{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/106491"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/106491","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Relation2vec: Contextualized network embedding for heterogeneous information networks","abstract":"From biology to sociology, network theory has been used as a tool for modeling the relationships among entities in complex systems. However, with the emergence of big data, applying the conventional network analysis algorithms, which are often combinatorial, to the contemporary networks is challenging due to the sheer size of the present day network data. On the other hand, deep neural networks (DNNs) have been exceptionally successful at learning from big data and achieved superhuman performance in the fields of computer vision and natural language processing. Hence, there is an opportunity to harness the power of DNNs for network analysis. Since DNNs require their inputs to be in the form of real-valued vectors, we need to use network embedding techniques to generate low-dimensional vectorized representations of the network that accurately encode the rich information and features that are relevant to the network analysis task. In this thesis, we present relation2vec, a contextualized network embedding method for heterogeneous information networks (HINs), in which there are more than one type of nodes and edges. Our method leverages the idea of meta-path, which allows a high-level abstraction of paths and denotes complex relationships among the nodes, to provide context for the nodes in the network, and then utilizes DNN, specifically, bi-directional long short-term memory, to encode the contextual information for each node, along with other rich information and heterogeneity, in the embeddings for both nodes and paths in HINs. We evaluate the performance of relation2vec across DBLP and Yelp datasets via four network analysis tasks: visualization, clustering purity test, node type prediction and path type prediction. The experiment results show that rela- tion2vec outperforms other state-of-the-art HIN embedding methods by 17% to 33% for average cluster purity and on average 0.36 for DBLP and 0.16 for Yelp in f-score for path type prediction. The performance of node type prediction is also competitive with the state of the art.","abstract_html":"From biology to sociology, network theory has been used as a tool for modeling the relationships among entities in complex systems. However, with the emergence of big data, applying the conventional network analysis algorithms, which are often combinatorial, to the contemporary networks is challenging due to the sheer size of the present day network data. On the other hand, deep neural networks (DNNs) have been exceptionally successful at learning from big data and achieved superhuman performance in the fields of computer vision and natural language processing. Hence, there is an opportunity to harness the power of DNNs for network analysis. Since DNNs require their inputs to be in the form of real-valued vectors, we need to use network embedding techniques to generate low-dimensional vectorized representations of the network that accurately encode the rich information and features that are relevant to the network analysis task. In this thesis, we present relation2vec, a contextualized network embedding method for heterogeneous information networks (HINs), in which there are more than one type of nodes and edges. Our method leverages the idea of meta-path, which allows a high-level abstraction of paths and denotes complex relationships among the nodes, to provide context for the nodes in the network, and then utilizes DNN, specifically, bi-directional long short-term memory, to encode the contextual information for each node, along with other rich information and heterogeneity, in the embeddings for both nodes and paths in HINs. We evaluate the performance of relation2vec across DBLP and Yelp datasets via four network analysis tasks: visualization, clustering purity test, node type prediction and path type prediction. The experiment results show that rela- tion2vec outperforms other state-of-the-art HIN embedding methods by 17% to 33% for average cluster purity and on average 0.36 for DBLP and 0.16 for Yelp in f-score for path type prediction. The performance of node type prediction is also competitive with the state of the art.","abstract_has_math":false,"creators":["Zeng, Ziheng"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Vasudevan, Shobha"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-03-02T22:38:57Z","date_published":"2020-03-02T22:38:57Z","updated_at":"2026-07-22T22:24:47Z","subjects":["heterogeneous information networks","network embedding","meta-path based","graph representation learning"],"languages":["en"],"rights":["Copyright 2019 Ziheng Zeng"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/106491","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Vasudevan, Shobha"]},{"key":"dc:creator","label":"Author","values":["Zeng, Ziheng"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2020-03-02T22:38:57Z","2022-03-03T10:15:08Z","2019-12-09","2019-12"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["heterogeneous information networks","network embedding","meta-path based","graph representation learning"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2019 Ziheng Zeng"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/106491"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["From biology to sociology, network theory has been used as a tool for modeling the relationships among entities in complex systems. However, with the emergence of big data, applying the conventional network analysis algorithms, which are often combinatorial, to the contemporary networks is challenging due to the sheer size of the present day network data. On the other hand, deep neural networks (DNNs) have been exceptionally successful at learning from big data and achieved superhuman performance in the fields of computer vision and natural language