Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.9
2.1
Journals
Entropy
Special Issues
Information Network Mining and Applications
entropy-logo
Submit to Entropy Review for Entropy Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Information Network Mining and Applications

A special issue of Entropy (ISSN 1099-4300). This special issue belongs to the section "Information Theory, Probability and Statistics".

Deadline for manuscript submissions: closed (30 September 2023) | Viewed by 34910

Special Issue Editors

Dr. Yongpan Sheng

E-Mail Website
Guest Editor
College of Computer and Information Science, Southwest University, Chongqing 400715, China
Interests: textual data mining; knowledge graphs; graph representation learning; code understanding and representation
Special Issues, Collections and Topics in MDPI journals
Dr. Hao Wang

E-Mail Website
Guest Editor
School of Computer Science and Technology, University of Science and Technology of China (USTC), Hefei 230027, China
Interests: data mining; graph neural networks; graph representation learning; recommendation system; network embedding
Special Issues, Collections and Topics in MDPI journals
Dr. Yixiang Fang

E-Mail Website
Guest Editor
School of Data Science, The Chinese University of Hong Kong, Shenzhen 518172, China
Interests: data management; data mining; cohesive subgraph searching; graph embedding; graph neural networks; keyword searching; trajectory computing
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Information networks, also known as heterogeneous graphs, linguistics graphs, social networks, knowledge graphs, and so forth, which are able to consist of different types of entities and relations, have been attracting substantial attention in academia and industry in recent years. Advanced research on information network theory is essential to address the issues that relate to the structure modeling, representation, and applications of more complex, high-order information networks. Additionally, deep learning models on information networks have achieved remarkable performance in various tasks (e.g., graph representation learning, graph generation, and graph classification) when applied to domains such as knowledge graphs, social networks, bibliographic networks, traffic networks, and molecules. Despite these successes, as a promising network analysis paradigm, information network mining also is facing new challenges, such as how to manage typical networks such as multi-modal, multi-relational, and dynamic graphs, how to efficiently learn network/graph representation of large-scale information networks for preserving rich structural and semantic information, how to learn with limited labels on information networks, and how to mine knowledge in the information network, which is also of significance in solving sophisticated problems with more promising performance. 

This Special Issue is a forum for researchers from a variety of fields working on mining and learning from information networks to share and discuss their latest findings. It welcomes original algorithmic, methodological, theoretical, statistical, or systems-based contributions to information network research and, in particular, applications broadly related to knowledge graphs, social networks, stock prediction, online shopping, recommendation systems, self-driving car, bioinformatics and medical informatics. Research papers and comprehensive reviews may focus on (but are not restricted to) the following research areas:

  • Network/graph representation learning for homogeneous or heterogeneous information networks;
  • Network/graph modelling like multi-modal, multi-relational, and dynamic graphs;
  • Graph transformer and graph convolutional neural network;
  • Data mining based on knowledge graphs, linguistics graphs, bibliographic graphs, textual graphs, social networks, traffic networks, and molecules;
  • Parallel computing for information network analysis;
  • Visual searching and browsing of information networks;
  • Applications of information network mining in e-commerce, text mining, stock prediction, recommendation systems, self-driving car, bioinformatics and medical informatics, and so on;
  • Information networks for explainable AI.

Dr. Yongpan Sheng
Dr. Hao Wang
Dr. Yixiang Fang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Entropy is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • information networks
  • network/graph representation learning
  • data mining
  • knowledge graphs
  • information network applications
  • explainable AI

