, and we provide three heuristics that obtain significant performance gains: gray optimizer, multi-seed gray optimizer and scaled gray optimizer. Furthermore, we investigate the more challenging case of dynamic alert zones, where the area of interest changes over time. Our extensive experimental evaluation shows that our solutions can significantly improve computational overhead compared to existing baselines.

Preserving complex object-centric graph structures to improve machine learning tasks in process mining

Interactions of multiple processes and different objects can be captured using object-centric event data. Object-centric event data represent process executions as event graphs of interacting objects. When applying machine learning techniques to object-centric event data, the event log has to be flattened into sequential process executions used as input for traditional process mining approaches. However, sequentializing the events by flattening removes the graph structure of object-centric event data and, therefore, constitutes an information loss. In this paper, we present a general approach to preserve the graph structures of object-centric event data across machine learning tasks in process mining. We provide two different techniques to preserve these structures depending on the required input format of machine learning techniques: as direct graph encodings or as graph embeddings. We evaluate our contributions by applying three different predictive process monitoring tasks to direct graph encodings, graph embeddings, and flattened event logs. Based on the relative performances, we assess the information contained in the graph structure of object-centric event logs that is, currently, lost in machine learning approaches for traditional process mining. Furthermore, we compare different graph embedding techniques for object-centric event logs to derive recommendations for future research and deployment. To conclude, we assess the improvement that graph embeddings constitute over state-of-the-art approaches that capture object information through specific features. Our contributions improve predictive process monitoring on object-centric event data and quantify the potential performance increases of predictive models. These contributions are especially relevant when looking at real-life applications of predictive process monitoring which are often applied to information systems with relational databases that contain multiple objects and, currently, still enforce flattening.

Graph Structure Learning on User Mobility Data for Social Relationship Inference

With the prevalence of smart mobile devices and location-based services, uncovering social relationships from human mobility data is of great value in real-world spatio-temporal applications ranging from friend recommendation, advertisement targeting to transportation scheduling. While a handful of sophisticated graph embedding techniques are developed for social relationship inference, they are significantly limited to the sparse and noisy nature of user mobility data, as they all ignore the essential problem of the existence of a large amount of noisy data unrelated to social activities in such mobility data. In this work, we present Social Relationship Inference Network (SRINet), a novel Graph Neural Network (GNN) framework, to improve inference performance by learning to remove noisy data. Specifically, we first construct a multiplex user meeting graph to model the spatial-temporal interactions among users in different semantic contexts. Our proposed SRINet tactfully combines the representation learning ability of Graph Convolutional Networks (GCNs) with the power of removing noisy edges of graph structure learning, which can learn effective user embeddings on the multiplex user meeting graph in a semi-supervised manner. Extensive experiments on three real-world datasets demonstrate the superiority of SRINet against state-of-the-art techniques in inferring social relationships from user mobility data. The source code of our method is available at https://github.com/qinguangming1999/SRINet.

IsoGloVe: A New Count-based Graph Embedding Method based on Geodesic Distance

Graph embedding techniques have gained increasing attention for their ability to encode the complex structural information of networks into low-dimensional vectors. Existing graph embedding methods have achieved considerable success in various applications. However, these methods have limitations in capturing global graph topology information and fail to provide insights into the underlying mechanisms of network function. In this paper, we propose IsoGloVe, a count-based method that encodes graph topology into vectors using the co-occurrence statistics of fixed-size routes in random walks. IsoGloVe calculates the final embeddings based on the geodesic distances of the node’s neighbors on a manifold. This representation in geodesic space allows for the analysis of node interactions and contributes to a better understanding of complex network structure and function. The performance of IsoGloVe is evaluated on various protein-protein interactions (PPI) using graph reconstruction, node classification, and visualization. The findings reveal that IsoGloVe surpasses other comparable methods with a 30% increase in MAP for graph reconstruction and a 25% increase in model scores for node classification in the Yeast PPI network. In addition, IsoGloVe demonstrated a 6.9% increase in MAP for graph reconstruction on the Human PPI network.

Java Code Clone Detection by Exploiting Semantic and Syntax Information From Intermediate Code-Based Graph

Code clone detection plays a critical role in the field of software engineering. To achieve this goal, developers are required to have rich development experience for finding the &#x201C;functional&#x201D; clone code. However, this is unfriendly to novice developers. Although many approaches were proposed to automatically detect code clones, the results are not satisfactory. A major reason is that it is difficult to extract syntax and semantic information from the source code. To resolve this problem, in this article, we develop a novel graph representation approach based on intermediate code to detect the functional code clones. This graph representation is built based on intermediate code compiled from the source code. By using it, we can easily utilize graph embedding techniques to extract syntactic and semantic features from abstract syntax tree, control flow graph, and DFG generated from intermediate code. After that, we use the Softmax classifier to detect functional code clone pairs. We evaluate the performance of the proposed graph representation approach based on intermediate code for the code clone detection task on the BigCloneBench dataset. In order to improve performance, the embedded representation of intermediate code is initialized based on pretrained vectors learned from the collected LLVM IR dataset in advance. The experimental results show that our proposed intermediate code-based graph approach performs better than existing functional code clone detection approaches. Especially for the type-4 code clone detection, our approach outperforms the baseline approaches by an average of 33.49&#x0025; in the term of <i>F</i>1 score.