processing. Hence, there is an opportunity to harness the power of DNNs for network analysis. Since DNNs require their inputs to be in the form of real-valued vectors, we need to use network embedding techniques to generate low-dimensional vectorized representations of the network that accurately encode the rich information and features that are relevant to the network analysis task. In this thesis, we present relation2vec, a contextualized network embedding method for heterogeneous information networks (HINs), in which there are more than one type of nodes and edges. Our method leverages the idea of meta-path, which allows a high-level abstraction of paths and denotes complex relationships among the nodes, to provide context for the nodes in the network, and then utilizes DNN, specifically, bi-directional long short-term memory, to encode the contextual information for each node, along with other rich information and heterogeneity, in the embeddings for both nodes and paths in HINs. We evaluate the performance of relation2vec across DBLP and Yelp datasets via four network analysis tasks: visualization, clustering purity test, node type prediction and path type prediction. The experiment results show that rela- tion2vec outperforms other state-of-the-art HIN embedding methods by 17% to 33% for average cluster purity and on average 0.36 for DBLP and 0.16 for Yelp in f-score for path type prediction. The performance of node type prediction is also competitive with the state of the art.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2021-12-01","The student, Ziheng Zeng, accepted the attached license on 2019-12-05 at 10:54.","The student, Ziheng Zeng, submitted this Thesis for approval on 2019-12-05 at 10:59.","This Thesis was approved for publication on 2019-12-09 at 08:22.","DSpace SAF Submission Ingestion Package generated from Vireo submission #14714 on 2020-02-28 at 17:38:01","Made available in DSpace on 2020-03-02T22:38:57Z (GMT). No. of bitstreams: 2 ZENG-THESIS-2019.pdf: 2782214 bytes, checksum: f0dc0ef68c082f6abb1e695d3770ed40 (MD5) LICENSE.txt: 4208 bytes, checksum: ff70c6a91f6724438beb78219913b079 (MD5) Previous issue date: 2019-12-09","Embargo set by: Seth Robbins for item 114035 Lift date: 2022-03-02T22:39:04Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Limited Restriction Lifted for Item 114035 on 2022-03-03T10:15:08Z."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Relation2vec: Contextualized network embedding for heterogeneous information networks"]}]}],"canonical_facts":{"dc:contributor":["Vasudevan, Shobha"],"dc:creator":["Zeng, Ziheng"],"dc:date":["2020-03-02T22:38:57Z","2022-03-03T10:15:08Z","2019-12-09","2019-12"],"dc:description":["From biology to sociology, network theory has been used as a tool for modeling the relationships among entities in complex systems. However, with the emergence of big data, applying the conventional network analysis algorithms, which are often combinatorial, to the contemporary networks is challenging due to the sheer size of the present day network data. On the other hand, deep neural networks (DNNs) have been exceptionally successful at learning from big data and achieved superhuman performance in the fields of computer vision and natural language processing. Hence, there is an opportunity to harness the power of DNNs for network analysis. Since DNNs require their inputs to be in the form of real-valued vectors, we need to use network embedding techniques to generate low-dimensional vectorized representations of the network that accurately encode the rich information and features that are relevant to the network analysis task. In this thesis, we present relation2vec, a contextualized network embedding method for heterogeneous information networks (HINs), in which there are more than one type of nodes and edges. Our method leverages the idea of meta-path, which allows a high-level abstraction of paths and denotes complex relationships among the nodes, to provide context for the nodes in the network, and then utilizes DNN, specifically, bi-directional long short-term memory, to encode the contextual information for each node, along with other rich information and heterogeneity, in the embeddings for both nodes and paths in HINs. We evaluate the performance of relation2vec across DBLP and Yelp datasets via four network analysis tasks: visualization, clustering purity test, node type prediction and path type prediction. The experiment results show that rela- tion2vec outperforms other state-of-the-art HIN embedding methods by 17% to 33% for average cluster purity and on average 0.36 for DBLP and 0.16 for Yelp in f-score for path type prediction. The performance of node type prediction is also competitive with the state of the art.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2021-12-01","The student, Ziheng Zeng, accepted the attached license on 2019-12-05 at 10:54.","The student, Ziheng Zeng, submitted this Thesis for approval on 2019-12-05 at 10:59.","This Thesis was approved for publication on 2019-12-09 at 08:22.","DSpace SAF Submission Ingestion Package generated from Vireo submission #14714 on 2020-02-28 at 17:38:01","Made available in DSpace on 2020-03-02T22:38:57Z (GMT). No. of bitstreams: 2 ZENG-THESIS-2019.pdf: 2782214 bytes, checksum: f0dc0ef68c082f6abb1e695d3770ed40 (MD5) LICENSE.txt: 4208 bytes, checksum: ff70c6a91f6724438beb78219913b079 (MD5) Previous issue date: 2019-12-09","Embargo set by: Seth Robbins for item 114035 Lift date: 2022-03-02T22:39:04Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Limited Restriction Lifted for Item 114035 on 2022-03-03T10:15:08Z."],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/106491"],"dc:language":["en"],"dc:rights":["Copyright 2019 Ziheng Zeng"],"dc:subject":["heterogeneous information networks","network embedding","meta-path based","graph representation learning"],"dc:title":["Relation2vec: Contextualized network embedding for heterogeneous information networks"],"dc:type":["text"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:47Z"}