{"id":{"repo_id":"colostate","oai_identifier":"oai:mountainscholar.org:10217/244817"},"canonical_url":"https://search.dev.ndltd.org/etd/colostate/oai:mountainscholar.org:10217/244817","repository":{"repo_id":"colostate","name":"Colorado State University","base_url":"https://api.mountainscholar.org/server/oai/request"},"display":{"title":"Graph feature engineering and coordinate-based learning for transferable and energy-efficient artificial intelligence","abstract":"A comprehensive framework for efficient and scalable graph representation learning is presented, emphasizing coordinate-based and explicit structural methods. The research addresses the limitations of Graph Neural Networks (GNNs) in resource-constrained environments, including edge devices and large-scale deployments, by developing lightweight, non-neural alternatives. The first contribution is the Network Feature Embedding (NFE) pipeline, which integrates diffusion-based, positional, and structural descriptors into a unified representation for node classification. The second contribution is the Topology Coordinate-Driven Random Forests (TC-DRF) framework, which combines anchor-based topology coordinates with Random Forest classifiers for graph-level learning and cross-dataset transfer. Extensive evaluations of NFE and TC-DRF on vision, molecular, and social graph benchmarks demonstrate competitive predictive performance while substantially reducing computational overhead, memory footprint, and energy consumption. The proposed frameworks enable zero-shot cross-dataset transfer, maintain robustness under class imbalance, and support practical deployment in Green AI settings. Edge-device experiments, including deployment on Raspberry Pi hardware, confirm sub-millisecond inference latency and ultra-low energy usage. This research challenges the prevailing reliance on deep message-passing architectures for graph learning, demonstrating that explicit structural representations coupled with lightweight models provide viable, interpretable, and resource-efficient alternatives. The findings contribute to the advancement of scalable and sustainable graph learning methodologies and establish a foundation for future work in structural embeddings, dynamic graph analysis, and hybrid structural-attribute learning models.","abstract_html":"A comprehensive framework for efficient and scalable graph representation learning is presented, emphasizing coordinate-based and explicit structural methods. The research addresses the limitations of Graph Neural Networks (GNNs) in resource-constrained environments, including edge devices and large-scale deployments, by developing lightweight, non-neural alternatives. The first contribution is the Network Feature Embedding (NFE) pipeline, which integrates diffusion-based, positional, and structural descriptors into a unified representation for node classification. The second contribution is the Topology Coordinate-Driven Random Forests (TC-DRF) framework, which combines anchor-based topology coordinates with Random Forest classifiers for graph-level learning and cross-dataset transfer. Extensive evaluations of NFE and TC-DRF on vision, molecular, and social graph benchmarks demonstrate competitive predictive performance while substantially reducing computational overhead, memory footprint, and energy consumption. The proposed frameworks enable zero-shot cross-dataset transfer, maintain robustness under class imbalance, and support practical deployment in Green AI settings. Edge-device experiments, including deployment on Raspberry Pi hardware, confirm sub-millisecond inference latency and ultra-low energy usage. This research challenges the prevailing reliance on deep message-passing architectures for graph learning, demonstrating that explicit structural representations coupled with lightweight models provide viable, interpretable, and resource-efficient alternatives. The findings contribute to the advancement of scalable and sustainable graph learning methodologies and establish a foundation for future work in structural embeddings, dynamic graph analysis, and hybrid structural-attribute learning models.","abstract_has_math":false,"creators":["Yasodara, Hansi, author","Jayasumana, Anura, advisor","Pasricha, Sudeep, committee member","Ray, Indrakshi, committee member"],"institution":"Colorado State University. Libraries","degree_name":"Master of Science (M.S.)","degree_level":"Masters","degree_discipline":"Electrical and Computer Engineering","degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026","date_published":"2026","updated_at":"2026-07-27T19:13:16Z","subjects":["graph learning","green AI","transfer learning","graph representation learning","graph embedding neural networks (GENNs)","topology-aware learning"],"languages":["eng","English"],"rights":["Copyright and other restrictions may apply. User is responsible for compliance with all applicable laws. For information about copyright law, please see https://libguides.colostate.edu/copyright."],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://doi.org/10.25675/3.027177"],"render_values":[{"text":"https://doi.org/10.25675/3.027177","href":"https://doi.org/10.25675/3.027177","code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/10217/244817","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Yasodara, Hansi, author","Jayasumana, Anura, advisor","Pasricha, Sudeep, committee member","Ray, Indrakshi, committee member"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2026-06-08T10:31:46Z"]},{"key":"dc:date.issued","label":"Date","values":["2026"]},{"key":"dc:publisher","label":"Institution","values":["Colorado State University. Libraries"]},{"key":"dc:type","label":"Dc Type","values":["Text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical and Computer Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (M.S.)