{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/improved-operator-learning-by-orthogonal","title":"Improved Operator Learning by Orthogonal Attention","arxiv_id":"2310.12487","date":"2023-10-19","proceeding":null,"authors":["Zipeng Xiao","Zhongkai Hao","Bokai Lin","Zhijie Deng","Hang Su"],"abstract":"Neural operators, as an efficient surrogate model for learning the solutions of PDEs, have received extensive attention in the field of scientific machine learning. Among them, attention-based neural operators have become one of the mainstreams in related research. However, existing approaches overfit the limited training data due to the considerable number of parameters in the attention mechanism. To address this, we develop an orthogonal attention based on the eigendecomposition of the kernel integral operator and the neural approximation of eigenfunctions. The orthogonalization naturally poses a proper regularization effect on the resulting neural operator, which aids in resisting overfitting and boosting generalization. Experiments on six standard neural operator benchmark datasets comprising both regular and irregular geometries show that our method can outperform competing baselines with decent margins.","url_abs":"https://arxiv.org/abs/2310.12487v4","url_pdf":"https://arxiv.org/pdf/2310.12487v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"improved-operator-learning-by-orthogonal","repo_url":"https://github.com/zhijie-group/orthogonal-neural-operator","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"operator-learning","task_name":"Operator learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.12487","atlas_url":"https://app.syntology.ai/?focus=2310.12487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12487"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhijie-group/orthogonal-neural-operator","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":8},"by_repo_kind":{"official":{"samples":8,"ran":8,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"6f4322bdb0cd6491","entry":"apply_2d_rotary_pos_emb","repo":"zhijie-group/orthogonal-neural-operator","repo_kind":"official","path":"ONOmodel2.py","file_url":"https://github.com/zhijie-group/orthogonal-neural-operator/blob/HEAD/ONOmodel2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6f4322bdb0cd6491"}},{"code_sha256_prefix":"b9007c9564c0612a","entry":"apply_rotary_pos_emb","repo":"zhijie-group/orthogonal-neural-operator","repo_kind":"official","path":"ONOmodel2.py","file_url":"https://github.com/zhijie-group/orthogonal-neural-operator/blob/HEAD/ONOmodel2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b9007c9564c0612a"}},{"code_sha256_prefix":"fbbefdd8c6f1550c","entry":"central_diff","repo":"zhijie-group/orthogonal-neural-operator","repo_kind":"official","path":"Darcy_example.py","file_url":"https://github.com/zhijie-group/orthogonal-neural-operator/blob/HEAD/Darcy_example.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fbbefdd8c6f1550c"}},{"code_sha256_prefix":"44cb0b9d7d877495","entry":"central_diff","repo":"zhijie-group/orthogonal-neural-operator","repo_kind":"official","path":"time_gen.py","file_url":"https://github.com/zhijie-group/orthogonal-neural-operator/blob/HEAD/time_gen.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"44cb0b9d7d877495"}},{"code_sha256_prefix":"54097d41b039f37b","entry":"count_parameters","repo":"zhijie-group/orthogonal-neural-operator","repo_kind":"official","path":"Darcy_example.py","file_url":"https://github.com/zhijie-group/orthogonal-neural-operator/blob/HEAD/Darcy_example.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"54097d41b039f37b"}},{"code_sha256_prefix":"7a755f3c02e8f45f","entry":"random_collate_fn","repo":"zhijie-group/orthogonal-neural-operator","repo_kind":"official","path":"NS_example2.py","file_url":"https://github.com/zhijie-group/orthogonal-neural-operator/blob/HEAD/NS_example2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7a755f3c02e8f45f"}},{"code_sha256_prefix":"532198a3d341e4b3","entry":"random_collate_fn","repo":"zhijie-group/orthogonal-neural-operator","repo_kind":"official","path":"pla_example.py","file_url":"https://github.com/zhijie-group/orthogonal-neural-operator/blob/HEAD/pla_example.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"532198a3d341e4b3"}},{"code_sha256_prefix":"8549b7478752bf18","entry":"rotate_half","repo":"zhijie-group/orthogonal-neural-operator","repo_kind":"official","path":"ONOmodel2.py","file_url":"https://github.com/zhijie-group/orthogonal-neural-operator/blob/HEAD/ONOmodel2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8549b7478752bf18"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}