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Related Special Issue

Published Papers (15 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

15 pages, 5173 KiB  
Article
Dynamic Causal Modeling and Online Collaborative Forecasting of Air Quality in Hong Kong and Macao
by Cheng He, Jia Ren and Wenjian Liu
Entropy 2023, 25(9), 1337; https://doi.org/10.3390/e25091337 - 15 Sep 2023
Cited by 1 | Viewed by 1707
Abstract
The Hong Kong and Macao Special Administrative Regions, situated within China’s Guangdong–Hong Kong–Macao Greater Bay Area, significantly influence and are impacted by their air quality conditions. Rapid urbanization, high population density, and air pollution from diverse factors present challenges, making the health of [...] Read more.
The Hong Kong and Macao Special Administrative Regions, situated within China’s Guangdong–Hong Kong–Macao Greater Bay Area, significantly influence and are impacted by their air quality conditions. Rapid urbanization, high population density, and air pollution from diverse factors present challenges, making the health of the atmospheric environment in these regions a research focal point. This study offers three key contributions: (1) It applied an interpretable dynamic Bayesian network (DBN) to construct a dynamic causal model of air quality in Hong Kong and Macao, amidst complex, unstable, multi-dimensional, and uncertain factors over time. (2) It investigated the dynamic interaction between meteorology and air quality sub-networks, and both qualitatively and quantitatively identified, evaluated, and understood the causal relationships between air pollutants and their determinants. (3) It facilitated an online collaborative forecast of air pollutant concentrations, enabling pollution warnings. The findings proposed that a DBN-based dynamic causal model can effectively explain and manage complex atmospheric environmental systems in Hong Kong and Macao. This method offers crucial insights for decision-making and the management of atmospheric environments not only in these regions but also for neighboring cities and regions with similar geographical contexts. Full article
(This article belongs to the Special Issue Information Network Mining and Applications)
►▼ Show Figures

Figure 1

15 pages, 1515 KiB  
Article
Conserving Semantic Unit Information and Simplifying Syntactic Constituents to Improve Implicit Discourse Relation Recognition
by Zhongyang Fang, Yue Cong, Yuhan Chai, Chengliang Gao, Ximing Chen and Jing Qiu
Entropy 2023, 25(9), 1294; https://doi.org/10.3390/e25091294 - 4 Sep 2023
Viewed by 1144
Abstract
Implicit discourse relation recognition (IDRR) has long been considered a challenging problem in shallow discourse parsing. The absence of connectives makes such relations implicit and requires much more effort to understand the semantics of the text. Thus, it is important to preserve the [...] Read more.
Implicit discourse relation recognition (IDRR) has long been considered a challenging problem in shallow discourse parsing. The absence of connectives makes such relations implicit and requires much more effort to understand the semantics of the text. Thus, it is important to preserve the semantic completeness before any attempt to predict the discourse relation. However, word level embedding, widely used in existing works, may lead to a loss of semantics by splitting some phrases that should be treated as complete semantic units. In this article, we proposed three methods to segment a sentence into complete semantic units: a corpus-based method to serve as the baseline, a constituent parsing tree-based method, and a dependency parsing tree-based method to provide a more flexible and automatic way to divide the sentence. The segmented sentence will then be embedded at the level of semantic units so the embeddings could be fed into the IDRR networks and play the same role as word embeddings. We implemented our methods into one of the recent IDRR models to compare the performance with the original version using word level embeddings. Results show that proper embedding level better conserves the semantic information in the sentence and helps to enhance the performance of IDRR models. Full article
(This article belongs to the Special Issue Information Network Mining and Applications)
►▼ Show Figures

Figure 1

20 pages, 3045 KiB  
Article
Generating Datasets for Real-Time Scheduling on 5G New Radio
by Xi Jin, Haoxuan Chai, Changqing Xia and Chi Xu
Entropy 2023, 25(9), 1289; https://doi.org/10.3390/e25091289 - 2 Sep 2023
Cited by 1 | Viewed by 1868
Abstract
A 5G system is an advanced solution for industrial wireless motion control. However, because the scheduling model of 5G new radio (NR) is more complicated than those of other wireless networks, existing real-time scheduling algorithms cannot be used to improve the 5G performance. [...] Read more.
A 5G system is an advanced solution for industrial wireless motion control. However, because the scheduling model of 5G new radio (NR) is more complicated than those of other wireless networks, existing real-time scheduling algorithms cannot be used to improve the 5G performance. This results in NR resources not being fully available for industrial systems. Supervised learning has been widely used to solve complicated problems, and its advantages have been demonstrated in multiprocessor scheduling. One of the main reasons why supervised learning has not been used for 5G NR scheduling is the lack of training datasets. Therefore, in this paper, we propose two methods based on optimization modulo theories (OMT) and satisfiability modulo theories (SMT) to generate training datasets for 5G NR scheduling. Our OMT-based method contains fewer variables than existing work so that the Z3 solver can find optimal solutions quickly. To further reduce the solution time, we transform the OMT-based method into an SMT-based method and tighten the search space of SMT based on three theorems and an algorithm. Finally, we evaluate the solution time of our proposed methods and use the generated dataset to train a supervised learning model to solve the 5G NR scheduling problem. The evaluation results indicate that our SMT-based method reduces the solution time by 74.7% compared to existing ones, and the supervised learning algorithm achieves better scheduling performance than other polynomial-time algorithms. Full article
(This article belongs to the Special Issue Information Network Mining and Applications)
►▼ Show Figures

