local proximity
Recently Published Documents





Bornali Phukon ◽  
Akash Anil ◽  
Sanasam Ranbir Singh ◽  
Priyankoo Sarmah

WordNets built for low-resource languages, such as Assamese, often use the expansion methodology. This may result in missing lexical entries and missing synonymy relations. As the Assamese WordNet is also built using the expansion method, using the Hindi WordNet, it also has missing synonymy relations. As WordNets can be visualized as a network of unique words connected by synonymy relations, link prediction in complex network analysis is an effective way of predicting missing relations in a network. Hence, to predict the missing synonyms in the Assamese WordNet, link prediction methods were used in the current work that proved effective. It is also observed that for discovering missing relations in the Assamese WordNet, simple local proximity-based methods might be more effective as compared to global and complex supervised models using network embedding. Further, it is noticed that though a set of retrieved words are not synonyms per se, they are semantically related to the target word and may be categorized as semantic cohorts.

2021 ◽  
Vol 7 (12) ◽  
pp. 278
Konstantinos Zagoris ◽  
Angelos Amanatiadis ◽  
Ioannis Pratikakis

Word spotting strategies employed in historical handwritten documents face many challenges due to variation in the writing style and intense degradation. In this paper, a new method that permits efficient and effective word spotting in handwritten documents is presented that relies upon document-oriented local features that take into account information around representative keypoints and a matching process that incorporates a spatial context in a local proximity search without using any training data. The method relies on a document-oriented keypoint and feature extraction, along with a fast feature matching method. This enables the corresponding methodological pipeline to be both effectively and efficiently employed in the cloud so that word spotting can be realised as a service in modern mobile devices. The effectiveness and efficiency of the proposed method in terms of its matching accuracy, along with its fast retrieval time, respectively, are shown after a consistent evaluation of several historical handwritten datasets.

2021 ◽  
Vol 16 (1) ◽  
Teresa Schätzl ◽  
Lars Kaiser ◽  
Hans-Peter Deigner

AbstractWhilst a disease-modifying treatment for Facioscapulohumeral muscular dystrophy (FSHD) does not exist currently, recent advances in complex molecular pathophysiology studies of FSHD have led to possible therapeutic approaches for its targeted treatment. Although the underlying genetics of FSHD have been researched extensively, there remains an incomplete understanding of the pathophysiology of FSHD in relation to the molecules leading to DUX4 gene activation and the downstream gene targets of DUX4 that cause its toxic effects. In the context of the local proximity of chromosome 4q to the nuclear envelope, a contraction of the D4Z4 macrosatellite induces lower methylation levels, enabling the ectopic expression of DUX4. This disrupts numerous signalling pathways that mostly result in cell death, detrimentally affecting skeletal muscle in affected individuals. In this regard different options are currently explored either to suppress the transcription of DUX4 gene, inhibiting DUX4 protein from its toxic effects, or to alleviate the symptoms triggered by its numerous targets.

2021 ◽  
Vol 11 (5) ◽  
pp. 2371
Junjian Zhan ◽  
Feng Li ◽  
Yang Wang ◽  
Daoyu Lin ◽  
Guangluan Xu

As most networks come with some content in each node, attributed network embedding has aroused much research interest. Most existing attributed network embedding methods aim at learning a fixed representation for each node encoding its local proximity. However, those methods usually neglect the global information between nodes distant from each other and distribution of the latent codes. We propose Structural Adversarial Variational Graph Auto-Encoder (SAVGAE), a novel framework which encodes the network structure and node content into low-dimensional embeddings. On one hand, our model captures the local proximity and proximities at any distance of a network by exploiting a high-order proximity indicator named Rooted Pagerank. On the other hand, our method learns the data distribution of each node representation while circumvents the side effect its sampling process causes on learning a robust embedding through adversarial training. On benchmark datasets, we demonstrate that our method performs competitively compared with state-of-the-art models.

2021 ◽  
Vol 3 ◽  
Muhammad Ifte Islam ◽  
Farhan Tanvir ◽  
Ginger Johnson ◽  
Esra Akbas ◽  
Mehmet Emin Aktas

Network embedding that encodes structural information of graphs into a low-dimensional vector space has been proven to be essential for network analysis applications, including node classification and community detection. Although recent methods show promising performance for various applications, graph embedding still has some challenges; either the huge size of graphs may hinder a direct application of the existing network embedding method to them, or they suffer compromises in accuracy from locality and noise. In this paper, we propose a novel Network Embedding method, NECL, to generate embedding more efficiently or effectively. Our goal is to answer the following two questions: 1) Does the network Compression significantly boost Learning? 2) Does network compression improve the quality of the representation? For these goals, first, we propose a novel graph compression method based on the neighborhood similarity that compresses the input graph to a smaller graph with incorporating local proximity of its vertices into super-nodes; second, we employ the compressed graph for network embedding instead of the original large graph to bring down the embedding cost and also to capture the global structure of the original graph; third, we refine the embeddings from the compressed graph to the original graph. NECL is a general meta-strategy that improves the efficiency and effectiveness of many state-of-the-art graph embedding algorithms based on node proximity, including DeepWalk, Node2vec, and LINE. Extensive experiments validate the efficiency and effectiveness of our method, which decreases embedding time and improves classification accuracy as evaluated on single and multi-label classification tasks with large real-world graphs.

2020 ◽  
Vol 34 (10) ◽  
pp. 13875-13876
Tae Hong Moon ◽  
Sungsu Lim

Learning latent representations in graphs is finding a mapping that embeds nodes or edges as data points in a low-dimensional vector space. This paper introduces a flexible framework to enhance existing methodologies that have difficulty capturing local proximity and global relationships at the same time. Our approach generates a virtual edge between non-adjacent nodes based on the Forman-Ricci curvature in network. By analyzing the network using topological information, global relationships structurally similar can easily be detected and successfully integrated with previous works.

2020 ◽  
Vol 29 (4) ◽  
pp. 047501 ◽  
Jingyuan Zhu ◽  
Sichao Zhang ◽  
Shanshan Xie ◽  
Chen Xu ◽  
Lijuan Zhang ◽  

2020 ◽  
pp. 016555152090273
Veslava Osinska

By applying different clustering algorithms, the author strived to construct the best visual representation of scientific domains and disciplines in Poland. Journals and their disciplinary categories constituted a data set. A comparative analysis of maps was based on both qualitative and quantitative approaches. Complex patterns of eight maps were evaluated taking into account both the local proximity of disciplines and the whole structure of presented domains. Final clustering quality value was introduced and calculated in reference to the knowledge domains. The authors underlined the role of quantitative and qualitative methods in combination in the mapping evaluation. The best results were obtained with the T-distributed stochastic neighbour embedding (t-SNE) algorithm. This youngest technique may have the biggest potential for semantic information studies and in the scope of broadly understood semantic solutions.

2020 ◽  
Vol 29 ◽  
pp. 2478-2491 ◽  
Srimanta Mandal ◽  
A. N. Rajagopalan

Sign in / Sign up

Export Citation Format

Share Document