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Colorado State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["graph learning","green AI","transfer learning","graph representation learning","graph embedding neural networks (GENNs)","topology-aware learning"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English"]},{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright and other restrictions may apply. User is responsible for compliance with all applicable laws. For information about copyright law, please see https://libguides.colostate.edu/copyright."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["PaththiniHettiArachchige_colostate_0053N_19566.pdf"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10217/244817","https://doi.org/10.25675/3.027177"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["A comprehensive framework for efficient and scalable graph representation learning is presented, emphasizing coordinate-based and explicit structural methods. The research addresses the limitations of Graph Neural Networks (GNNs) in resource-constrained environments, including edge devices and large-scale deployments, by developing lightweight, non-neural alternatives. The first contribution is the Network Feature Embedding (NFE) pipeline, which integrates diffusion-based, positional, and structural descriptors into a unified representation for node classification. The second contribution is the Topology Coordinate-Driven Random Forests (TC-DRF) framework, which combines anchor-based topology coordinates with Random Forest classifiers for graph-level learning and cross-dataset transfer. Extensive evaluations of NFE and TC-DRF on vision, molecular, and social graph benchmarks demonstrate competitive predictive performance while substantially reducing computational overhead, memory footprint, and energy consumption. The proposed frameworks enable zero-shot cross-dataset transfer, maintain robustness under class imbalance, and support practical deployment in Green AI settings. Edge-device experiments, including deployment on Raspberry Pi hardware, confirm sub-millisecond inference latency and ultra-low energy usage. This research challenges the prevailing reliance on deep message-passing architectures for graph learning, demonstrating that explicit structural representations coupled with lightweight models provide viable, interpretable, and resource-efficient alternatives. The findings contribute to the advancement of scalable and sustainable graph learning methodologies and establish a foundation for future work in structural embeddings, dynamic graph analysis, and hybrid structural-attribute learning models."]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["born digital","masters theses"]},{"key":"dc:title","label":"Title","values":["Graph feature engineering and coordinate-based learning for transferable and energy-efficient artificial intelligence"]}]}],"canonical_facts":{"dc:creator":["Yasodara, Hansi, author","Jayasumana, Anura, advisor","Pasricha, Sudeep, committee member","Ray, Indrakshi, committee member"],"dc:date.accessioned":["2026-06-08T10:31:46Z"],"dc:date.issued":["2026"],"dc:description.abstract":["A comprehensive framework for efficient and scalable graph representation learning is presented, emphasizing coordinate-based and explicit structural methods. The research addresses the limitations of Graph Neural Networks (GNNs) in resource-constrained environments, including edge devices and large-scale deployments, by developing lightweight, non-neural alternatives. The first contribution is the Network Feature Embedding (NFE) pipeline, which integrates diffusion-based, positional, and structural descriptors into a unified representation for node classification. The second contribution is the Topology Coordinate-Driven Random Forests (TC-DRF) framework, which combines anchor-based topology coordinates with Random Forest classifiers for graph-level learning and cross-dataset transfer. Extensive evaluations of NFE and TC-DRF on vision, molecular, and social graph benchmarks demonstrate competitive predictive performance while substantially reducing computational overhead, memory footprint, and energy consumption. The proposed frameworks enable zero-shot cross-dataset transfer, maintain robustness under class imbalance, and support practical deployment in Green AI settings. Edge-device experiments, including deployment on Raspberry Pi hardware, confirm sub-millisecond inference latency and ultra-low energy usage. This research challenges the prevailing reliance on deep message-passing architectures for graph learning, demonstrating that explicit structural representations coupled with lightweight models provide viable, interpretable, and resource-efficient alternatives. The findings contribute to the advancement of scalable and sustainable graph learning methodologies and establish a foundation for future work in structural embeddings, dynamic graph analysis, and hybrid structural-attribute learning models."],"dc:format.medium":["born digital","masters theses"],"dc:identifier":["PaththiniHettiArachchige_colostate_0053N_19566.pdf"],"dc:identifier.uri":["https://hdl.handle.net/10217/244817","https://doi.org/10.25675/3.027177"],"dc:language":["English"],"dc:language.iso":["eng"],"dc:publisher":["Colorado State University. Libraries"],"dc:rights":["Copyright and other restrictions may apply. User is responsible for compliance with all applicable laws. For information about copyright law, please see https://libguides.colostate.edu/copyright."],"dc:subject":["graph learning","green AI","transfer learning","graph representation learning","graph embedding neural networks (GENNs)","topology-aware learning"],"dc:title":["Graph feature engineering and coordinate-based learning for transferable and energy-efficient artificial intelligence"],"dc:type":["Text"],"thesis:degree_discipline":["Electrical and Computer Engineering"],"thesis:degree_level":["Masters"],"thesis:degree_name":["Master of Science (M.S.)"],"thesis:institution_name":["Colorado State University"]},"updated_at":"2026-07-27T19:13:16Z"}