Relevant bibliographies by topics / Graph-type classification

Contents

  1. Journal articles
  2. Books
  3. Book chapters
  4. Conference papers

Academic literature on the topic 'Graph-type classification'

Author: Grafiati
Published: 3 June 2025
Last updated: 19 July 2025

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Graph-type classification.'

Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.

You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.

Journal articles on the topic "Graph-type classification"

1

Perepelitsa, V. A., I. V. Kozin, and S. V. Kurapov. "Methods of classification and algorithms of graph coloring." Researches in Mathematics 16 (February 7, 2021): 135. http://dx.doi.org/10.15421/240816.

Full text
Abstract:
We study the connection between classifications on finite set and the problem of graph coloring. We consider the optimality criterion for classification of special type: h-classifications, which are built on the base of proximity measure. It is shown that the problem of finding the optimal h-classification can be reduced to the problem of coloring of non-adjacency graph vertices by the smallest possible number of colors. We consider algorithms of proper coloring of graph vertices.
APA, Harvard, Vancouver, ISO, and other styles
2

Gharaee, Zahra, Shreyas Kowshik, Oliver Stromann, and Michael Felsberg. "Graph representation learning for road type classification." Pattern Recognition 120 (December 2021): 108174. http://dx.doi.org/10.1016/j.patcog.2021.108174.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Yang, Dilian. "Factoriality and Type Classification of k-Graph von Neumann Algebras." Proceedings of the Edinburgh Mathematical Society 60, no. 2 (2016): 499–518. http://dx.doi.org/10.1017/s0013091516000304.

Full text
Abstract:
AbstractLet be a single vertex k-graph and let be the von Neumann algebra induced from the Gelfand–Naimark–Segal (GNS) representation of a distinguished state ω of its k-graph C*-algebra . In this paper we prove the factoriality of , and furthermore determine its type when either has the little pullback property, or the intrinsic group of has rank 0. The key step to achieving this is to show that the fixed-point algebra of the modular action corresponding to ω has a unique tracial state.
APA, Harvard, Vancouver, ISO, and other styles
4

Power, Stephen C., Igor A. Baburin, and Davide M. Proserpio. "Isotopy classes for 3-periodic net embeddings." Acta Crystallographica Section A Foundations and Advances 76, no. 3 (2020): 275–301. http://dx.doi.org/10.1107/s2053273320000625.

Full text
Abstract:
Entangled embedded periodic nets and crystal frameworks are defined, along with their dimension type, homogeneity type, adjacency depth and periodic isotopy type. Periodic isotopy classifications are obtained for various families of embedded nets with small quotient graphs. The 25 periodic isotopy classes of depth-1 embedded nets with a single-vertex quotient graph are enumerated. Additionally, a classification is given of embeddings of n-fold copies of pcu with all connected components in a parallel orientation and n vertices in a repeat unit, as well as demonstrations of their maximal symmetry periodic isotopes. The methodology of linear graph knots on the flat 3-torus [0,1)3 is introduced. These graph knots, with linear edges, are spatial embeddings of the labelled quotient graphs of an embedded net which are associated with its periodicity bases.
APA, Harvard, Vancouver, ISO, and other styles
5

Wang, Zijian, Rafael Sacks, and Timson Yeung. "Exploring graph neural networks for semantic enrichment: Room type classification." Automation in Construction 134 (February 2022): 104039. http://dx.doi.org/10.1016/j.autcon.2021.104039.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Rowland, Dana. "Classification of book representations of K6." Journal of Knot Theory and Its Ramifications 26, no. 12 (2017): 1750075. http://dx.doi.org/10.1142/s0218216517500754.

