Filters








32,580 Hits in 11.9 sec

Parameterized Hypercomplex Graph Neural Networks for Graph Classification [article]

Tuan Le, Marco Bertolini, Frank Noé, Djork-Arné Clevert
2021 arXiv   pre-print
Despite recent advances in representation learning in hypercomplex (HC) space, this subject is still vastly unexplored in the context of graphs.  ...  Given a fixed model architecture, we present empirical evidence that our proposed model incorporates a regularization effect, alleviating the risk of overfitting.  ...  Table 1 . 1 Results on the OGB graph classification datasets.  ... 
arXiv:2103.16584v1 fatcat:fmovzq7v5vhm3c2lzwkspyhbda

Functions, Graphs, and Graphing: Tasks, Learning, and Teaching

Gaea Leinhardt, Orit Zaslavsky, Mary Kay Stein
1990 Review of Educational Research  
The mathematical presentation is usually from an algebraic function rule to ordered pairs to a graph, or from a data table of ordered pairs to a graph.  ...  , the number of studies is still small enough to make such an integration feasible and informative for future work in this area.  ...  FIGURE 14 . 14 An overview of the variety of misconceptions and difficulties presented in this section reveals learning problems in three broad areas: a desire for regularity, Graph interpretation task  ... 
doi:10.3102/00346543060001001 fatcat:aeiwxddiojfw7mz3qwljpp4tei

AutoNet: Knowledge Graphs for Occasions Object Recognition

Zheng LIU, Yang HUANG
2018 DEStech Transactions on Computer Science and Engineering  
In this paper, we have proposal a novel knowledge graphs framework for occasions object recognition called AutoNet, which shows using this knowledge graphs improves performance on image recognition.  ...  Object recognition in images fields is a novel and importance challenge in Computer Vision.  ...  This work use guns as a way of incorporating potentially large knowledge graphs into an end-to-end learning system and propose a framework for using noisy knowledge graphs for image classification, which  ... 
doi:10.12783/dtcse/ccnt2018/24744 fatcat:et7b6q7ovbadzn2yyk7q4eeyuq

Size-Invariant Graph Representations for Graph Classification Extrapolations [article]

Beatrice Bevilacqua, Yangze Zhou, Bruno Ribeiro
2021 arXiv   pre-print
In this work we consider an underexplored area of an otherwise rapidly developing field of graph representation learning: The task of out-of-distribution (OOD) graph classification, where train and test  ...  In general, graph representation learning methods assume that the train and test data come from the same distribution.  ...  Acknowledgements This work was funded in part by the National Science Foundation (NSF) awards CAREER IIS-1943364 and CCF-1918483, the Frederick N.  ... 
arXiv:2103.05045v2 fatcat:yul2sfauanhjfppdvdqz4vanme

Querying in the Age of Graph Databases and Knowledge Graphs [article]

Marcelo Arenas and Claudio Gutierrez and Juan F. Sequeda
2021 arXiv   pre-print
The goal of this document is to provide a conceptual map of the data management tasks underlying these developments, paying particular attention to data models and query languages for graphs.  ...  Graph databases and knowledge graphs surface as the most successful solutions to this program.  ...  ACKNOWLEDGMENTS This work was funded by ANID -Millennium Science Initiative Program -Code ICN17_002.  ... 
arXiv:2106.11456v2 fatcat:cuvuubx5pjbmhlh4kmrw43hupi

Random Walks on the Reputation Graph

Sabir Ribas, Berthier Ribeiro-Neto, Rodrygo L.T. Santos, Edmundo de Souza e Silva, Alberto Ueda, Nivio Ziviani
2015 Proceedings of the 2015 International Conference on Theory of Information Retrieval - ICTIR '15  
Otherwise, I would have to explain to people why my younger brother started later and finished before. Karine, thanks for being a good friend and supporting Sávio in his journey.  ...  It is great having you in the family. Lili, thanks for always helping us carefully and teach us math.  ...  In Table C .3, we show the CAPES classification 4 of Brazilian graduate programs in the area of Computer Science and in all areas for the year of 2013.  ... 
doi:10.1145/2808194.2809462 dblp:conf/ictir/RibasRSSUZ15 fatcat:3u3ry2ijl5do3p2gbkagmgg2rm

PCG-Cut: Graph Driven Segmentation of the Prostate Central Gland

Jan Egger, Zoran Culig
2013 PLoS ONE  
In this study, the segmentation results for the prostate central gland (PCG) in MR scans are presented.  ...  The aim of this research study is to apply a graph-based algorithm to automated segmentation (i.e. delineation) of organ limits for the prostate central gland.  ...  Acknowledgments In the first place, the author would like to thank Fraunhofer MeVis in Bremen, Germany, for their collaboration and especially Horst K. Hahn for his support.  ... 
doi:10.1371/journal.pone.0076645 pmid:24146901 pmcid:PMC3795743 fatcat:3e7octpkynakvp4py2ba525iye

Graph-Based Inter-Subject Pattern Analysis of fMRI Data

Sylvain Takerkart, Guillaume Auzias, Bertrand Thirion, Liva Ralaivola, Daniele Marinazzo
2014 PLoS ONE  
Here we introduce a novel classification framework based on group-invariant graphical representations, allowing to overcome the inter-subject variability present in functional magnetic resonance imaging  ...  The dataset used in this study and an implementation of our framework are available at http://dx.  ...  Acknowledgments The authors would like to thank the Centre IRMf de Marseille and its staff for setting up the data acquisition, as well as Daniele Schön for designing the tonotopy paradigm.  ... 
doi:10.1371/journal.pone.0104586 pmid:25127129 pmcid:PMC4134217 fatcat:esoo6tcgljbhfcy6laacftrzru