Figure 1

17 pages, 3215 KiB  
Article
An Adaptive Model Filtering Algorithm Based on Grubbs Test in Federated Learning
by Wenbin Yao, Bangli Pan, Yingying Hou, Xiaoyong Li and Yamei Xia
Entropy 2023, 25(5), 715; https://doi.org/10.3390/e25050715 - 26 Apr 2023
Viewed by 1490
Abstract
Federated learning has been popular for its ability to train centralized models while protecting clients’ data privacy. However, federated learning is highly susceptible to poisoning attacks, which can result in a decrease in model performance or even make it unusable. Most existing defense [...] Read more.
Federated learning has been popular for its ability to train centralized models while protecting clients’ data privacy. However, federated learning is highly susceptible to poisoning attacks, which can result in a decrease in model performance or even make it unusable. Most existing defense methods against poisoning attacks cannot achieve a good trade-off between robustness and training efficiency, especially on non-IID data. Therefore, this paper proposes an adaptive model filtering algorithm based on the Grubbs test in federated learning (FedGaf), which can achieve great trade-offs between robustness and efficiency against poisoning attacks. To achieve a trade-off between system robustness and efficiency, multiple child adaptive model filtering algorithms have been designed. Meanwhile, a dynamic decision mechanism based on global model accuracy is proposed to reduce additional computational costs. Finally, a global model weighted aggregation method is incorporated, which improves the convergence speed of the model. Experimental results on both IID and non-IID data show that FedGaf outperforms other Byzantine-robust aggregation rules in defending against various attack methods. Full article
(This article belongs to the Special Issue Information Network Mining and Applications)
►▼ Show Figures

Figure 1

22 pages, 5487 KiB  
Article
Graph Autoencoder with Preserving Node Attribute Similarity
by Mugang Lin, Kunhui Wen, Xuanying Zhu, Huihuang Zhao and Xianfang Sun
Entropy 2023, 25(4), 567; https://doi.org/10.3390/e25040567 - 26 Mar 2023
Cited by 7 | Viewed by 4451
Abstract
The graph autoencoder (GAE) is a powerful graph representation learning tool in an unsupervised learning manner for graph data. However, most existing GAE-based methods typically focus on preserving the graph topological structure by reconstructing the adjacency matrix while ignoring the preservation of the [...] Read more.
The graph autoencoder (GAE) is a powerful graph representation learning tool in an unsupervised learning manner for graph data. However, most existing GAE-based methods typically focus on preserving the graph topological structure by reconstructing the adjacency matrix while ignoring the preservation of the attribute information of nodes. Thus, the node attributes cannot be fully learned and the ability of the GAE to learn higher-quality representations is weakened. To address the issue, this paper proposes a novel GAE model that preserves node attribute similarity. The structural graph and the attribute neighbor graph, which is constructed based on the attribute similarity between nodes, are integrated as the encoder input using an effective fusion strategy. In the encoder, the attributes of the nodes can be aggregated both in their structural neighborhood and by their attribute similarity in their attribute neighborhood. This allows performing the fusion of the structural and node attribute information in the node representation by sharing the same encoder. In the decoder module, the adjacency matrix and the attribute similarity matrix of the nodes are reconstructed using dual decoders. The cross-entropy loss of the reconstructed adjacency matrix and the mean-squared error loss of the reconstructed node attribute similarity matrix are used to update the model parameters and ensure that the node representation preserves the original structural and node attribute similarity information. Extensive experiments on three citation networks show that the proposed method outperforms state-of-the-art algorithms in link prediction and node clustering tasks. Full article
(This article belongs to the Special Issue Information Network Mining and Applications)
►▼ Show Figures