Full text
Abstract:
A book representation of a graph is a particular way of embedding a graph in three-dimensional space so that the vertices lie on a circle and the edges are chords on disjoint topological disks. We describe a set of operations on book representations that preserves ambient isotopy, and apply these operations to [Formula: see text], the complete graph with six vertices. We prove there are exactly 59 distinct book representations for [Formula: see text], and we identify the number and type of knotted and linked cycles in each representation. We show that book representations of [Formula: see text] contain between one and seven links, and up to nine knotted cycles. Furthermore, all links and cycles in a book representation of [Formula: see text] have crossing number at most four.
APA, Harvard, Vancouver, ISO, and other styles
7

Dong, Guozhong, Weizhe Zhang, Rahul Yadav, Xin Mu, and Zhili Zhou. "OWGC-HMC: An Online Web Genre Classification Model Based on Hierarchical Multilabel Classification." Security and Communication Networks 2022 (March 29, 2022): 1–9. http://dx.doi.org/10.1155/2022/7549880.

Full text
Abstract:
Web genre plays an important role in focused crawling, web link analysis, and contextual advertising. In this paper, web genre is defined as the functional purpose and the information type contained in the website. The intelligent classification of web genre can predict the content and functional type of website. However, there are several critical challenges to solve the web genre classification problem: lack of web genre classification dataset and efficient web genre classification mechanism. To improve web genre classification performance, we crawled Chinese websites of different web genres and converted crawled data into a hierarchical multilabel classification dataset. A website knowledge graph is constructed based on the relationship of website and meta tag features. Using entity features extracted from the knowledge graph, we propose an online web genre classification model based on hierarchical multilabel classification (OWGC-HMC) to mine the functional purpose of the corresponding website. Experimental results show that our OWGC-HMC model can mine hierarchical multilabel structure of web genre and outperform other web genre classification methods.
APA, Harvard, Vancouver, ISO, and other styles
8

Chen, Yang, Zhonglin Ye, Haixing Zhao, and Ying Wang. "Feature-Based Graph Backdoor Attack in the Node Classification Task." International Journal of Intelligent Systems 2023 (February 21, 2023): 1–13. http://dx.doi.org/10.1155/2023/5418398.

Full text
Abstract:
Graph neural networks (GNNs) have shown significant performance in various practical applications due to their strong learning capabilities. Backdoor attacks are a type of attack that can produce hidden attacks on machine learning models. GNNs take backdoor datasets as input to produce an adversary-specified output on poisoned data but perform normally on clean data, which can have grave implications for applications. Backdoor attacks are under-researched in the graph domain, and almost existing graph backdoor attacks focus on the graph-level classification task. To close this gap, we propose a novel graph backdoor attack that uses node features as triggers and does not need knowledge of the GNNs parameters. In the experiments, we find that feature triggers can destroy the feature spaces of the original datasets, resulting in GNNs inability to identify poisoned data and clean data well. An adaptive method is proposed to improve the performance of the backdoor model by adjusting the graph structure. We conducted extensive experiments to validate the effectiveness of our model on three benchmark datasets.
APA, Harvard, Vancouver, ISO, and other styles
9

Li, Yiyan, Xiaomin Lu, Haowen Yan, Wenning Wang, and Pengbo Li. "A Skeleton-Line-Based Graph Convolutional Neural Network for Areal Settlements’ Shape Classification." Applied Sciences 12, no. 19 (2022): 10001. http://dx.doi.org/10.3390/app121910001.

Full text
Abstract:
Among the geographic elements, shape recognition and classification is one of the im portant elements of map cartographic generalization, and the shape classification of an areal settlement is an important part of geospatial vector data. However, there is currently no relatively simple and efficient way to achieve areal settlement classification. Therefore, we combined the skeleton line vector data of an areal settlement and the graph convolutional neural network to propose an areal settlement shape classification method that (1) extracts the skeleton line of the areal settlement to form a dual graph with nodes as edges, (2) extracts multiple features to obtain a graph representation of the shape, (3) extracts and aggregates the shape information represented by the areal settlement skeleton line using the graph convolutional neural network for multiple rounds to extract high-dimensional shape information, and (4) completes the shape classification of the high-dimensional shape information. The experiment used 240 samples, and the classification accuracy was 93.3%, with areal settlement shapes of E-, F-, and H-type achieving F-measures of 96.5%, 92.3%, and 100%, respectively. The result shows that the classification method of the areal settlement shape has high accuracy.
APA, Harvard, Vancouver, ISO, and other styles
10

TAO, PENG, CAO WENLI, CHEN JIA, et al. "Research on fabric classification based on graph neural network." Industria Textila 74, no. 01 (2023): 3–11. http://dx.doi.org/10.35530/it.074.01.202224.

