Filters








14,382 Hits in 9.7 sec

Towards realistic artificial benchmark for community detection algorithms evaluation

Günce Keziban Orman, Vincent Labatut, Hocine Cherifi
2013 International Journal of Web Based Communities  
Artificially generated networks are often used as benchmarks for this purpose. However, previous studies showed their level of realism have a significant effect on the algorithms performance.  ...  Moreover, the results obtained with eleven popular community identification algorithms on these benchmarks show their performance decrease on more realistic networks.  ...  Indeed, its topological properties are closer to Towards realistic artificial benchmark for community detection algorithms 21 those encountered in real networks compared to LFR-CM.  ... 
doi:10.1504/ijwbc.2013.054908 fatcat:hobmpgoajvgn5ouxav65p24pde

Fast Detection of Size-Constrained Communities in Large Networks [chapter]

Marek Ciglan, Kjetil Nørvåg
2010 Lecture Notes in Computer Science  
Extensive evaluation of the algorithm on synthetic benchmark graphs for community detection showed that the proposed approach is very competitive with state-of-the-art methods, outperforming other approaches  ...  In this paper, we propose a new algorithm for detecting communities in networks.  ...  For those purposes, community detection benchmarks were proposed. Benchmarks generate artificial networks containing communities.  ... 
doi:10.1007/978-3-642-17616-6_10 fatcat:avxipr6ebfesxcbavso5nuidre

A Detailed Analysis of Benchmark Datasets for Network Intrusion Detection System

Mossa Ghurab, Ghaleb Gaphari, Faisal Alshami, Reem Alshamy, Suad Othman
2021 Asian Journal of Research in Computer Science  
There are a lot of researches proposed to develop the NIDS and depend on the dataset for the evaluation. Datasets allow evaluating the ability in detecting intrusion behavior.  ...  This paper introduces a detailed analysis of benchmark and recent datasets for NIDS.  ...  Toward developing a systematic approach to generate benchmark datasets for intrusion detection. computers & security. 2012;31(3):357-374. 48. Kumar G.  ... 
doi:10.9734/ajrcos/2021/v7i430185 fatcat:ymje2jsbzje7nocqdxpsbpsvii

Modular Networks for Validating Community Detection Algorithms [article]

Justin Fagnan, Afra Abnar, Reihaneh Rabbany, Osmar R. Zaiane
2018 arXiv   pre-print
We further show how common community detection algorithms rank differently when being evaluated on these benchmarks compared to current available alternatives.  ...  Given the lack of cluster labels in real-world networks, a model that generates realistic networks is required for accurate evaluation of these algorithm.  ...  In our experiment we showed how tuning these parameters provides means to generate a variety of realistic networks and presents different settings for comparing community detection algorithms.  ... 
arXiv:1801.01229v1 fatcat:2anjeolk6rhgxl373erakkqb3m

A Comparative Analysis of Community Detection Algorithms on Artificial Networks

Zhao Yang, René Algesheimer, Claudio J. Tessone
2016 Scientific Reports  
Based on simple network properties and the aforementioned results, we provide guidelines that help to choose the most adequate community detection algorithm for a given network.  ...  Many community detection algorithms have been developed to uncover the mesoscopic properties of complex networks.  ...  reported in this study, as well as Santo Fortunato for useful comments.  ... 
doi:10.1038/srep30750 pmid:27476470 pmcid:PMC4967864 fatcat:b7feo23yevaprpbxuv3auh3tre

Fluid Communities: A Competitive, Scalable and Diverse Community Detection Algorithm [article]

Ferran Parés, Dario Garcia-Gasulla, Armand Vilalta, Jonatan Moreno, Eduard Ayguadé, Jesús Labarta, Ulises Cortés, Toyotaro Suzumura
2017 arXiv   pre-print
We introduce a community detection algorithm (Fluid Communities) based on the idea of fluids interacting in an environment, expanding and contracting as a result of that interaction.  ...  To illustrate the relevance of the algorithm, we evaluate the diversity of the communities found by Fluid Communities, and find them to be significantly different from the ones found by alternative methods  ...  The performance of the algorithms was measured on artificially generated graphs provided by the LFR benchmark [12] , which defines a more realistic setting than the GN benchmark [13] , including scalefree  ... 
arXiv:1703.09307v3 fatcat:lppbnqf3qrdyvgufqpm55uf2vm

A Comparative Analysis of Community Detection Algorithms on Artificial Networks

Zhao Yang, Renn Algesheimer
2016 Social Science Research Network  
Based on simple network properties and the aforementioned results, we provide guidelines that help to choose the most adequate community detection algorithm for a given network.  ...  Based on simple network properties and the aforementioned results, we provide guidelines that help to choose the most adequate community detection algorithm for a given network.  ...  reported in this study, as well as Santo Fortunato for useful comments.  ... 
doi:10.2139/ssrn.2937843 fatcat:b5jja5bbkzgohjnf6reyphjgie

Towards Sonification in Multimodal and User-friendlyExplainable Artificial Intelligence

Björn W. Schuller, Tuomas Virtanen, Maria Riveiro, Georgios Rizos, Jing Han, Annamaria Mesaros, Konstantinos Drossos
2021 Proceedings of the 2021 International Conference on Multimodal Interaction  
While such approaches are good for communication via visual media such as in research papers or screens of intelligent devices, they may not always be the best way to explain; especially when the end user  ...  That involves incorporating innovative XAI algorithms to allow pointing back at the learning data responsible for decisions made by an AI, and to include decomposition of the data to identify salient aspects  ...  Towards Sonification in Multimodal and User-friendly Explainable Artificial Intelligence.  ... 
doi:10.1145/3462244.3479879 fatcat:m2gtqpihabgtded2bdjskwyvs4