Figure 1

16 pages, 2436 KiB  
Article
Unsupervised Embedding Learning for Large-Scale Heterogeneous Networks Based on Metapath Graph Sampling
by Hongwei Zhong, Mingyang Wang and Xinyue Zhang
Entropy 2023, 25(2), 297; https://doi.org/10.3390/e25020297 - 4 Feb 2023
Cited by 5 | Viewed by 1981
Abstract
How to learn the embedding vectors of nodes in unsupervised large-scale heterogeneous networks is a key problem in heterogeneous network embedding research. This paper proposes an unsupervised embedding learning model, named LHGI (Large-scale Heterogeneous Graph Infomax). LHGI adopts the subgraph sampling technology under [...] Read more.
How to learn the embedding vectors of nodes in unsupervised large-scale heterogeneous networks is a key problem in heterogeneous network embedding research. This paper proposes an unsupervised embedding learning model, named LHGI (Large-scale Heterogeneous Graph Infomax). LHGI adopts the subgraph sampling technology under the guidance of metapaths, which can compress the network and retain the semantic information in the network as much as possible. At the same time, LHGI adopts the idea of contrastive learning, and takes the mutual information between normal/negative node vectors and the global graph vector as the objective function to guide the learning process. By maximizing the mutual information, LHGI solves the problem of how to train the network without supervised information. The experimental results show that, compared with the baseline models, the LHGI model shows a better feature extraction capability both in medium-scale unsupervised heterogeneous networks and in large-scale unsupervised heterogeneous networks. The node vectors generated by the LHGI model achieve better performance in the downstream mining tasks. Full article
(This article belongs to the Special Issue Information Network Mining and Applications)
►▼ Show Figures

Figure 1

25 pages, 1812 KiB  
Article
A Pseudorandom Number Generator Based on the Chaotic Map and Quantum Random Walks
by Wenbo Zhao, Zhenhai Chang, Caochuan Ma and Zhuozhuo Shen
Entropy 2023, 25(1), 166; https://doi.org/10.3390/e25010166 - 13 Jan 2023
Cited by 11 | Viewed by 2959
Abstract
In this paper, a surjective mapping that satisfies the Li–Yorke chaos in the unit area is constructed and a perturbation algorithm (disturbing its parameters and inputs through another high-dimensional chaos) is proposed to enhance the randomness of the constructed chaotic system and expand [...] Read more.
In this paper, a surjective mapping that satisfies the Li–Yorke chaos in the unit area is constructed and a perturbation algorithm (disturbing its parameters and inputs through another high-dimensional chaos) is proposed to enhance the randomness of the constructed chaotic system and expand its key space. An algorithm for the composition of two systems (combining sequence based on quantum random walks with chaotic system’s outputs) is designed to improve the distribution of the system outputs and a compound chaotic system is ultimately obtained. The new compound chaotic system is evaluated using some test methods such as time series complexity, autocorrelation and distribution of output frequency. The test results showed that the new system has complex dynamic behavior such as high randomicity, unpredictability and uniform output distribution. Then, a new scheme for generating pseudorandom numbers is presented utilizing the composite chaotic system. The proposed pseudorandom number generator (PRNG) is evaluated using a series test suites such as NIST sp 800-22 soft and other tools or methods. The results of tests are promising, as the proposed PRNG passed all these tests. Thus, the proposed PRNG can be used in the information security field. Full article
(This article belongs to the Special Issue Information Network Mining and Applications)
►▼ Show Figures

Figure 1

16 pages, 662 KiB  
Article
Mining Mobile Network Fraudsters with Augmented Graph Neural Networks
by Xinxin Hu, Haotian Chen, Hongchang Chen, Xing Li, Junjie Zhang and Shuxin Liu
Entropy 2023, 25(1), 150; https://doi.org/10.3390/e25010150 - 11 Jan 2023
Cited by 8 | Viewed by 2865
Abstract
With the rapid evolution of mobile communication networks, the number of subscribers and their communication practices is increasing dramatically worldwide. However, fraudsters are also sniffing out the benefits. Detecting fraudsters from the massive volume of call detail records (CDR) in mobile communication networks [...] Read more.
With the rapid evolution of mobile communication networks, the number of subscribers and their communication practices is increasing dramatically worldwide. However, fraudsters are also sniffing out the benefits. Detecting fraudsters from the massive volume of call detail records (CDR) in mobile communication networks has become an important yet challenging topic. Fortunately, Graph neural network (GNN) brings new possibilities for telecom fraud detection. However, the presence of the graph imbalance and GNN oversmoothing problems makes fraudster detection unsatisfactory. To address these problems, we propose a new fraud detector. First, we transform the user features with the help of a multilayer perceptron. Then, a reinforcement learning-based neighbor sampling strategy is designed to balance the number of neighbors of different classes of users. Next, we perform user feature aggregation using GNN. Finally, we innovatively treat the above augmented GNN as weak classifier and integrate multiple weak classifiers using the AdaBoost algorithm. A balanced focal loss function is also used to monitor the model training error. Extensive experiments are conducted on two open real-world telecom fraud datasets, and the results show that the proposed method is significantly effective for the graph imbalance problem and the oversmoothing problem in telecom fraud detection. Full article
(This article belongs to the Special Issue Information Network Mining and Applications)
►▼ Show Figures

