{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/115773"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/115773","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Adversarial graph contrastive learning with information regularization","abstract":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-11-11 without embargo terms","abstract_html":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-11-11 without embargo terms","abstract_has_math":false,"creators":["Feng, Shengyu"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Tong, Hanghang"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-05","date_published":"2022-05","updated_at":"2026-07-22T22:24:55Z","subjects":["graph representation learning","contrastive learning","adversarial training","mutual information"],"languages":["en","eng"],"rights":["Copyright 2022 Shengyu Feng"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/115773","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Tong, Hanghang"]},{"key":"dc:creator","label":"Author","values":["Feng, Shengyu"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2022-05","2022-04-25"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"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":["graph representation learning","contrastive learning","adversarial training","mutual information"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2022 Shengyu Feng"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/115773"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-11-11 without embargo terms","The student, Shengyu Feng, accepted the attached license on 2022-04-24 at 01:50.","The student, Shengyu Feng, submitted this Thesis for approval on 2022-04-24 at 02:07.","This Thesis was approved for publication on 2022-04-25 at 11:44.","DSpace SAF Submission Ingestion Package generated from Vireo submission #17620 on 2022-11-11 at 17:38:02","Contrastive learning is an effective unsupervised method in graph representation learning, and the key component of contrastive learning lies in the construction of positive and negative samples. Previous methods usually utilize the proximity of nodes in the graph as the principle to decide the positive and negative samples. Recently, the data augmentation based contrastive learning method has advanced to show great power in the visual domain. This method forces the encoder to maximize the mutual information between the positive pairs generated through the data augmentation of the same instance. It achieves comparable performance to the supervised learning on various downstream tasks. Some works also extended this method from images to graphs. However, most prior works are directly adapted from the models designed for images. Unlike the data augmentation on images, the data augmentation on graphs is far less intuitive and much harder to provide high-quality contrastive samples, which are the key to the performance of contrastive learning models. Although some works also try to design an adaptive data augmentation strategy based on human knowledge, they can only take effect on some specific datasets and fail to achieve a consistent improvement. This leaves much space for improvement over the existing graph contrastive learning frameworks. In this thesis, by introducing an adversarial graph view for data augmentation, we propose a simple but effective method, Adversarial Graph Contrastive Learning (ARIEL), to extract informative contrastive samples within a reasonable constraint. We make use of the Projected Gradient Descent attack to generate a new augmentation view by adding perturbations on the original graph, which maximizes the contrastive loss against a standard augmentation view, subject to the constraints on perturbations. Due to the instability brought by the adversarial view, we also develop a technique called information regularization to penalize the high similarity granted to a less similar pair. By using the subgraph sampling technique, we successfully scale ARIEL to large graphs with affordable computational cost. ARIEL consistently outperforms the current graph contrastive learning methods in the node classification and graph classification tasks over various real-world datasets. We further demonstrate that ARIEL could behave better on the attacked graphs than previous graph contrastive learning algorithms, which indicates ARIEL is more robust to adversarial attacks."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Adversarial graph contrastive learning with information regularization"]}]}],"canonical_facts":{"dc:contributor":["Tong, Hanghang"],"dc:creator":["Feng, Shengyu"],"dc:date":["2022-05","2022-04-25"],"dc:description":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-11-11 without embargo terms","The student, Shengyu Feng, accepted the attached license on 2022-04-24 at 01:50.","The student, Shengyu Feng, submitted this Thesis for approval on 2022-04-24 at 02:07.","This Thesis was approved for publication on 2022-04-25 at 11:44.","DSpace SAF Submission Ingestion Package generated from Vireo submission #17620 on 2022-11-11 at 17:38:02","Contrastive learning is an effective unsupervised method in graph representation learning, and the key component of contrastive learning lies in the construction of positive and negative samples. Previous methods usually utilize the proximity of nodes in the graph as the principle to decide the positive and negative samples. Recently, the data augmentation based contrastive learning method has advanced to show great power in the visual domain. This method forces the encoder to maximize the mutual information between the positive pairs generated through the data augmentation of the same instance. It achieves comparable performance to the supervised learning on various downstream tasks. Some works also extended this method from images to graphs. However, most prior works are directly adapted from the models designed for images. Unlike the data augmentation on images, the data augmentation on graphs is far less intuitive and much harder to provide high-quality contrastive samples, which are the key to the performance of contrastive learning models. Although some works also try to design an adaptive data augmentation strategy based on human knowledge, they can only take effect on some specific datasets and fail to achieve a consistent improvement. This leaves much space for improvement over the existing graph contrastive learning frameworks. In this thesis, by introducing an adversarial graph view for data augmentation, we propose a simple but effective method, Adversarial Graph Contrastive Learning (ARIEL), to extract informative contrastive samples within a reasonable constraint. We make use of the Projected Gradient Descent attack to generate a new augmentation view by adding perturbations on the original graph, which maximizes the contrastive loss against a standard augmentation view, subject to the constraints on perturbations. Due to the instability brought by the adversarial view, we also develop a technique called information regularization to penalize the high similarity granted to a less similar pair. By using the subgraph sampling technique, we successfully scale ARIEL to large graphs with affordable computational cost. ARIEL consistently outperforms the current graph contrastive learning methods in the node classification and graph classification tasks over various real-world datasets. We further demonstrate that ARIEL could behave better on the attacked graphs than previous graph contrastive learning algorithms, which indicates ARIEL is more robust to adversarial attacks."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/115773"],"dc:language":["en","eng"],"dc:rights":["Copyright 2022 Shengyu Feng"],"dc:subject":["graph representation learning","contrastive learning","adversarial training","mutual information"],"dc:title":["Adversarial graph contrastive learning with information regularization"],"dc:type":["text","Thesis"],"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":"2026-07-22T22:24:55Z"}