Full text
Abstract:
Fabric classification plays a crucial role in the modern textile industry and fashion market. In the early stage, traditional neural network methods were adopted to identify fabrics with the drawback of restricted fabric type and poor accuracy. Combining multi-frame temporality and analysing fabric graph data made from fabric motion features, this paper proposes a novel hybrid model that introduces the concept of graph networks to classify 30 textile materials in a public database. We utilize the graph inductive representation learning method (GraphSAGE, Graph Sample and Aggregate) to extract node embedding features of the fabric. Moreover, bidirectional gated recurrent unit and layer attention mechanism (BiGRU-attention) are employed in the last layer of aggregation to calculate the score of previous cells. Intending to further enhance performance, we link the jump connection with adaptive selection aggregation frameworks to determine the influential region of each node. Our method breaks through the limitation that the original methods can only classify a few fabrics with great classification results.
APA, Harvard, Vancouver, ISO, and other styles
More sources

Books on the topic "Graph-type classification"

1

Algebraic And Geometric Aspects Of Integrable Systems And Random Matrices Ams Special Session Algebraic And Geometric Aspects Of Integrable Systems And Random Matrices January 67 2012 Boston Ma. American Mathematical Society, 2013.

Find full text
APA, Harvard, Vancouver, ISO, and other styles

Book chapters on the topic "Graph-type classification"

1

Molefe, Mohale E., and Jules R. Tapamo. "A New Approach for Road Type Classification Using Multi-stage Graph Embedding Method." In Lecture Notes in Computer Science. Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-33783-3_3.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Dicente Cid, Yashin, Oscar Jimenez-del-Toro, Pierre-Alexandre Poletti, and Henning Müller. "A Graph Model of the Lungs with Morphology-Based Structure for Tuberculosis Type Classification." In Lecture Notes in Computer Science. Springer International Publishing, 2019. http://dx.doi.org/10.1007/978-3-030-20351-1_28.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Dicente Cid, Yashin, Kayhan Batmanghelich, and Henning Müller. "Textured Graph-Based Model of the Lungs: Application on Tuberculosis Type Classification and Multi-drug Resistance Detection." In Lecture Notes in Computer Science. Springer International Publishing, 2018. http://dx.doi.org/10.1007/978-3-319-98932-7_15.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Dadgostari, Faraz, and Mahtab Hosseininia. "Graph Coloring." In Graph Theory for Operations Research and Management. IGI Global, 2013. http://dx.doi.org/10.4018/978-1-4666-2661-4.ch009.

Full text
Abstract:
In this chapter a particular type of graph labeling, called graph coloring, is introduced and discussed. In the first part, the simple type of coloring, vertex coloring, is focused. Thus, concerning vertex coloring, some terms and definitions are introduced. Next, some theorems and applying those theorems, some coloring algorithms and applications are introduced. At last, some helpful concepts such as critical graphs, list coloring, and vertex decomposition are presented and discussed. In the second section, edge coloring is focused. Thus, concerning edge coloring, some terms and definitions are described, some important information about edge chromatic number and edge list coloring is presented, and applying them, classification of graphs using the coloring approach is summarized. At last some helpful concepts such as edge list coloring and edge decomposition are illustrated and discussed.
APA, Harvard, Vancouver, ISO, and other styles
5

Pirrò, Giuseppe. "Adaptive Spectral-Heterophily for Node Classification." In Frontiers in Artificial Intelligence and Applications. IOS Press, 2024. http://dx.doi.org/10.3233/faia240758.

