{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/101634"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/101634","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Curriculum learning for heterogeneous star network embedding via deep reinforcement learning","abstract":"Learning node representations for networks has attracted much attention recently due to its effectiveness in a variety of applications. This paper focuses on learning node representations for heterogeneous star networks, which have a center node type linked with multiple attribute node types through different types of edges. In heterogeneous star networks, we observe that the training order of different types of edges affects the learning performance significantly. Therefore we study learning curricula for node representation learning in heterogeneous star networks, i.e., learning an optimal sequence of edges of different types for the node representation learning process. We formulate the problem as a Markov decision process, with the action as selecting a specific type of edges for learning or terminating the training process, and the state as the sequence of edge types selected so far. The reward is calculated as the performance on external tasks with node representations as features, and the goal is to take a series of actions to maximize the cumulative rewards. We propose an approach based on deep reinforcement learning for this problem. Our approach leverages LSTM models to encode states and further estimate the expected cumulative reward of each state-action pair, which essentially measures the long-term performance of different actions at each state. Experimental results on real-world heterogeneous star networks demonstrate the effectiveness and efficiency of our approach over competitive baseline approaches.","abstract_html":"Learning node representations for networks has attracted much attention recently due to its effectiveness in a variety of applications. This paper focuses on learning node representations for heterogeneous star networks, which have a center node type linked with multiple attribute node types through different types of edges. In heterogeneous star networks, we observe that the training order of different types of edges affects the learning performance significantly. Therefore we study learning curricula for node representation learning in heterogeneous star networks, i.e., learning an optimal sequence of edges of different types for the node representation learning process. We formulate the problem as a Markov decision process, with the action as selecting a specific type of edges for learning or terminating the training process, and the state as the sequence of edge types selected so far. The reward is calculated as the performance on external tasks with node representations as features, and the goal is to take a series of actions to maximize the cumulative rewards. We propose an approach based on deep reinforcement learning for this problem. Our approach leverages LSTM models to encode states and further estimate the expected cumulative reward of each state-action pair, which essentially measures the long-term performance of different actions at each state. Experimental results on real-world heterogeneous star networks demonstrate the effectiveness and efficiency of our approach over competitive baseline approaches.","abstract_has_math":false,"creators":["Qu, Meng"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Han, Jiawei"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2018,"date_issued":"2018-09-27T16:28:00Z","date_published":"2018-09-27T16:28:00Z","updated_at":"2026-07-22T22:24:40Z","subjects":["Curriculum Learning Network Embedding Reinforcement Learning"],"languages":["en"],"rights":["Copyright 2018 Meng Qu"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/101634","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Han, Jiawei"]},{"key":"dc:creator","label":"Author","values":["Qu, Meng"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2018-09-27T16:28:00Z","2020-09-28T09:15:24Z","2018-05-01","2018-08"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"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":["Curriculum Learning Network Embedding Reinforcement 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 2018 Meng Qu"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/101634"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Learning node representations for networks has attracted much attention recently due to its effectiveness in a variety of applications. This paper focuses on learning node representations for heterogeneous star networks, which have a center node type linked with multiple attribute node types through different types of edges. In heterogeneous star networks, we observe that the training order of different types of edges affects the learning performance significantly. Therefore we study learning curricula for node representation learning in heterogeneous star networks, i.e., learning an optimal sequence of edges of different types for the node representation learning process. We formulate the problem as a Markov decision process, with the action as selecting a specific type of edges for learning or