{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/152648"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/152648","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Balancing Memory Efficiency and Accuracy in Spectral-Based Graph Transformers","abstract":"The transformer architecture has been a significant driving force behind advancements in deep learning, yet transformer-based models for graph representation learning have not caught up to mainstream Graph Neural Network (GNN) variants. A major limitation is the large O(𝑛2) memory consumption of graph transformers, where 𝑛 is the number of nodes. Therefore, we develop a memory-efficient graph transformer for node classification, capable of handling graphs with thousands of nodes while maintaining accuracy. Specifically, we reduce the memory use in the attention mechanism and add a random-walk positional encoding to improve upon the SAN graph transformer architecture. We evaluate our model on standard node classification benchmarks: Cora, Citeseer, and Chameleon. Unlike SAN, which runs out of memory, our memory-efficient graph transformer can be run on these benchmarks. Compared with landmark GNN models GCN and GAT, our graph transformer requires 27.92% less memory while being competitive in accuracy.","abstract_html":"The transformer architecture has been a significant driving force behind advancements in deep learning, yet transformer-based models for graph representation learning have not caught up to mainstream Graph Neural Network (GNN) variants. A major limitation is the large O(𝑛2) memory consumption of graph transformers, where 𝑛 is the number of nodes. Therefore, we develop a memory-efficient graph transformer for node classification, capable of handling graphs with thousands of nodes while maintaining accuracy. Specifically, we reduce the memory use in the attention mechanism and add a random-walk positional encoding to improve upon the SAN graph transformer architecture. We evaluate our model on standard node classification benchmarks: Cora, Citeseer, and Chameleon. Unlike SAN, which runs out of memory, our memory-efficient graph transformer can be run on these benchmarks. Compared with landmark GNN models GCN and GAT, our graph transformer requires 27.92% less memory while being competitive in accuracy.","abstract_has_math":false,"creators":["Ho, Kelly"],"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":["Arvind"],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-09","date_published":"2023-09","updated_at":"2026-07-22T22:21:44Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"rights_urls":["https://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/152648","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Arvind"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Ho, Kelly"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2023-11-02T20:05:39Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2023-11-02T20:05:39Z"]},{"key":"dc:date.issued","label":"Date","values":["2023-09"]},{"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 Engineering 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 retained by author(s)"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/152648"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The transformer architecture has been a significant driving force behind advancements in deep learning, yet transformer-based models for graph representation learning have not caught up to mainstream Graph Neural Network (GNN) variants. A major limitation is the large O(𝑛2) memory consumption of graph transformers, where 𝑛 is the number of nodes. Therefore, we develop a memory-efficient graph transformer for node classification, capable of handling graphs with thousands of nodes while maintaining accuracy. Specifically, we reduce the memory use in the attention mechanism and add a random-walk positional encoding to improve upon the SAN graph transformer architecture. We evaluate our model on standard node classification benchmarks: Cora, Citeseer, and Chameleon. Unlike SAN, which runs out of memory, our memory-efficient graph transformer can be run on these benchmarks. Compared with landmark GNN models GCN and GAT, our graph transformer requires 27.92% less memory while being competitive in accuracy."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["Balancing Memory Efficiency and Accuracy in Spectral-Based Graph Transformers"]}]}],"canonical_facts":{"dc:contributor.advisor":["Arvind"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Ho, Kelly"],"dc:date.accessioned":["2023-11-02T20:05:39Z"],"dc:date.available":["2023-11-02T20:05:39Z"],"dc:date.issued":["2023-09"],"dc:description.abstract":["The transformer architecture has been a significant driving force behind advancements in deep learning, yet transformer-based models for graph representation learning have not caught up to mainstream Graph Neural Network (GNN) variants. A major limitation is the large O(𝑛2) memory consumption of graph transformers, where 𝑛 is the number of nodes. Therefore, we develop a memory-efficient graph transformer for node classification, capable of handling graphs with thousands of nodes while maintaining accuracy. Specifically, we reduce the memory use in the attention mechanism and add a random-walk positional encoding to improve upon the SAN graph transformer architecture. We evaluate our model on standard node classification benchmarks: Cora, Citeseer, and Chameleon. Unlike SAN, which runs out of memory, our memory-efficient graph transformer can be run on these benchmarks. Compared with landmark GNN models GCN and GAT, our graph transformer requires 27.92% less memory while being competitive in accuracy."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/152648"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"dc:rights.uri":["https://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Balancing Memory Efficiency and Accuracy in Spectral-Based Graph Transformers"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:21:44Z"}