Full text
Abstract:
Node classification in graphs, particularly those exhibiting heterophily, poses significant challenges for traditional methodologies. These include various graph neural network variants and approaches that simplify graph convolutions. This paper proposes a novel approach called nCASH, which combines an innovative label propagation method that utilizes features to compute soft labels and node homophily scores. It also incorporates multi-filter spectral convolutions and a redefined Laplacian matrix tailored for heterophilic graphs. nCASH allows for different types of feature transformations; each region of the graph is characterized by its homophily scores, which dictate the type of filter applied. Low-pass filters are used in homophilous regions, and high-pass filters in heterophilous regions to accentuate differences. nCASH, free from extensive training requirements, relies on sparse matrix multiplications. This enhances scalability and efficiency. Empirical results demonstrate the effectiveness of this approach, showing improvements in classification accuracy on several state-of-the-art heterophilic datasets.
APA, Harvard, Vancouver, ISO, and other styles
6

Lyman, R. Lee. "Materials and Methods." In Graphing Culture Change in North American Archaeology. Oxford University Press, 2021. http://dx.doi.org/10.1093/oso/9780198871156.003.0004.

Full text
Abstract:
To determine the origin of archaeological spindle graphs, and to track the frequency of use of each of several types of graph used to diagram culture change, a sample of North American archaeological literature was examined. Numerous series of monographs and volumes of journals in both the archaeological and the paleontological literature were inspected. If a graph of biological (paleontological) or cultural (archaeological) change was included in a publication, that piece of literature was recorded along with the type of graph included. To record such data, a classification of graph types was developed based on categories of statistical graphs (e.g., bar graph, line graph, pie graph, time range, spatio-temporal rectangle). More than 900 pieces of literature on North American archaeology published between ~1880 and ~1960 were inspected, and more than 450 pieces of literature on paleontology were inspected. Because different graph types are constructed under different guidelines, they require an understanding of graph grammar—the rules for constructing, deciphering, and interpreting graphs.
APA, Harvard, Vancouver, ISO, and other styles
7

Suga Yuji. "Classification of Generalized Graph-type (2,n)-Visual Secret Sharing Schemes and Optimal Construction for Multiple Secrets." In Frontiers in Artificial Intelligence and Applications. IOS Press, 2015. https://doi.org/10.3233/978-1-61499-484-8-746.

Full text
Abstract:
Visual secret sharing scheme with access structure based on graph has been proposed and this can be considered as an extension of (2,n)-threshold VSS scheme. Ateniese et al. showed a decomposition method that we decompose star graphs from a given graph which edges are specified by qualified sets, that is two participants (vertices in a given graph) has a common edge if and only if participants can reconstruct the secret image by stacking the shares each other. This paper classifies graph-based VSS schemes and show several optimal examples and also proposes optimal construction about graph-based VSS scheme for (multiple) q secrets which pixel expansion is less than 3*q.
APA, Harvard, Vancouver, ISO, and other styles
8

Paradesi, Martin S. R., Doina Caragea, and William H. Hsu. "Incorporating Graph Features for Predicting Protein-Protein Interactions." In Biological Data Mining in Protein Interaction Networks. IGI Global, 2009. http://dx.doi.org/10.4018/978-1-60566-398-2.ch004.