Figure 1

16 pages, 5379 KiB  
Article
Rainwater-Removal Image Conversion Learning with Training Pair Augmentation
by Yu-Keun Han, Sung-Woon Jung, Hyuk-Ju Kwon and Sung-Hak Lee
Entropy 2023, 25(1), 118; https://doi.org/10.3390/e25010118 - 6 Jan 2023
Cited by 1 | Viewed by 1901
Abstract
In this study, we proposed an image conversion method that efficiently removes raindrops on a camera lens from an image using a deep learning technique. The proposed method effectively presents a raindrop-removed image using the Pix2pix generative adversarial network (GAN) model, which can [...] Read more.
In this study, we proposed an image conversion method that efficiently removes raindrops on a camera lens from an image using a deep learning technique. The proposed method effectively presents a raindrop-removed image using the Pix2pix generative adversarial network (GAN) model, which can understand the characteristics of two images in terms of newly formed images of different domains. The learning method based on the captured image has the disadvantage that a large amount of data is required for learning and that unnecessary noise is generated owing to the nature of the learning model. In particular, obtaining sufficient original and raindrops images is the most important aspect of learning. Therefore, we proposed a method that efficiently obtains learning data by generating virtual water-drop image data and effectively identifying it using a convolutional neural network (CNN). Full article
(This article belongs to the Special Issue Information Network Mining and Applications)
►▼ Show Figures

Figure 1

17 pages, 3573 KiB  
Article
News Stance Discrimination Based on a Heterogeneous Network of Social Background Information Fusion
by Yanze Ren, Yan Liu, Jing Chen, Xiaoyu Guo, Junyu Shi and Mengmeng Jia
Entropy 2023, 25(1), 78; https://doi.org/10.3390/e25010078 - 30 Dec 2022
Cited by 2 | Viewed by 1662
Abstract
Media with partisan tendencies publish news articles to support their preferred political parties to guide the direction of public opinion. Therefore, discovering political bias in news texts has important practical significance for national election prediction and public opinion management. Some biased news often [...] Read more.
Media with partisan tendencies publish news articles to support their preferred political parties to guide the direction of public opinion. Therefore, discovering political bias in news texts has important practical significance for national election prediction and public opinion management. Some biased news often has obscure expressions and ambiguous writing styles. By bypassing the language model, the accuracy of methods that rely on news semantic information for position discrimination is low. This manuscript proposes a news standpoint discrimination method based on social background information fusion heterogeneous network. This method expands the judgment ability of creators and topics on news standpoints from external information and fine-grained topics based on news semantics. Multi-attribute features of nodes enrich the feature representation of nodes, and joint representation of heterogeneous networks can reduce the dependence of position discrimination on the news semantic information. To effectively deal with the position discrimination of new news, the design of a multi-attribute fusion heterogeneous network is extended to inductive learning, avoiding the cost of model training caused by recomposition. Based on the Allsides dataset, this manuscript expands the information of its creator’s social background and compares the model for discriminating political positions based on news content. In the experiment, the best transductive attribute fusion heterogeneous network achieved an accuracy of 92.24% and a macro F1 value of 92.05%. The effect is improved based purely on semantic information for position discrimination, which proves the effectiveness of the model design. Full article
(This article belongs to the Special Issue Information Network Mining and Applications)
►▼ Show Figures