Topological Similarity and Centrality Driven Hybrid Deep Learning for Temporal Link Prediction

Several real-world phenomena, including social, communication, transportation, and biological networks, can be efficiently expressed as graphs. This enables the deployment of graph algorithms to infer information from such complex network interactions to enhance graph applications&amp;rsquo; accuracy, including link prediction, node classification, and clustering. However, the large size and complexity of the network data limit the efficiency of the learning algorithms in making decisions from such graph datasets. To overcome these limitations, graph embedding techniques are usually adopted. However, many studies not only assume static networks but also pay less attention to preserving the network topological and centrality information, which information is key in analyzing networks. In order to fill these gaps, we propose a novel end-to-end unified Topological Similarity and Centrality driven Hybrid Deep Learning model for Temporal Link Prediction (TSC-TLP). First, we extract topological similarity and centrality-based features from the raw networks. Next, we systematically aggregate these topological and centrality features to act as inputs for the encoder. In addition, we leverage the long short-term memory (LSTM) layer to learn the underlying temporal information in the graph snapshots. Lastly, we impose topological similarity and centrality constraints on the model learning to enforce preserving of topological structure and node centrality role of the input graphs in the learned embeddings. The proposed TSC-TLP is tested on 3 real-world temporal social networks. On average, it exhibits a 4% improvement in link prediction accuracy and a 37% reduction in MSE on centrality prediction over the best benchmark.

Surrogate explanations for role discovery on graphs

Role discovery is the task of dividing the set of nodes on a graph into classes of structurally similar roles. Modern strategies for role discovery typically rely on graph embedding techniques, which are capable of recognising complex graph structures when reducing nodes to dense vector representations. However, when working with large, real-world networks, it is difficult to interpret or validate a set of roles identified according to these methods. In this work, motivated by advancements in the field of explainable artificial intelligence, we propose surrogate explanation for role discovery, a new framework for interpreting role assignments on large graphs using small subgraph structures known as graphlets. We demonstrate our framework on a small synthetic graph with prescribed structure, before applying them to a larger real-world network. In the second case, a large, multidisciplinary citation network, we successfully identify a number of important citation patterns or structures which reflect interdisciplinary research.

Leveraging multimodal features for knowledge graph entity alignment based on dynamic self-attention networks

Entity alignment establishes correspondence between entities across different knowledge graphs, which plays an important role in knowledge fusion. The key of entity alignment is to represent and fuse the features of entities across graphs. To improve efficiency, recent methods introduce graph embedding techniques that map different knowledge graphs into common latent spaces to encode structure and attribute features of entities. However, the structure embedding is generated by aggregating coarse connection information between entities without capturing semantics of the relations, which is incapable of dealing with entities of similar structures. Besides, multiple features are integrated by static arithmetic weighting method, which has difficulty in balancing the relative importance of structure and attribute features. To address these problems, we propose a dynamic self-attention based entity alignment model (DSEA), which leverages multimodal features for entity alignment through a dynamic self-attention network. To learn informative representations, we build a multimodal feature embedding component (MFE) to leverage structure, name, and position importance of entities. In MFE, semantics of adjacent entities and relations are exploited to enhance the structure embedding through a fine-granularity semantic augmentation network. Then a dynamic self-attention network is designed to adaptively evaluate the relative importance of structure and attribute features by learning the weights according to their contribution in entity alignment. Based on the feature weights, a similarity function of entities is formulated and the entity correspondence is established according to the similarities of entities. Extensive experiments conducted on five real-world datasets show that DSEA significantly outperforms state-of-the-art methods.

Evolving Social Media Background Representation with Frequency Weights and Co-Occurrence Graphs

Social media as a background information source has been utilized in many practical computational tasks, such as stock price prediction, epidemic tracking, and product recommendation. However, proper representation of an evolving social media background is still in an early research stage. In this article, we propose a representation method that considers temporal novelties as well as the fine details of word inter-dependencies. Our method is based on the tf-idf and graph embedding techniques. The proposed method has superiority over other representation methods because it takes the advantage of both the temporal aspect of tf-idf and the semantic aspect of graph embeddings. We compare our method with a variety of baselines in two practical application scenarios using real-world data. In tweet popularity prediction, our representation achieves 5.7% less error and 12.8% higher correlation compared to the best baseline. In e-commerce product recommendation, our representation achieves 17% higher hit-rate and 20% higher NDCG compared to the best baseline.