Full text
Abstract:
This chapter presents applications of machine learning to predicting protein-protein interactions (PPI) in Saccharomyces cerevisiae. Several supervised inductive learning methods have been developed that treat this task as a classification problem over candidate links in a PPI network – a graph whose nodes represent proteins and whose arcs represent interactions. Most such methods use feature extraction from protein sequences (e.g., amino acid composition) or associated with protein sequences directly (e.g., GO annotation). Others use relational and structural features extracted from the PPI network, along with the features related to the protein sequence. Topological features of nodes and node pairs can be extracted directly from the underlying graph. This chapter presents two approaches from the literature (Qi et al., 2006; Licamele & Getoor, 2006) that construct features on the basis of background knowledge, an approach that extracts purely topological graph features (Paradesi et al., 2007), and one that combines knowledge-based and topological features (Paradesi, 2008). Specific graph features that help in predicting protein interactions are reviewed. This study uses two previously published datasets (Chen & Liu, 2005; Qi et al., 2006) and a third dataset (Paradesi, 2008) that was created by combining and augmenting three existing PPI databases. The chapter includes a comparative study of the impact of each type of feature (topological, protein sequence-based, etc.) on the sensitivity and specificity of classifiers trained using specific types of features. The results indicate gains in the area under the sensitivity-specificity curve for certain algorithms when topological graph features are combined with other biological features such as protein sequence-based features.
APA, Harvard, Vancouver, ISO, and other styles
9

Gavrish, Alina, Yang Yang, Julie Loesch, and Michel Dumontier. "Forecasting Banned Substances: Leveraging GNN and Explainable AI for Sports Anti-Doping." In Studies in Health Technology and Informatics. IOS Press, 2025. https://doi.org/10.3233/shti250287.

Full text
Abstract:
Ensuring fairness in competitive sports requires robust mechanisms for detecting prohibited substances. Despite established regulations, challenges persist in accurately identifying new and emerging doping agents. This study introduces the use of Graph Neural Network (GNN) and Explainable AI (XAI) to classify substances as prohibited or non-prohibited, based on molecular and pharmacological data. The study utilizes Knowledge Graphs (KG) of heterogeneous type to develop predictive models. Explainability methods like Integrated Gradients and Saliency provide transparency into the models’ decisions, ensuring traceability and accountability in classification results. By offering a novel, AI-driven approach to doping detection, this work supports regulatory bodies in making informed decisions and enhances the robustness of anti-doping measures.
APA, Harvard, Vancouver, ISO, and other styles
10

Hage, Per, and Frank Harary. "Paths, Cycles, and Partitions." In Exchange In Oceania. Oxford University PressOxford, 1991. http://dx.doi.org/10.1093/oso/9780198277606.003.0002.

Full text
Abstract:
Abstract Graphical models of exchange systems enable us to discover structural commonality beneath empirical diversity, and they provide for the coherent classification of structural forms. We begin with two analyses. First, we give a unitary definition of dual organization, a widely distributed and, it has been conjectured, archaic type of social structure in Melanesia. Rather than giving an ethnographic survey, we consider three radically different surface forms, all of which have the underlying structure of a bipartite graph. Then, using digraphs and networks, we clarify the application of models of restricted and generalized marriage exchange to the analysis of ceremonial exchange in New Guinea. We start with a set of mathematical definitions that are the foundation of all that follows.
APA, Harvard, Vancouver, ISO, and other styles

Conference papers on the topic "Graph-type classification"

1

Wang, Xiaofeng, Jiahao Zhang, and Jianyu Zhou. "Diffusion-Enhanced Graph Attention Network for Cancer Type Classification." In 2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE, 2023. http://dx.doi.org/10.1109/bibm58861.2023.10386042.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Helm, Daniel, Florian Kleber, and Martin Kampel. "Graph-based Shot Type Classification in Large Historical Film Archives." In 17th International Conference on Computer Vision Theory and Applications. SCITEPRESS - Science and Technology Publications, 2022. http://dx.doi.org/10.5220/0010905800003124.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Sun, Zhongao, Alexander Khvostikov, and Andrey Krylov. "Tissue type classification for whole slide histological images with graph convolutional neural network." In ICBSP '24: 2024 9th International Conference on Biomedical Imaging, Signal Processing. ACM, 2024. https://doi.org/10.1145/3707172.3707175.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Chen, Kang, Xueying Li, Tao Gong, and Dehong Qiu. "A Graph Neural Network with Type-Feature Attention for Node Classification on Heterogeneous Graphs." In 2022 International Conference on Automation, Robotics and Computer Engineering (ICARCE). IEEE, 2022. http://dx.doi.org/10.1109/icarce55724.2022.10046551.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Saini, Loveneet, Axel Acosta, and Gor Hakobyan. "Graph Neural Networks for Object Type Classification Based on Automotive Radar Point Clouds and Spectra." In ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2023. http://dx.doi.org/10.1109/icassp49357.2023.10096657.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Gao, Shuming, and Jami J. Shah. "Automatic Recognition of Interacting Machining Features Based on Minimal Condition Sub-Graph." In ASME 1997 Design Engineering Technical Conferences. American Society of Mechanical Engineers, 1997. http://dx.doi.org/10.1115/detc97/cie-4277.

