Variable-Based Network Analysis of Datasets on Data Exchange Platforms

• URL: http://arxiv.org/abs/2003.05109v1
• Date: Wed, 11 Mar 2020 04:42:30 GMT
• Title: Variable-Based Network Analysis of Datasets on Data Exchange Platforms
• Authors: Teruaki Hayashi, Yukio Ohsawa
• Abstract summary: We apply a network approach with a novel variable-based structural analysis to the metadata of datasets on two data platform services. It was noted that the structures of the data networks are locally dense and highly assortative, similar to human-related net-works.
• Score: 0.15229257192293197
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recently, data exchange platforms have emerged in the digital economy to enable better resource allocation in a data-driven society, which requires cross-organizational data collaborations. Understanding the characteristics of the data on these platforms is important for their application; however, the structures of such platforms have not been extensively investigated. In this study, we apply a network approach with a novel variable-based structural analysis to the metadata of datasets on two data platform services. It was noted that the structures of the data networks are locally dense and highly assortative, similar to human-related net-works. Even though the data on these platforms are designed and collected differently, depending on the use objectives, the variables of heterogeneous data exhibit a power distribution, and the data networks exhibit multi-scaling behavior. Furthermore, we found that the data collection strategies of the platforms are related to the variety of variables, density of the networks, and their robustness from the viewpoint of sustainability and social acceptability of the data platforms.

Related papers

• Visual Data Diagnosis and Debiasing with Concept Graphs [50.84781894621378]
  Deep learning models often pick up inherent biases in the data during the training process, leading to unreliable predictions. We present CONBIAS, a novel framework for diagnosing and mitigating Concept co-occurrence Biases in visual datasets. We show that by employing a novel clique-based concept balancing strategy, we can mitigate these imbalances, leading to enhanced performance on downstream tasks.
  arXiv  Detail & Related papers  (2024-09-26T16:59:01Z)
• Leveraging GPT for the Generation of Multi-Platform Social Media Datasets for Research [0.0]
  Social media datasets are essential for research on disinformation, influence operations, social sensing, hate speech detection, cyberbullying, and other significant topics. Access to these datasets is often restricted due to costs and platform regulations. This paper explores the potential of large language models to create lexically and semantically relevant social media datasets across multiple platforms.
  arXiv  Detail & Related papers  (2024-07-11T09:12:39Z)
• UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction [93.77809355002591]
  We introduce UniTraj, a comprehensive framework that unifies various datasets, models, and evaluation criteria. We conduct extensive experiments and find that model performance significantly drops when transferred to other datasets. We provide insights into dataset characteristics to explain these findings.
  arXiv  Detail & Related papers  (2024-03-22T10:36:50Z)
• On the Cross-Dataset Generalization of Machine Learning for Network Intrusion Detection [50.38534263407915]
  Network Intrusion Detection Systems (NIDS) are a fundamental tool in cybersecurity. Their ability to generalize across diverse networks is a critical factor in their effectiveness and a prerequisite for real-world applications. In this study, we conduct a comprehensive analysis on the generalization of machine-learning-based NIDS through an extensive experimentation in a cross-dataset framework.
  arXiv  Detail & Related papers  (2024-02-15T14:39:58Z)
• Decentralized Data Governance as Part of a Data Mesh Platform: Concepts and Approaches [0.0]
  Data mesh is a socio-technical approach to decentralized analytics data management. This paper presents a conceptual model of key data mesh concepts and discusses different approaches to drive governance through platform means.
  arXiv  Detail & Related papers  (2023-07-05T15:18:15Z)
• infoVerse: A Universal Framework for Dataset Characterization with Multidimensional Meta-information [68.76707843019886]
  infoVerse is a universal framework for dataset characterization. infoVerse captures multidimensional characteristics of datasets by incorporating various model-driven meta-information. In three real-world applications (data pruning, active learning, and data annotation), the samples chosen on infoVerse space consistently outperform strong baselines.
  arXiv  Detail & Related papers  (2023-05-30T18:12:48Z)
• Federated Learning over Harmonized Data Silos [0.7106986689736825]
  Federated Learning is a distributed machine learning approach that enables geographically distributed data silos to collaboratively learn a joint machine learning model without sharing data. We propose an architectural vision for an end-to-end Federated Learning and Integration system, incorporating the critical steps of data harmonization and data imputation.
  arXiv  Detail & Related papers  (2023-05-15T19:55:51Z)
• TRoVE: Transforming Road Scene Datasets into Photorealistic Virtual Environments [84.6017003787244]
  This work proposes a synthetic data generation pipeline to address the difficulties and domain-gaps present in simulated datasets. We show that using annotations and visual cues from existing datasets, we can facilitate automated multi-modal data generation.
  arXiv  Detail & Related papers  (2022-08-16T20:46:08Z)
• Towards Federated Bayesian Network Structure Learning with Continuous Optimization [14.779035801521717]
  We present a cross-silo federated learning approach to estimate the structure of Bayesian network. We develop a distributed structure learning method based on continuous optimization.
  arXiv  Detail & Related papers  (2021-10-18T14:36:05Z)
• Collaborative Problem Solving on a Data Platform Kaggle [0.4511923587827301]
  Data exchange ecosystem is developed by platform services that facilitate data and knowledge exchange. In this study, we investigate Kaggle, a data analysis competition platform.
  arXiv  Detail & Related papers  (2021-07-26T02:28:01Z)
• Multi-level Graph Convolutional Networks for Cross-platform Anchor Link Prediction [47.047999403900775]
  Cross-platform account matching plays a significant role in social network analytics. We propose a novel framework that considers multi-level graph convolutions on both local network structure and hypergraph structure. The proposed method overcomes data insufficiency problem of existing work and does not necessarily rely on user demographic information.
  arXiv  Detail & Related papers  (2020-06-02T22:01:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.