Capsule Neural Networks for Graph Classification using Explicit Tensorial Graph Representations [article]

Marcelo Daniel Gutierrez Mallea, Peter Meltzer, Peter J Bentley
2019 arXiv   pre-print
from each graph in a given set, and using a Capsule Network to perform classification.  ...  A significant difficulty in this task arises when attempting to apply established classification algorithms due to the requirement for fixed size matrix or tensor representations of the graphs which may  ...  ACKNOWLEDGMENT We wish to thank Kyohei Koyama for his assistance in the implementation of our CNN baseline and data preparation with the benchmark datasets.  ... 
arXiv:1902.08399v1 fatcat:fgovkhvycvaxtfeam75ijkmwcy

Visualizing large graphs

Yifan Hu, Lei Shi
2015 Wiley Interdisciplinary Reviews: Computational Statistics  
In this article we review layout algorithms and interactive exploration techniques for large graphs.  ...  With the prevailence of big data, there is a growing need for algorithms and techniques for visualizing very large and complex graphs.  ...  Further research in this area may discover important graph patterns and structures that are universal in a class of graphs and thus can be abstracted into motifs.  ... 
doi:10.1002/wics.1343 fatcat:j4mg4hizwfbs3ky67j6d67uiqq

Using Unsupervised Learning to Help Discover the Causal Graph [article]

Seamus Brady
2020 arXiv   pre-print
In this paper the problem space of causality is briefly described and an overview of related research is provided. A problem statement and requirements for the software are outlined.  ...  It is found that AitiaExplorer meets these requirements and is a useful exploratory causal analysis tool that automatically selects subsets of important features from a dataset and creates causal graph  ...  For clarity and simplicity, a small simulated dataset was used and only 7 features of a possible 10 features were selected. The results from the run are displayed in Table VI below.  ... 
arXiv:2009.10790v1 fatcat:ccvyamim6jbo5lxa5lj253sk4i

Visual Analytics of Time Evolving Large-scale Graphs

Raju N. Gottumukkala, Siva R. Venna, Vijay Raghavan
2015 The IEEE intelligent informatics bulletin  
ACKNOWLEDGEMENTS This material is based upon work supported by: NSF Grant No.1429526 and NSF Grant No. 1160958  ...  Another survey paper visual analytics [19] also highlights the stateof-the-art in visual analytics and the challenges in individual research areas.  ...  We also present our ongoing work in building a big data sandbox for visual analytics, and discuss ongoing big data projects that use time evolving graphs. II. TIME EVOLVING GRAPHS A.  ... 
dblp:journals/cib/GottumukkalaV015 fatcat:c6rvatyem5bqpjqads3ijvbx6m

State Estimation in Electric Power Systems Leveraging Graph Neural Networks [article]

Ognjen Kundacina, Mirsad Cosovic, Dejan Vukobratovic
2022 arXiv   pre-print
The presented results display the accuracy of GNN predictions in various test scenarios and tackle the sensitivity of the predictions to the missing input data.  ...  This paper proposes training a graph neural network (GNN) to learn the estimates given the PMU voltage and current measurements as inputs, with the intent of obtaining fast and accurate predictions during  ...  We used the IGNNITION framework [14] for building and utilising GNN models, with the hyperparameters presented in Table I, the first three of which were obtained with the grid search hyperparameter optimization  ... 
arXiv:2201.04056v2 fatcat:5kcfn2mhyzclte45ndcw2splui

SSHOC D9.9 Delivery of user-validated Knowledge Graph, and Election Studies Analytics dashboard

Sotirios Karampatakis, Albin Ahmeti, Martin Kaltenböck, Johann Gründl, Julia Partheymüller, Cees Van Der Eijk
2021 Zenodo  
The SSHOC project Deliverable D9.9 Delivery of User Validated Knowledge Graph and Election Studies Analytics Dashboard, describes the implementation of the SSHOC Pilot project in the field of Electoral  ...  It describes the efforts to create a domain specific Taxonomy, capable of modelling experts' knowledge in the field, in order to weave an integration layer between the various contributions on the domain  ...  Given that, one of the largest challenges was to develop novel extensive classification schemes for the theories, concepts and research methods within the field of electoral behaviour.  ... 
doi:10.5281/zenodo.4700169 fatcat:sjz3hvossvgcfhbbwsj74l2v7q

Multiclass Data Segmentation using Diffuse Interface Methods on Graphs [article]

Cristina Garcia-Cardona, Ekaterina Merkurjev, Andrea L. Bertozzi, Arjuna Flenner, Allon Percus
2014 arXiv   pre-print
We present two graph-based algorithms for multiclass segmentation of high-dimensional data.  ...  The second algorithm is a uses a graph adaptation of the classical numerical Merriman-Bence-Osher (MBO) scheme, which alternates between diffusion and thresholding.  ...  in Applied Mathematics, and the W.  ... 
arXiv:1302.3913v2 fatcat:lai6mmkjebga7fqvdtftyfaw5i
« Previous Showing results 1 — 15 out of 32,580 results