Full text
Abstract:
Abstract This paper presents a new approach for automatic recognition of machining features from the B-Reps of the part. In this approach we combine the conventional graph based recognition method with the hint based feature recognition idea so as to efficiently handle feature interactions and provide alternative interpretations of interacting features. A Manufacturing Face Adjacency Graph proposed here is useful for improving the recognition of isolated features and effectively reducing the search space for virtual links, unifiable faces and features. Isolated (non-intersecting) features are recognized first based on the Manufacturing Face Adjacency Graph. Then, interacting features are recognized based on the Feature’s Minimal Condition Sub-Graph (MCSG) which is proposed as feature hint. The MCSGs for all types of features are defined, generated and completed in a uniform way, independent of feature type. Feature definitions are based on an extended Attributed Adjacency Graph, generated by graph decomposition and completed by adding related virtual links. An efficient algorithm for generating virtual links is developed. A new feature interaction classification and a virtual link classification are also described. Our approach can produce alternative interpretations of intersecting features. The main contribution of this paper is a methodology for recognizing interacting features in a uniform way.
APA, Harvard, Vancouver, ISO, and other styles
7

Wan, Hai, Yonghao Luo, Bo Peng, and Wei-Shi Zheng. "Representation Learning for Scene Graph Completion via Jointly Structural and Visual Embedding." In Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18}. International Joint Conferences on Artificial Intelligence Organization, 2018. http://dx.doi.org/10.24963/ijcai.2018/132.

Full text
Abstract:
This paper focuses on scene graph completion which aims at predicting new relations between two entities utilizing existing scene graphs and images. By comparing with the well-known knowledge graph, we first identify that each scene graph is associated with an image and each entity of a visual triple in a scene graph is composed of its entity type with attributes and grounded with a bounding box in its corresponding image. We then propose an end-to-end model named Representation Learning via Jointly Structural and Visual Embedding (RLSV) to take advantages of structural and visual information in scene graphs. In RLSV model, we provide a fully-convolutional module to extract the visual embeddings of a visual triple and apply hierarchical projection to combine the structural and visual embeddings of a visual triple. In experiments, we evaluate our model on two scene graph completion tasks: link prediction and visual triple classification, and further analyze by case studies. Experimental results demonstrate that our model outperforms all baselines in both tasks, which justifies the significance of combining structural and visual information for scene graph completion.
APA, Harvard, Vancouver, ISO, and other styles
8

Tohmuang, Sitthichart, James L. Swayze, Mohammad Fard, et al. "Mode Shape Identification Using Graph Neural Networks for Vehicle Structure Design." In Noise & Vibration Conference & Exhibition. SAE International, 2025. https://doi.org/10.4271/2025-01-0131.

