Filters








65,863 Hits in 5.4 sec

Improving Fuzzy Multilevel Graph Embedding through Feature Selection Technique [chapter]

Muhammad Muzzamil Luqman, Jean Yves Ramel, Josep Lladós
2012 Lecture Notes in Computer Science  
Feature selection permits FMGE to select the subset of most discriminating features and to discard the confusing ones for underlying graph dataset.  ...  In this paper we take forward our work on explicit graph embedding and present an improvement to our earlier proposed method, named "fuzzy multilevel graph embedding -FMGE", through feature selection technique  ...  Feature Selection by Ranking Discriminatory Features The feature vector obtained by FMGE is based on histogram encoding of the multilevel information extracted from graph.  ... 
doi:10.1007/978-3-642-34166-3_27 fatcat:zxl3fcf775c2hm23vurc3yfqd4

Little Ball of Fur: A Python Library for Graph Sampling [article]

Benedek Rozemberczki, Oliver Kiss, Rik Sarkar
2020 arXiv   pre-print
Experiments demonstrate that Little Ball of Fur can speed up node and whole graph embedding techniques considerably with mildly deteriorating the predictive value of distilled features.  ...  We show the practical usability of the library by estimating various global statistics of social networks and web graphs.  ...  Using these embeddings as input features for node and graph classification tasks we establish that the embeddings learned on the subsampled graphs extract high quality features. Our contributions.  ... 
arXiv:2006.04311v2 fatcat:acolhpjfefbvpgwcuklm3c2zna

Little Ball of Fur

Benedek Rozemberczki, Oliver Kiss, Rik Sarkar
2020 Proceedings of the 29th ACM International Conference on Information & Knowledge Management  
Experiments demonstrate that Little Ball of Fur can speed up node and whole graph embedding techniques considerably with mildly deteriorating the predictive value of distilled features.  ...  We show the practical usability of the library by estimating various global statistics of social networks and web graphs.  ...  Using these embeddings as input features for node and graph classification tasks we establish that the embeddings learned on the subsampled graphs extract high quality features. Our contributions.  ... 
doi:10.1145/3340531.3412758 dblp:conf/cikm/RozemberczkiKS20a fatcat:sqxrjqzyxzbufanmg5fyp6cxpu

A Comparison of Explicit and Implicit Graph Embedding Methods for Pattern Recognition [chapter]

Donatello Conte, Jean-Yves Ramel, Nicolas Sidère, Muhammad Muzzamil Luqman, Benoît Gaüzère, Jaume Gibert, Luc Brun, Mario Vento
2013 Lecture Notes in Computer Science  
Our preliminary experimentation on different chemoinformatics datasets illustrates that the two implicit and three explicit graph embedding approaches obtain competitive performance for the problem of  ...  In recent years graph embedding has emerged as a promising solution for enabling the expressive, convenient, powerful but computational expensive graph based representations to benefit from mature, less  ...  Method 3: Attribute Statistics based Embedding The attribute statistics based embedding of graphs is a simple and efficient way of expressing the labelling information stored in nodes and edges of graphs  ... 
doi:10.1007/978-3-642-38221-5_9 fatcat:pzp6r7hjgjbwrmbykpjapbz6t4

A Knowledge Graph Entity Disambiguation Method Based on Entity-Relationship Embedding and Graph Structure Embedding

Jiangtao Ma, Duanyang Li, Yonggang Chen, Yaqiong Qiao, Haodong Zhu, Xuncai Zhang, Abdelkader Nasreddine Belkacem
2021 Computational Intelligence and Neuroscience  
To improve the Precision and Recall of entity disambiguation problems, we propose the EDEGE (Entity Disambiguation based on Entity and Graph Embedding) method, which utilizes the semantic embedding vector  ...  of entity relationship and the embedding vector of subgraph structure feature.  ...  Entity Disambiguation Based on Graph Neural Network. e final entity disambiguation is based on the similarity measurement of the entity embedding vector V KGE and the entity structure embedding vector  ... 
doi:10.1155/2021/2878189 pmid:34603428 pmcid:PMC8486511 fatcat:yyh34x6zfbhgdntxzurlpgwdki