Figure 1

12 pages, 556 KiB  
Article
Enhanced Signed Graph Neural Network with Node Polarity
by Jiawang Chen, Zhi Qiao, Jun Yan and Zhenqiang Wu
Entropy 2023, 25(1), 38; https://doi.org/10.3390/e25010038 - 25 Dec 2022
Cited by 1 | Viewed by 1729
Abstract
Signed graph neural networks learn low-dimensional representations for nodes in signed networks with positive and negative links, which helps with many downstream tasks like link prediction. However, most existing signed graph neural networks ignore individual characteristics of nodes and thus limit the ability [...] Read more.
Signed graph neural networks learn low-dimensional representations for nodes in signed networks with positive and negative links, which helps with many downstream tasks like link prediction. However, most existing signed graph neural networks ignore individual characteristics of nodes and thus limit the ability to learn the underlying structure of real signed graphs. To address this limitation, a deep graph neural network framework SiNP to learn Signed network embedding with Node Polarity is proposed. To be more explicit, a node-signed property metric mechanism is developed to encode the individual characteristics of the nodes. In addition, a graph convolution layer is added so that both positive and negative information from neighboring nodes can be combined. The final embedding of nodes is produced by concatenating the outcomes of these two portions. Finally, extensive experiments have been conducted on four significant real-world signed network datasets to demonstrate the efficiency and superiority of the proposed method in comparison to the state-of-the-art. Full article
(This article belongs to the Special Issue Information Network Mining and Applications)
►▼ Show Figures

Figure 1

14 pages, 12948 KiB  
Article
Self-Supervised Node Classification with Strategy and Actively Selected Labeled Set
by Yi Kang, Ke Liu, Zhiyuan Cao and Jiacai Zhang
Entropy 2023, 25(1), 30; https://doi.org/10.3390/e25010030 - 23 Dec 2022
Viewed by 2127
Abstract
To alleviate the impact of insufficient labels in less-labeled classification problems, self-supervised learning improves the performance of graph neural networks (GNNs) by focusing on the information of unlabeled nodes. However, none of the existing self-supervised pretext tasks perform optimally on different datasets, and [...] Read more.
To alleviate the impact of insufficient labels in less-labeled classification problems, self-supervised learning improves the performance of graph neural networks (GNNs) by focusing on the information of unlabeled nodes. However, none of the existing self-supervised pretext tasks perform optimally on different datasets, and the choice of hyperparameters is also included when combining self-supervised and supervised tasks. To select the best-performing self-supervised pretext task for each dataset and optimize the hyperparameters with no expert experience needed, we propose a novel auto graph self-supervised learning framework and enhance this framework with a one-shot active learning method. Experimental results on three real world citation datasets show that training GNNs with automatically optimized pretext tasks can achieve or even surpass the classification accuracy obtained with manually designed pretext tasks. On this basis, compared with using randomly selected labeled nodes, using actively selected labeled nodes can further improve the classification performance of GNNs. Both the active selection and the automatic optimization contribute to semi-supervised node classification. Full article
(This article belongs to the Special Issue Information Network Mining and Applications)
►▼ Show Figures

Figure 1

19 pages, 3271 KiB  
Article
Complex Knowledge Base Question Answering for Intelligent Bridge Management Based on Multi-Task Learning and Cross-Task Constraints
by Xiaoxia Yang, Jianxi Yang, Ren Li, Hao Li, Hongyi Zhang and Yue Zhang
Entropy 2022, 24(12), 1805; https://doi.org/10.3390/e24121805 - 10 Dec 2022
Cited by 5 | Viewed by 2265
Abstract
In the process of bridge management, large amounts of domain information are accumulated, such as basic attributes, structural defects, technical conditions, etc. However, the valuable information is not fully utilized, resulting in insufficient knowledge service in the field of bridge management. To tackle [...] Read more.
In the process of bridge management, large amounts of domain information are accumulated, such as basic attributes, structural defects, technical conditions, etc. However, the valuable information is not fully utilized, resulting in insufficient knowledge service in the field of bridge management. To tackle these problems, this paper proposes a complex knowledge base question answering (C-KBQA) framework for intelligent bridge management based on multi-task learning (MTL) and cross-task constraints (CTC). First, with C-KBQA as the main task, part-of-speech (POS) tagging, topic entity extraction (TEE), and question classification (QC) as auxiliary tasks, an MTL framework is built by sharing encoders and parameters, thereby effectively avoiding the error propagation problem of the pipeline model. Second, cross-task semantic constraints are provided for different subtasks via POS embeddings, entity embeddings, and question-type embeddings. Finally, using template matching, relevant query statements are generated and interaction with the knowledge base is established. The experimental results show that the proposed model outperforms compared mainstream models in terms of TEE and QC on bridge management datasets, and its performance in C-KBQA is outstanding. Full article
(This article belongs to the Special Issue Information Network Mining and Applications)
►▼ Show Figures

