25,555 Hits in 4.6 sec

An analysis of how ensembles of collective classifiers improve predictions in graphs

Hoda Eldardiry, Jennifer Neville
2012 Proceedings of the 21st ACM international conference on Information and knowledge management - CIKM '12  
We present a theoretical analysis framework that shows how ensembles of collective classifiers can improve predictions for graph data.  ...  We show how collective ensemble classification reduces errors due to variance in learning and more interestingly inference.  ...  The analytical results shows how the simple relational ensemble improves performance over the single collective classifier, as well as how the interleaved ensemble improves performance over the simple  ... 
doi:10.1145/2396761.2396793 dblp:conf/cikm/EldardiryN12 fatcat:7ac3s5usuzf7lfyka45antz2w4

Characterizing and Detecting Money Laundering Activities on the Bitcoin Network [article]

Yining Hu, Suranga Seneviratne, Kanchana Thilakarathna, Kensuke Fukuda, Aruna Seneviratne
2019 arXiv   pre-print
Using data collected over three years, we create transaction graphs and provide an in-depth analysis on various graph characteristics to differentiate money laundering transactions from regular transactions  ...  The classifier performance dropped compared to binary classification, however, the prediction can be improved with simple ensemble techniques for some services.  ...  Section 3 presents details of our data collection, ground truth labelling and how we created the Bitcoin transaction graphs.  ... 
arXiv:1912.12060v1 fatcat:vfg6enbadfcpvmespisesfh5oi

Multilabel Classification through Random Graph Ensembles [article]

Hongyu Su, Juho Rousu
2013 arXiv   pre-print
For ensemble learning, differences among the output graphs provide the required base classifier diversity and lead to improved performance in the increasing size of the ensemble.  ...  In our experiments, the random graph ensembles are very competitive and robust, ranking first or second on most of the datasets.  ...  Acknowledgments The work was financially supported by Helsinki Doctoral Programme in Computer Science (Hecse), Academy of Finland grant 118653 (ALGODAN), IST Programme of the European  ... 
arXiv:1310.8428v2 fatcat:kyuozkuoqzhtpmmlz5ubdqclke

Predicting Parallelization of Sequential Programs Using Supervised Learning

Daniel Fried, Zhen Li, Ali Jannesari, Felix Wolf
2013 2013 12th International Conference on Machine Learning and Applications  
We investigate an automatic method for classifying which regions of sequential programs could be parallelized, using dynamic features of the code collected at runtime.  ...  dependency graph features of secondary importance.  ...  Although not directly predicting parallelization, Park et al [11] use an SVM with a kernel function operating on the static control flow graph of a program to predict the improvements gained from compiler  ... 
doi:10.1109/icmla.2013.108 dblp:conf/icmla/FriedLJW13 fatcat:wwh6qdq27jd45oxfa32ssx43rm

Multilabel classification through random graph ensembles

Hongyu Su, Juho Rousu
2014 Machine Learning  
For ensemble learning, differences among the output graphs provide the required base classifier diversity and lead to improved performance in the increasing size of the ensemble.  ...  We put forward a theoretical explanation of the behaviour of multilabel ensembles in terms of the diversity and coherence of microlabel predictions, generalizing previous work on single target ensembles  ...  Acknowledgments The work was financially supported by Helsinki Doctoral Programme in Computer Science (Hecse), Academy of Finland grant 118653 (ALGODAN), IST Programme of the European Community under the  ... 
doi:10.1007/s10994-014-5465-9 fatcat:cmq6knacfffcdh7e3e7i7gkzqa

Ensembles of instance selection methods: A comparative study

Marcin Blachnik
2019 International Journal of Applied Mathematics and Computer Science  
Instance selection is often performed as one of the preprocessing methods which, along with feature selection, allows a significant reduction in computational complexity and an increase in prediction accuracy  ...  So far, only few authors have considered ensembles of instance selection methods, while the ensembles of final predictive models attract many researchers.  ...  First, we provide an overview of instance selection methods and the state of the art of ensembles in application to predictive models.  ... 
doi:10.2478/amcs-2019-0012 fatcat:fv3cqstwd5a7ndodtoztyfvs2y

A New Ensemble Model for Efficient Churn Prediction in Mobile Telecommunication

Namhyoung Kim, Jaewook Lee, Kyu-Hwan Jung, Yong Seog Kim
2012 2012 45th Hawaii International Conference on System Sciences  
In particular, this study introduces a uniformly subsampled ensemble model of SVM classifiers combined with principal component analysis (PCA) not only to reduce the high dimensionality of data but also  ...  This paper explores the possible application of a single SVM classifier and its variants to churner identification problem in mobile telecommunication industry in which the role of customer retention program  ...  Finally, the prediction of all classifiers will be aggregated via a weighted summation to construct the final prediction as an ensemble model for each record in a test data.  ... 
doi:10.1109/hicss.2012.74 dblp:conf/hicss/KimLJK12 fatcat:3sxhkqngwjgobjog4vkjvp7cxq

Design of adaptive ensemble classifier for online sentiment analysis and opinion mining

Sanjeev Kumar, Ravendra Singh, Mohammad Zubair Khan, Abdulfattah Noorwali
2021 PeerJ Computer Science  
The weight of the classifier decides the contribution of each classifier in the final classification results.  ...  The proposed method creates and adds a new classifier to the ensemble whenever a drift happens. A weighting mechanism is implemented, which provides weights to each classifier in the ensemble.  ...  In this novel proposed method, an ensemble classifier will be created to improve the performance for sentiment analysis. The objectives of this study are: 1.  ... 
doi:10.7717/peerj-cs.660 fatcat:yojujw7tbnde5jm2e5d5vxbcpy