Using ontology embeddings for structural inductive bias in gene expression data analysis [article]

Maja Trębacz, Zohreh Shams, Mateja Jamnik, Paul Scherer, Nikola Simidjievski, Helena Andres Terre, Pietro Liò
2020 arXiv   pre-print
Stratifying cancer patients based on their gene expression levels allows improving diagnosis, survival analysis and treatment planning.  ...  We use ontology embeddings that capture the semantic similarities between the genes to direct a Graph Convolutional Network, and therefore sparsify the network connections.  ...  Moreover, the ontology-based feature selection allows selecting a biologically relevant set of features.  ... 
arXiv:2011.10998v1 fatcat:px2whb62q5apjesojodgjq7hsu

Explainability-based Backdoor Attacks Against Graph Neural Networks [article]

Jing Xu, Minhui Xue, Stjepan Picek
2021 arXiv   pre-print
For instance, on the node classification task, the backdoor attack with trigger injecting position selected by GraphLIME reaches over 84 % attack success rate with less than 2.5 % accuracy drop  ...  There are already numerous works on backdoor attacks on neural networks, but only a few works consider graph neural networks (GNNs).  ...  node classification task based on different trigger features selecting strategies.  ... 
arXiv:2104.03674v2 fatcat:iip3rirgtbbtpljsk4d24vdanu

Comparative effectiveness of medical concept embedding for feature engineering in phenotyping

Junghwan Lee, Cong Liu, Jae Hyun Kim, Alex Butler, Ning Shang, Chao Pang, Karthik Natarajan, Patrick Ryan, Casey Ta, Chunhua Weng
2021 JAMIA Open  
Of MCEs based on knowledge graphs and EHR data, MCEs learned by using node2vec with knowledge graphs and MCEs learned by using GloVe with EHR data outperforms other MCEs, respectively.  ...  Properly learned medical concept embeddings (MCEs) capture the semantics of medical concepts, thus are useful for retrieving relevant medical features in phenotyping tasks.  ...  of the nodes in a graph using random walk.  ... 
doi:10.1093/jamiaopen/ooab028 pmid:34142015 pmcid:PMC8206403 fatcat:tmxwmx7cnfcgbgvzmldpdczkqm

Graph-based Neural Multi-Document Summarization [article]

Michihiro Yasunaga, Rui Zhang, Kshitijh Meelu, Ayush Pareek, Krishnan Srinivasan, Dragomir Radev
2017 arXiv   pre-print
We employ a Graph Convolutional Network (GCN) on the relation graphs, with sentence embeddings obtained from Recurrent Neural Networks as input node features.  ...  In our experiments on DUC 2004, we consider three types of sentence relation graphs and demonstrate the advantage of combining sentence relations in graphs with the representation power of deep neural  ...  Acknowledgements We would like to thank Mirella Lapata, the members of the Sapphire Project (University of Michigan and IBM), as well as all the anonymous reviewers for their helpful suggestions on this  ... 
arXiv:1706.06681v3 fatcat:nq6s6fmdpzetnhtqbws7c6depm

Graph embedding in vector spaces by node attribute statistics

Jaume Gibert, Ernest Valveny, Horst Bunke
2012 Pattern Recognition  
The approach presented in this paper is based on statistics of the node labels and the edges between them, based on their similarity to a set of representatives.  ...  statistical learning machinery to be used on graph-based input patterns.  ...  Kaspar Riesen for providing us with the databases that are used in this work and the corresponding implementations of the reference systems.  ... 
doi:10.1016/j.patcog.2012.01.009 fatcat:ubz2fdx7p5hmjp56luihghyeqa

Graph Embedding Using Constant Shift Embedding [chapter]