Figure 1

16 pages, 3633 KiB  
Article
HDGFI: Hierarchical Dual-Level Graph Feature Interaction Model for Personalized Recommendation
by Xinxin Ma and Zhendong Cui
Entropy 2022, 24(12), 1799; https://doi.org/10.3390/e24121799 - 9 Dec 2022
Viewed by 1828
Abstract
Under the background of information overload, the recommendation system has attracted wide attention as one of the most important means for this problem. Feature interaction considers not only the impact of each feature but also the combination of two or more features, which [...] Read more.
Under the background of information overload, the recommendation system has attracted wide attention as one of the most important means for this problem. Feature interaction considers not only the impact of each feature but also the combination of two or more features, which has become an important research field in recommendation systems. There are two essential problems in current feature interaction research. One is that not all feature interactions can generate positive gains, and some may lead to an increase in noise. The other is that the process of feature interactions is implicit and uninterpretable. In this paper, a Hierarchical Dual-level Graph Feature Interaction (HDGFI) model is proposed to solve these problems in the recommendation system. The model regards features as nodes and edges as interactions between features in the graph structure. Interaction noise is filtered by beneficial interaction selection based on a hierarchical edge selection module. At the same time, the importance of interaction between nodes is modeled in two perspectives in order to learn the representation of feature nodes at a finer granularity. Experimental results show that the proposed HDGFI model has higher accuracy than the existing models. Full article
(This article belongs to the Special Issue Information Network Mining and Applications)
►▼ Show Figures

Figure 1

15 pages, 4784 KiB  
Article
A Dual Attention Encoding Network Using Gradient Profile Loss for Oil Spill Detection Based on SAR Images
by Jiding Zhai, Chunxiao Mu, Yongchao Hou, Jianping Wang, Yingjie Wang and Haokun Chi
Entropy 2022, 24(10), 1453; https://doi.org/10.3390/e24101453 - 12 Oct 2022
Cited by 6 | Viewed by 1716
Abstract
Marine oil spills due to ship collisions or operational errors have caused tremendous damage to the marine environment. In order to better monitor the marine environment on a daily basis and reduce the damage and harm caused by oil pollution, we use marine [...] Read more.
Marine oil spills due to ship collisions or operational errors have caused tremendous damage to the marine environment. In order to better monitor the marine environment on a daily basis and reduce the damage and harm caused by oil pollution, we use marine image information acquired by synthetic aperture radar (SAR) and combine it with image segmentation techniques in deep learning to monitor oil spills. However, it is a significant challenge to accurately distinguish oil spill areas in original SAR images, which are characterized by high noise, blurred boundaries, and uneven intensity. Hence, we propose a dual attention encoding network (DAENet) using an encoder–decoder U-shaped architecture for identifying oil spill areas. In the encoding phase, we use the dual attention module to adaptively integrate local features with their global dependencies, thus improving the fusion feature maps of different scales. Moreover, a gradient profile (GP) loss function is used to improve the recognition accuracy of the oil spill areas’ boundary lines in the DAENet. We used the Deep-SAR oil spill (SOS) dataset with manual annotation for training, testing, and evaluation of the network, and we established a dataset containing original data from GaoFen-3 for network testing and performance evaluation. The results show that DAENet has the highest mIoU of 86.1% and the highest F1-score of 90.2% in the SOS dataset, and it has the highest mIoU of 92.3% and the highest F1-score of 95.1% in the GaoFen-3 dataset. The method proposed in this paper not only improves the detection and identification accuracy of the original SOS dataset, but also provides a more feasible and effective method for marine oil spill monitoring. Full article
(This article belongs to the Special Issue Information Network Mining and Applications)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-15
Back to TopTop