terminating the training process, and the state as the sequence of edge types selected so far. The reward is calculated as the performance on external tasks with node representations as features, and the goal is to take a series of actions to maximize the cumulative rewards. We propose an approach based on deep reinforcement learning for this problem. Our approach leverages LSTM models to encode states and further estimate the expected cumulative reward of each state-action pair, which essentially measures the long-term performance of different actions at each state. Experimental results on real-world heterogeneous star networks demonstrate the effectiveness and efficiency of our approach over competitive baseline approaches.","Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2020-08-01","The student, Meng Qu, accepted the attached license on 2018-04-28 at 03:27.","The student, Meng Qu, submitted this Thesis for approval on 2018-04-28 at 03:32.","This Thesis was approved for publication on 2018-05-01 at 14:12.","DSpace SAF Submission Ingestion Package generated from Vireo submission #12548 on 2018-09-27 at 11:15:31","Made available in DSpace on 2018-09-27T16:28:00Z (GMT). No. of bitstreams: 2 QU-THESIS-2018.pdf: 796856 bytes, checksum: 30a59b6e036a099beb5aab939947cd7d (MD5) LICENSE.txt: 4204 bytes, checksum: 719b2eb6b187103bda6cfc701f3c93be (MD5) Previous issue date: 2018-05-01","Embargo set by: Seth Robbins for item 107731 Lift date: 2020-09-27T16:28:07Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 107731 Lift date: 2020-09-27T16:30:34Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 107731 Lift date: 2020-09-27T16:31:43Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 107731 Lift date: 2020-09-27T16:34:29Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only Restriction Lifted for Item 107731 on 2020-09-28T09:15:24Z."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Curriculum learning for heterogeneous star network embedding via deep reinforcement learning"]}]}],"canonical_facts":{"dc:contributor":["Han, Jiawei"],"dc:creator":["Qu, Meng"],"dc:date":["2018-09-27T16:28:00Z","2020-09-28T09:15:24Z","2018-05-01","2018-08"],"dc:description":["Learning node representations for networks has attracted much attention recently due to its effectiveness in a variety of applications. This paper focuses on learning node representations for heterogeneous star networks, which have a center node type linked with multiple attribute node types through different types of edges. In heterogeneous star networks, we observe that the training order of different types of edges affects the learning performance significantly. Therefore we study learning curricula for node representation learning in heterogeneous star networks, i.e., learning an optimal sequence of edges of different types for the node representation learning process. We formulate the problem as a Markov decision process, with the action as selecting a specific type of edges for learning or terminating the training process, and the state as the sequence of edge types selected so far. The reward is calculated as the performance on external tasks with node representations as features, and the goal is to take a series of actions to maximize the cumulative rewards. We propose an approach based on deep reinforcement learning for this problem. Our approach leverages LSTM models to encode states and further estimate the expected cumulative reward of each state-action pair, which essentially measures the long-term performance of different actions at each state. Experimental results on real-world heterogeneous star networks demonstrate the effectiveness and efficiency of our approach over competitive baseline approaches.","Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2020-08-01","The student, Meng Qu, accepted the attached license on 2018-04-28 at 03:27.","The student, Meng Qu, submitted this Thesis for approval on 2018-04-28 at 03:32.","This Thesis was approved for publication on 2018-05-01 at 14:12.","DSpace SAF Submission Ingestion Package generated from Vireo submission #12548 on 2018-09-27 at 11:15:31","Made available in DSpace on 2018-09-27T16:28:00Z (GMT). No. of bitstreams: 2 QU-THESIS-2018.pdf: 796856 bytes, checksum: 30a59b6e036a099beb5aab939947cd7d (MD5) LICENSE.txt: 4204 bytes, checksum: 719b2eb6b187103bda6cfc701f3c93be (MD5) Previous issue date: 2018-05-01","Embargo set by: Seth Robbins for item 107731 Lift date: 2020-09-27T16:28:07Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 107731 Lift date: 2020-09-27T16:30:34Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 107731 Lift date: 2020-09-27T16:31:43Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 107731 Lift date: 2020-09-27T16:34:29Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only Restriction Lifted for Item 107731 on 2020-09-28T09:15:24Z."],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/101634"],"dc:language":["en"],"dc:rights":["Copyright 2018 Meng Qu"],"dc:subject":["Curriculum Learning Network Embedding Reinforcement Learning"],"dc:title":["Curriculum learning for heterogeneous star network embedding via deep reinforcement learning"],"dc:type":["text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:40Z"}