Results 21 to 30 of about 333,836 (279)

Neural Distributed Autoassociative Memories: A Survey [PDF]

, 2017
Introduction. Neural network models of autoassociative, distributed memory allow storage and retrieval of many items (vectors) where the number of stored items can exceed the vector dimension (the number of neurons in the network).
Frolov, A. A., Gayler, R., Gritsenko, V. I., Kleyko, D., Osipov, E., Rachkovskij, D. A.   +5 more
core   +1 more source

Similarity search over graphs using localized spectral analysis [PDF]

2017 International Conference on Sampling Theory and Applications (SampTA), 2017
This paper provides a new similarity detection algorithm. Given an input set of multi-dimensional data points, where each data point is assumed to be multi-dimensional, and an additional reference data point for similarity finding, the algorithm uses kernel method that embeds the data points into a low dimensional manifold. Unlike other kernel methods,
Aizenbud, Yariv, Averbuch, Amir, Shabat, Gil, Ziv, Guy   +3 more
openaire   +2 more sources

Enhancing Semantic Code Search With Deep Graph Matching

IEEE Access, 2023
The job of discovering appropriate code snippets against a natural language query is an important task for software developers. Appropriate code retrieval increases software productivity and quality as well.
Nazia Bibi, Ayesha Maqbool, Tauseef Rana, Farkhanda Afzal, Ali Akgul, Sayed M. Eldin   +5 more
doaj   +1 more source

Heterogeneous Graph Based Similarity Measure for Categorical Data Unsupervised Learning

IEEE Access, 2019
Different from numerical attributes, measuring the similarity between categorical attributes is more complex due to their non-inherently ordered characteristic, especially in an unsupervised scheme.
Yanqing Ye, Jiang Jiang, Bingfeng Ge, Kewei Yang, H. Eugene Stanley   +4 more
doaj   +1 more source

Learning to rank graphs for online similar graph search [PDF]

Proceedings of the 18th ACM conference on Information and knowledge management, 2009
Many applications in structure matching require the ability to search for graphs that are similar to a query graph, i.e., similarity graph queries. Prior works, especially in chemoinformatics, have used the maximum common edge subgraph (MCEG) to compute the graph similarity. This approach is prohibitively slow for real-time queries.
Bingjun Sun, Prasenjit Mitra, C. Lee Giles   +2 more
openaire   +1 more source

Community Search Based on Disentangled Graph Neural Network in Heterogeneous Information Networks [PDF]

Jisuanji kexue
Searching the community containing a given query node in heterogeneous information networks(HINs) has a wide range of application values,such as friend recommendation,epidemic monitoring and so on.However,most of the existing HINs community search ...
CHEN Wei, ZHOU Lihua, WANG Yafeng, WANG Lizhen, CHEN Hongmei
doaj   +1 more source

More is simpler : effectively and efficiently assessing node-pair similarities based on hyperlinks [PDF]

, 2013
Similarity assessment is one of the core tasks in hyperlink analysis. Recently, with the proliferation of applications, e.g., web search and collaborative filtering, SimRank has been a well-studied measure of similarity between two nodes in a graph.
Chang, Lijun, Lin, Xuemin, Pei, Jian, Yu, Weiren, Zhang, Wenjie   +4 more
core   +3 more sources

Node embeddings in dynamic graphs

Applied Network Science, 2019
In this paper, we present algorithms that learn and update temporal node embeddings on the fly for tracking and measuring node similarity over time in graph streams. Recently, several representation learning methods have been proposed that are capable of
Ferenc Béres, Domokos M. Kelen, Róbert Pálovics, András A. Benczúr   +3 more
doaj   +1 more source

Pan-genome de Bruijn graph using the bidirectional FM-index

BMC Bioinformatics, 2023
Background Pan-genome graphs are gaining importance in the field of bioinformatics as data structures to represent and jointly analyze multiple genomes. Compacted de Bruijn graphs are inherently suited for this purpose, as their graph topology naturally ...
Lore Depuydt, Luca Renders, Thomas Abeel, Jan Fostier   +3 more
doaj   +1 more source

Towards distributed node similarity search on graphs [PDF]

World Wide Web, 2020
Node similarity search on graphs has wide applications in recommendation, link prediction, to name just a few. However, existing studies are insufficient due to two reasons: (i) the scale of the real-world graph is growing rapidly, and (ii) vertices are always associated with complex attributes.
ZHANG, Tianming, GAO, Yunjun, ZHENG, Baihua, CHEN, Lu, WEN, Shiting, GUO, Wei   +5 more
openaire   +3 more sources