A General Bayesian Network-Assisted Ensemble System for Context Prediction: An Emphasis on Location Prediction [chapter]

Kun Chang Lee, Heeryon Cho
2010 Lecture Notes in Computer Science  
To improve the prediction accuracy of such systems, various methods have been proposed and tested; these include Bayesian networks, decision classifiers, and SVMs.  ...  Still, greater accuracy may be achieved when individual classifiers are integrated into an ensemble system.  ...  The prediction accuracy increases in general for the graded ensemble approach when an SVM classifier is added to the GBN+DecisionTree ensembles.  ... 
doi:10.1007/978-3-642-17569-5_29 fatcat:emedwq2xxfexpfowtmns5wx4ke

Diversified Multiscale Graph Learning with Graph Self-Correction [article]

Yuzhao Chen, Yatao Bian, Jiying Zhang, Xi Xiao, Tingyang Xu, Yu Rong, Junzhou Huang
2021 arXiv   pre-print
The proposed DBR instead enhances the ensemble diversity at the graph-level embeddings by leveraging the interaction among individual classifiers.  ...  Extensive experiments on popular graph classification benchmarks show that the proposed GSC mechanism leads to significant improvements over state-of-the-art graph pooling methods.  ...  A common solution to improve the ensemble diversity is to build multiple classifiers that get trained with different sampled data in an independent manner.  ... 
arXiv:2103.09754v1 fatcat:m45gmpnvm5fipozyucbkvjhspq

Cyberbullying Detection in Social Networks: Artificial Intelligence Approach

Nureni Ayofe Azeez, Sunday O. Idiakose, Chinazo Juliet Onyema, Charles Van Der Vyver
2021 Journal of Cyber Security and Mobility  
In this work, efforts were made to review prominent classification algorithms and also to propose an ensemble model for identifying cases of cyberbullying, using Twitter datasets.  ...  The ensemble model has shown to improve the results of its constituent classifiers with medians of 0.77, 0.66 and 0.94, as against the 0.59, 0.42 and 0.86 of Linear Support Vector Classifier.  ...  Figure 2 2 Line graph of Results Obtained v Classifiers (Dataset 1). Figure 3 3 Analysis of results obtained against classifiers using Boxplots (Dataset 1).  ... 
doi:10.13052/jcsm2245-1439.1046 fatcat:d6lby7akqnekvamogfkedygyva

Bootstrapping Graph Convolutional Neural Networks for Autism Spectrum Disorder Classification [article]

Rushil Anirudh, Jayaraman J. Thiagarajan
2018 arXiv   pre-print
Though the underlying graph strongly dictates the overall performance, there exists no systematic way of choosing an appropriate graph in practice, thus making predictive models non-robust.  ...  Graph neural networks have shown improvements in inferencing with graph-structured data.  ...  PREDICTIVE MODELING WITH ENSEMBLES In this section, we describe the proposed approach for predictive modeling to classify subjects with autism.  ... 
arXiv:1704.07487v2 fatcat:mifvkywksjbw3lchkc7gimfai4

Augmented Machine Learning Ensemble Extension Model for Social Media Health Trends Predictions

2019 International journal of recent technology and engineering  
We introduce an Analytical Model which will identify most discussed terms/ topics of health/ healthcare on social networks to predict the emerging health trends.  ...  Ensemble Learning wherein an array of various Machine Learning techniques can be employed to achieve better classification or clustering results.  ...  Figure 4 4 illustrates how the Augmented Machine Learning Ensemble Extended (AMLEE) model can utilize both an Augmentation as well as an Ensemble approach to improve prediction accuracy.  ... 
doi:10.35940/ijrte.b1091.0782s719 fatcat:f57k7bqqojg4vimz7vqrvjmxnu

Fibers of Failure: Classifying Errors in Predictive Processes

Leo S. Carlsson, Mikael Vejdemo-Johansson, Gunnar Carlsson, Pär G. Jönsson
2020 Algorithms  
Our method uses Mapper, an algorithm from topological data analysis (TDA), to build a graphical model of input data stratified by prediction errors.  ...  Predictive models are used in many different fields of science and engineering and are always prone to make faulty predictions.  ...  The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript, or in the decision to publish the results.  ... 
doi:10.3390/a13060150 fatcat:q5niz3xda5edlpu5norlxakun4

JKRW Link Prediction – A New Ensemble Technique Based on Merging Other Known Techniques in The Social Network Analysis

Aya Taleb, Rizik M. H. Al-Sayyed, Hamed S. Al-Bdour
2021 International Journal of Interactive Mobile Technologies  
In this research, a new technique to improve the accuracy of the link prediction for most of the networks is proposed; it is based on the prediction ensemble approach using the voting merging technique  ...  Results from applying the evaluation matrices verify the improvement of JKRW effectiveness and stability in comparison to the other tested models.  ...  that can analyze and predict these links in an accurate and improved method.  ... 
doi:10.3991/ijim.v15i12.22831 fatcat:qjoafxy3bfgy5l2f2w72clh6sm
« Previous Showing results 1 — 15 out of 25,555 results