{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/145052"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/145052","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Revisiting Contrastive Learning through the Lens of Neighborhood Component Analysis","abstract":"As a seminal tool in self-supervised representation learning, contrastive learning has gained unprecedented attention in recent years. In essence, contrastive learning aims to leverage pairs of positive and negative samples for representation learning, which relates to exploiting neighborhood information in a feature space. However, as a self-supervised learning method, the current contrastive learning method have encoded priors on the downstream classification tasks implicitly. In this thesis, by investigating the connection between contrastive learning and neighborhood component analysis (NCA), we provide a novel stochastic nearest neighbor viewpoint of contrastive learning and subsequently propose a series of contrastive losses that outperform the existing ones. Under our proposed framework, we show a new methodology to design integrated contrastive losses that could simultaneously achieve good accuracy and robustness on downstream tasks.","abstract_html":"As a seminal tool in self-supervised representation learning, contrastive learning has gained unprecedented attention in recent years. In essence, contrastive learning aims to leverage pairs of positive and negative samples for representation learning, which relates to exploiting neighborhood information in a feature space. However, as a self-supervised learning method, the current contrastive learning method have encoded priors on the downstream classification tasks implicitly. In this thesis, by investigating the connection between contrastive learning and neighborhood component analysis (NCA), we provide a novel stochastic nearest neighbor viewpoint of contrastive learning and subsequently propose a series of contrastive losses that outperform the existing ones. Under our proposed framework, we show a new methodology to design integrated contrastive losses that could simultaneously achieve good accuracy and robustness on downstream tasks.","abstract_has_math":false,"creators":["Ko, Ching-Yun"],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Daniel, Luca"],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-05","date_published":"2022-05","updated_at":"2026-07-22T22:22:24Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"rights_urls":["http://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/145052","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Daniel, Luca"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Ko, Ching-Yun"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2022-08-29T16:29:44Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2022-08-29T16:29:44Z"]},{"key":"dc:date.issued","label":"Date","values":["2022-05"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master","Master of Science in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright MIT"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/145052"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["As a seminal tool in self-supervised representation learning, contrastive learning has gained unprecedented attention in recent years. In essence, contrastive learning aims to leverage pairs of positive and negative samples for representation learning, which relates to exploiting neighborhood information in a feature space. However, as a self-supervised learning method, the current contrastive learning method have encoded priors on the downstream classification tasks implicitly. In this thesis, by investigating the connection between contrastive learning and neighborhood component analysis (NCA), we provide a novel stochastic nearest neighbor viewpoint of contrastive learning and subsequently propose a series of contrastive losses that outperform the existing ones. Under our proposed framework, we show a new methodology to design integrated contrastive losses that could simultaneously achieve good accuracy and robustness on downstream tasks."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["S.M."]},{"key":"dc:title","label":"Title","values":["Revisiting Contrastive Learning through the Lens of Neighborhood Component Analysis"]}]}],"canonical_facts":{"dc:contributor.advisor":["Daniel, Luca"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Ko, Ching-Yun"],"dc:date.accessioned":["2022-08-29T16:29:44Z"],"dc:date.available":["2022-08-29T16:29:44Z"],"dc:date.issued":["2022-05"],"dc:description.abstract":["As a seminal tool in self-supervised representation learning, contrastive learning has gained unprecedented attention in recent years. In essence, contrastive learning aims to leverage pairs of positive and negative samples for representation learning, which relates to exploiting neighborhood information in a feature space. However, as a self-supervised learning method, the current contrastive learning method have encoded priors on the downstream classification tasks implicitly. In this thesis, by investigating the connection between contrastive learning and neighborhood component analysis (NCA), we provide a novel stochastic nearest neighbor viewpoint of contrastive learning and subsequently propose a series of contrastive losses that outperform the existing ones. Under our proposed framework, we show a new methodology to design integrated contrastive losses that could simultaneously achieve good accuracy and robustness on downstream tasks."],"dc:description.degree":["S.M."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/145052"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright MIT"],"dc:rights.uri":["http://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Revisiting Contrastive Learning through the Lens of Neighborhood Component Analysis"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Science in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:22:24Z"}