Full text
Abstract:
<div class="section abstract"><div class="htmlview paragraph">This paper introduces a novel, automated approach for identifying and classifying full vehicle mode shapes using Graph Neural Networks (GNNs), a deep learning model for graph-structured data. Mode shape identification and naming refers to classifying deformation patterns in structures vibrating at natural frequencies with systematic naming based on the movement or deformation type. Many times, these mode shapes are named based on the type of movement or deformation involved. The systematic naming of mode shapes and their frequencies is essential for understanding structural dynamics and “Modal Alignment” or “Modal Separation” charts used in Noise, Vibration and Harshness (NVH) analysis. Current methods are manual, time-consuming, and rely on expert judgment. The integration of GNNs into mode shape classification represents a significant advancement in vehicle modal identification and structure design. Results demonstrate that GNNs offer superior accuracy and efficiency compared to current labor intensive manual modes labelling, making this innovative approach promising for vehicle NVH/dynamics analysis and structural design.</div></div>
APA, Harvard, Vancouver, ISO, and other styles
9

Huang, Zhichao, Xutao Li, Yunming Ye, and Michael K. Ng. "MR-GCN: Multi-Relational Graph Convolutional Networks based on Generalized Tensor Product." In Twenty-Ninth International Joint Conference on Artificial Intelligence and Seventeenth Pacific Rim International Conference on Artificial Intelligence {IJCAI-PRICAI-20}. International Joint Conferences on Artificial Intelligence Organization, 2020. http://dx.doi.org/10.24963/ijcai.2020/175.

Full text
Abstract:
Graph Convolutional Networks (GCNs) have been extensively studied in recent years. Most of existing GCN approaches are designed for the homogenous graphs with a single type of relation. However, heterogeneous graphs of multiple types of relations are also ubiquitous and there is a lack of methodologies to tackle such graphs. Some previous studies address the issue by performing conventional GCN on each single relation and then blending their results. However, as the convolutional kernels neglect the correlations across relations, the strategy is sub-optimal. In this paper, we propose the Multi-Relational Graph Convolutional Network (MR-GCN) framework by developing a novel convolution operator on multi-relational graphs. In particular, our multi-dimension convolution operator extends the graph spectral analysis into the eigen-decomposition of a Laplacian tensor. And the eigen-decomposition is formulated with a generalized tensor product, which can correspond to any unitary transform instead of limited merely to Fourier transform. We conduct comprehensive experiments on four real-world multi-relational graphs to solve the semi-supervised node classification task, and the results show the superiority of MR-GCN against the state-of-the-art competitors.
APA, Harvard, Vancouver, ISO, and other styles
10

Malyshev, Gregory, Vyacheslav Andreev, Olga Andreeva, Oleg Chistyakov, and Dmitriy Sveshnikov. "Choice of Neural Network Architecture when Recognizing Objects that do not Have High-Level Features." In 31th International Conference on Computer Graphics and Vision. Keldysh Institute of Applied Mathematics, 2021. http://dx.doi.org/10.20948/graphicon-2021-3027-1073-1081.

Full text
Abstract:
This article explores the capabilities of pretrained convolutional neural networks in relation to the problem of recognizing defects for which it is impossible to identify any abstract features. The results of training the convolutional neural network AlexNet and the fully connected classifier of the VGG16 network are compared. The efficiency of using a pretrained neural network in the problem of defect recognition is demonstrated. A graph of the change in the proportion of correctly recognized images in the process of training a fully connected classifier is presented. The article attempts to explain the efficiency of a fully connected neural network classifier trained on a critically small training dataset with images of defects. The work of a convolutional neural network with a fully connected classifier is investigated. The classifier allows for classification into five categories: «crack» type defects, «chip» type defects, «hole» type defects, «multi hole» type defects and «defect-free surface». The article provides examples of convolutional network activation channels, visualized for each of the five categories. The signs of defects on which the activation of the network channels takes place are formulated. The classification errors made by the network are analyzed. The article provides predictive probabilities, below which the result of the network operation can be considered doubtful. Practical recommendations for using the trained network are given.
APA, Harvard, Vancouver, ISO, and other styles
You might also be interested in the extended bibliographies on the topic 'Graph-type classification' for particular source types:
Journal articles
We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!

To the bibliography