Neuromorphic Engineering Needs Closed-Loop Benchmarks

Moritz B. Milde, Saeed Afshar, Ying Xu, Alexandre Marcireau, Damien Joubert, Bharath Ramesh, Yeshwanth Bethi, Nicholas O. Ralph, Sami El Arja, Nik Dennler, André van Schaik, Gregory Cohen
2022 Frontiers in Neuroscience  
The shift towards dynamic real-world benchmarking tasks should usher in richer, more resilient, and robust artificially intelligent systems in the future.  ...  evaluation metrics.  ...  Concluding Remarks In this article, we discussed the understandable reasons why the research community, whether neuromorphic or not, gravitates towards open-loop datasets to train and evaluate their artificially  ... 
doi:10.3389/fnins.2022.813555 pmid:35237122 pmcid:PMC8884247 fatcat:2chx7ilyive3nnjb3lbd2ytgbu

FedScale: Benchmarking Model and System Performance of Federated Learning at Scale [article]

Fan Lai, Yinwei Dai, Sanjay S. Singapuram, Jiachen Liu, Xiangfeng Zhu, Harsha V. Madhyastha, Mosharaf Chowdhury
2022 arXiv   pre-print
We combine the two to perform systematic benchmarking experiments and highlight potential opportunities for heterogeneity-aware co-optimizations in FL.  ...  We present FedScale, a federated learning (FL) benchmarking suite with realistic datasets and a scalable runtime to enable reproducible FL research.  ...  Acknowledgments We would like to thank the anonymous reviewers and Sym-bioticLab members for their insightful feedback.  ... 
arXiv:2105.11367v5 fatcat:6xfm4h37znecbkrqijjs3lo4um

Grid-based SensorDCSP

Ramón Béjar, Carmel Domshlak, Cèsar Fernández, Carla P. Gomes, Bart Selman, Magda Valls
2003 International Joint Conference on Artificial Intelligence  
We introduce Grid-based SensorDCSP, a geometrically structured benchmark problem for the study of distributed CSP algorithms.  ...  This domain provides realistic structure of the communication and tracking constraints. We formally define this problem, and perform its worst-case complexity analysis.  ...  Finally, a further step towards an even more realistic DisCSP benchmark would be to consider its optimization version: maximizing the number of tracked mobiles.  ... 
dblp:conf/ijcai/BejarDFGSV03 fatcat:ec5jlbite5d75balqzisd7dpce

Big Data Clustering via Community Detection and Hyperbolic Network Embedding in IoT Applications

Vasileios Karyotis, Konstantinos Tsitseklis, Konstantinos Sotiropoulos, Symeon Papavassiliou
2018 Sensors  
and random geometric topologies, and frequently-employed benchmark datasets for demonstrating its efficacy in terms of data clustering via community detection.  ...  Specifically, we propose a novel computational approach for enhancing the traditional Girvan-Newman (GN) community detection algorithm via hyperbolic network embedding.  ...  Data Clustering Framework via Hyperbolic Network Embedding Known Communities To evaluate the performance and accuracy of the proposed algorithm for clustering via community detection, a number of graphs  ... 
doi:10.3390/s18041205 pmid:29662043 pmcid:PMC5948775 fatcat:mmbe22hbcjhdnovug3jnwqgjhy

Wanderlust: Online Continual Object Detection in the Real World [article]

Jianren Wang, Xin Wang, Yue Shang-Guan, Abhinav Gupta
2021 arXiv   pre-print
These egocentric long-running videos provide a realistic playground for continual learning algorithms, especially in online embodied settings.  ...  We also introduce new evaluation metrics to evaluate the model performance and catastrophic forgetting and provide baseline studies for online continual object detection.  ...  However, realistic datasets and benchmarks, especially for object detection, are still missing. In this work, we presented a new online continual object detection benchmark dataset called OAK.  ... 
arXiv:2108.11005v2 fatcat:4wdu2v5kynbdpd5u2twarsodem

Real-World Image Datasets for Federated Learning [article]

Jiahuan Luo, Xueyang Wu, Yun Luo, Anbu Huang, Yunfeng Huang, Yang Liu, Qiang Yang
2021 arXiv   pre-print
Based on this dataset, we implemented two mainstream object detection algorithms (YOLO and Faster R-CNN) and provided an extensive benchmark on model performance, efficiency, and communication in a federated  ...  Consequently, advances on benchmark and model evaluations for federated learning have been lagging behind. In this paper, we introduce a real-world image dataset.  ...  In addition to one-stage approach towards object detection, we contain Faster R-CNN as our benchmark, which is a popular two-stage approach.  ... 
arXiv:1910.11089v3 fatcat:hwhljikoa5d47i2zl4mghre2oq

Identifying Properties of Real-World Optimisation Problems through a Questionnaire [article]

Koen van der Blom, Timo M. Deist, Vanessa Volz, Mariapia Marchi, Yusuke Nojima, Boris Naujoks, Akira Oyama, Tea Tušar
2021 arXiv   pre-print
Optimisation algorithms are commonly compared on benchmarks to get insight into performance differences.  ...  These are all important aspects to consider when designing realistic benchmark problems.  ...  This limits the use of gradient-based optimisation algorithms. Realistic benchmarks should preferably reflect these limitations.  ... 
arXiv:2011.05547v2 fatcat:5law7mfk5zf3pn5a24dl6yfswi
« Previous Showing results 1 — 15 out of 14,382 results