{"id":{"repo_id":"purdue-thes","oai_identifier":"oai:docs.lib.purdue.edu:open_access_dissertations-2661"},"canonical_url":"https://search.dev.ndltd.org/etd/purdue-thes/oai:docs.lib.purdue.edu:open_access_dissertations-2661","repository":{"repo_id":"purdue-thes","name":"Purdue University","base_url":"https://docs.lib.purdue.edu/do/oai/"},"display":{"title":"Scaling Up Network Analysis and Mining: Statistical Sampling, Estimation, and Pattern Discovery","abstract":"Network analysis and graph mining play a prominent role in providing insights and studying phenomena across various domains, including social, behavioral, biological, transportation, communication, and financial domains. Across all these domains, networks arise as a natural and rich representation for data. Studying these real-world networks is crucial for solving numerous problems that lead to high-impact applications. For example, identifying the behavior and interests of users in online social networks (e.g., viral marketing), monitoring and detecting virus outbreaks in human contact networks, predicting protein functions in biological networks, and detecting anomalous behavior in computer networks. A key characteristic of these networks is that their complex structure is massive and continuously evolving over time, which makes it challenging and computationally intensive to analyze, query, and model these networks in their entirety. In this dissertation, we propose sampling as well as fast, efficient, and scalable methods for network analysis and mining in both static and streaming graphs.","abstract_html":"Network analysis and graph mining play a prominent role in providing insights and studying phenomena across various domains, including social, behavioral, biological, transportation, communication, and financial domains. Across all these domains, networks arise as a natural and rich representation for data. Studying these real-world networks is crucial for solving numerous problems that lead to high-impact applications. For example, identifying the behavior and interests of users in online social networks (e.g., viral marketing), monitoring and detecting virus outbreaks in human contact networks, predicting protein functions in biological networks, and detecting anomalous behavior in computer networks. A key characteristic of these networks is that their complex structure is massive and continuously evolving over time, which makes it challenging and computationally intensive to analyze, query, and model these networks in their entirety. In this dissertation, we propose sampling as well as fast, efficient, and scalable methods for network analysis and mining in both static and streaming graphs.","abstract_has_math":false,"creators":["Ahmed, Nesreen Kamel"],"institution":null,"degree_name":"Doctor of Philosophy (PhD)","degree_level":"Dissertation","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Jennifer Neville","Christopher W Clifton","Walid G Aref","Sonia Fahmy"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2015,"date_issued":"2015-01-01T08:00:00Z","date_published":"2015-01-01T08:00:00Z","updated_at":"2026-07-24T03:54:44Z","subjects":["Data Mining","Graph Mining","Machine Learning","Network Science","Sampling","Statistical Estimation"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://docs.lib.purdue.edu/open_access_dissertations/1445","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Jennifer Neville","Christopher W Clifton","Walid G Aref","Sonia Fahmy"]},{"key":"dc:creator","label":"Author","values":["Ahmed, Nesreen Kamel"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy (PhD)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Data Mining","Graph Mining","Machine Learning","Network Science","Sampling","Statistical Estimation"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://docs.lib.purdue.edu/open_access_dissertations/1445"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Network analysis and graph mining play a prominent role in providing insights and studying phenomena across various domains, including social, behavioral, biological, transportation, communication, and financial domains. Across all these domains, networks arise as a natural and rich representation for data. Studying these real-world networks is crucial for solving numerous problems that lead to high-impact applications. For example, identifying the behavior and interests of users in online social networks (e.g., viral marketing), monitoring and detecting virus outbreaks in human contact networks, predicting protein functions in biological networks, and detecting anomalous behavior in computer networks. A key characteristic of these networks is that their complex structure is massive and continuously evolving over time, which makes it challenging and computationally intensive to analyze, query, and model these networks in their entirety. In this dissertation, we propose sampling as well as fast, efficient, and scalable methods for network analysis and mining in both static and streaming graphs."]},{"key":"dc:title","label":"Title","values":["Scaling Up Network Analysis and Mining: Statistical Sampling, Estimation, and Pattern Discovery"]}]}],"canonical_facts":{"dc:contributor":["Jennifer Neville","Christopher W Clifton","Walid G Aref","Sonia Fahmy"],"dc:creator":["Ahmed, Nesreen Kamel"],"dc:description.abstract":["Network analysis and graph mining play a prominent role in providing insights and studying phenomena across various domains, including social, behavioral, biological, transportation, communication, and financial domains. Across all these domains, networks arise as a natural and rich representation for data. Studying these real-world networks is crucial for solving numerous problems that lead to high-impact applications. For example, identifying the behavior and interests of users in online social networks (e.g., viral marketing), monitoring and detecting virus outbreaks in human contact networks, predicting protein functions in biological networks, and detecting anomalous behavior in computer networks. A key characteristic of these networks is that their complex structure is massive and continuously evolving over time, which makes it challenging and computationally intensive to analyze, query, and model these networks in their entirety. In this dissertation, we propose sampling as well as fast, efficient, and scalable methods for network analysis and mining in both static and streaming graphs."],"dc:identifier":["https://docs.lib.purdue.edu/open_access_dissertations/1445"],"dc:subject":["Data Mining","Graph Mining","Machine Learning","Network Science","Sampling","Statistical Estimation"],"dc:title":["Scaling Up Network Analysis and Mining: Statistical Sampling, Estimation, and Pattern Discovery"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Doctor of Philosophy (PhD)"]},"updated_at":"2026-07-24T03:54:44Z"}