Salim Jouili, Salvatore Tabbone
2010 Lecture Notes in Computer Science  
In this paper, we propose a graph embedding technique based on the constant shift embedding which transforms a graph to a real vector.  ...  This technique gives the abilities to perform the graph classification tasks by procedures based on feature vectors.  ...  This method was originally developed for the embedding of feature vectors in a dissimilarity space [16, 17] and is based on the selection of some prototypes and the computation of the graph edit distance  ... 
doi:10.1007/978-3-642-17711-8_9 fatcat:xwjktu425nhadm6tptbcmxq4aa

Graph-based Neural Multi-Document Summarization

Michihiro Yasunaga, Rui Zhang, Kshitijh Meelu, Ayush Pareek, Krishnan Srinivasan, Dragomir Radev
2017 Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)  
We employ a Graph Convolutional Network (GCN) on the relation graphs, with sentence embeddings obtained from Recurrent Neural Networks as input node features.  ...  In our experiments on DUC 2004, we consider three types of sentence relation graphs and demonstrate the advantage of combining sentence relations in graphs with the representation power of deep neural  ...  Acknowledgements We would like to thank the members of the Sapphire Project (University of Michigan and IBM), as well as all the anonymous reviewers for their helpful suggestions on this work.  ... 
doi:10.18653/v1/k17-1045 dblp:conf/conll/YasunagaZMPSR17 fatcat:qshfkz4torefjhuzagpsi2rlaq

Hypergraph Partitioning With Embeddings [article]

Justin Sybrandt, Ruslan Shaydulin, Ilya Safro
2020 arXiv   pre-print
In this work we propose using graph embeddings of the initial hypergraph in order to ensure that coarsened problem instances retrain key structural features.  ...  A hypergraph is a generalization of a traditional graph wherein "hyperedges" may connect any number of nodes. As a result, hypergraph partitioning is an NP-Hard problem to both solve or approximate.  ...  We would like to thank Sebastian Schlag from the Karlsruhe Institute of Technology for helping us to understand KaHyPar. We would also like to thank our editor and reviewers.  ... 
arXiv:1909.04016v5 fatcat:wfpycc6sirdsnasocgyp72375a

Graph Embedding on Biomedical Networks: Methods, Applications, and Evaluations [article]

Xiang Yue, Zhen Wang, Jingong Huang, Srinivasan Parthasarathy, Soheil Moosavinasab, Yungui Huang, Simon M. Lin, Wen Zhang, Ping Zhang, Huan Sun
2019 arXiv   pre-print
the more recent graph embedding methods (e.g., random walk-based and neural network-based) in terms of their usability and potential to further the state-of-the-art.  ...  Besides, compared with three state-of-the-art methods for DDAs, DDIs and protein function predictions, the recent graph embedding methods achieve competitive performance without using any biological features  ...  Petrone, Kaushik Mani and anonymous reviewers for their helpful comments and suggestions on our work, and Ohio Supercomputer Center (OSC) (Ohio Supercomputer Center, 1987) for providing us computing resources  ... 
arXiv:1906.05017v2 fatcat:7k6vrdkwybdu7pikmxa3xrnowm

On the Correlation of Graph Edit Distance and L 1 Distance in the Attribute Statistics Embedding Space [chapter]

Jaume Gibert, Ernest Valveny, Horst Bunke, Alicia Fornés
2012 Lecture Notes in Computer Science  
In this work, we analyse relations between the edit distance in the graph domain and the L1 distance of the attribute statistics based embedding, for which good classification performance has been reported  ...  We show that there is actually a high correlation between the two kinds of distances provided that the corresponding parameter values that account for balancing the weight between node and edge based features  ...  In other words, this kind of embedding is based on occurrence and co-occurrence statistics of labels in the underlying graph.  ... 
doi:10.1007/978-3-642-34166-3_15 fatcat:cwinatggwzdldoex5c3m5ttike
« Previous Showing results 1 — 15 out of 65,863 results