{"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/improving-memory-efficiency-for-training-kans","title":"Improving Memory Efficiency for Training KANs via Meta Learning","arxiv_id":"2506.07549","date":"2025-06-09","proceeding":null,"authors":["Zhangchi Zhao","Jun Shu","Deyu Meng","Zongben Xu"],"abstract":"Inspired by the Kolmogorov-Arnold representation theorem, KANs offer a novel framework for function approximation by replacing traditional neural network weights with learnable univariate functions. This design demonstrates significant potential as an efficient and interpretable alternative to traditional MLPs. However, KANs are characterized by a substantially larger number of trainable parameters, leading to challenges in memory efficiency and higher training costs compared to MLPs. To address this limitation, we propose to generate weights for KANs via a smaller meta-learner, called MetaKANs. By training KANs and MetaKANs in an end-to-end differentiable manner, MetaKANs achieve comparable or even superior performance while significantly reducing the number of trainable parameters and maintaining promising interpretability. Extensive experiments on diverse benchmark tasks, including symbolic regression, partial differential equation solving, and image classification, demonstrate the effectiveness of MetaKANs in improving parameter efficiency and memory usage. The proposed method provides an alternative technique for training KANs, that allows for greater scalability and extensibility, and narrows the training cost gap with MLPs stated in the original paper of KANs. Our code is available at https://github.com/Murphyzc/MetaKAN.","url_abs":"https://arxiv.org/abs/2506.07549v1","url_pdf":"https://arxiv.org/pdf/2506.07549v1.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":"improving-memory-efficiency-for-training-kans","repo_url":"https://github.com/murphyzc/metakan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"symbolic-regression","task_name":"Symbolic Regression"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2506.07549","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.07549"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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":"deterministic:regex_extraction","url":"https://github.com/Murphyzc/MetaKAN","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/murphyzc/metakan","reach":{"status":"ok"}}],"summary":{"ran":2,"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":9,"ran":3,"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":9,"samples":[{"code_sha256_prefix":"f834237a690b8080","entry":"KANLinear","repo":"murphyzc/metakan","repo_kind":"official","path":"base_model/metakan.py","file_url":"https://github.com/murphyzc/metakan/blob/HEAD/base_model/metakan.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f834237a690b8080"}},{"code_sha256_prefix":"4d957ea70c66d99b","entry":"MetaKAN","repo":"murphyzc/metakan","repo_kind":"official","path":"base_model/metakan.py","file_url":"https://github.com/murphyzc/metakan/blob/HEAD/base_model/metakan.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4d957ea70c66d99b"}},{"code_sha256_prefix":"865a460121322edb","entry":"linear_layer","repo":"murphyzc/metakan","repo_kind":"official","path":"base_model/metakan.py","file_url":"https://github.com/murphyzc/metakan/blob/HEAD/base_model/metakan.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"865a460121322edb"}},{"code_sha256_prefix":"8a688f23d22db1ae","entry":"test","repo":"murphyzc/metakan","repo_kind":"official","path":"function_fitting/train_hyper.py","file_url":"https://github.com/murphyzc/metakan/blob/HEAD/function_fitting/train_hyper.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8a688f23d22db1ae"}},{"code_sha256_prefix":"8eaee068bab1dbe7","entry":"test","repo":"murphyzc/metakan","repo_kind":"official","path":"image_classification/train_meta.py","file_url":"https://github.com/murphyzc/metakan/blob/HEAD/image_classification/train_meta.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8eaee068bab1dbe7"}},{"code_sha256_prefix":"f5071e69b20f7f81","entry":"train","repo":"murphyzc/metakan","repo_kind":"official","path":"image_classification/train_meta.py","file_url":"https://github.com/murphyzc/metakan/blob/HEAD/image_classification/train_meta.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f5071e69b20f7f81"}},{"code_sha256_prefix":"9ccc07a301388187","entry":"train_double","repo":"murphyzc/metakan","repo_kind":"official","path":"function_fitting/train_hyper.py","file_url":"https://github.com/murphyzc/metakan/blob/HEAD/function_fitting/train_hyper.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9ccc07a301388187"}},{"code_sha256_prefix":"ca4749e30c04cc81","entry":"train_double","repo":"murphyzc/metakan","repo_kind":"official","path":"image_classification/train_meta.py","file_url":"https://github.com/murphyzc/metakan/blob/HEAD/image_classification/train_meta.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ca4749e30c04cc81"}},{"code_sha256_prefix":"e36f4b3b995f032f","entry":"train_single","repo":"murphyzc/metakan","repo_kind":"official","path":"function_fitting/train_hyper.py","file_url":"https://github.com/murphyzc/metakan/blob/HEAD/function_fitting/train_hyper.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e36f4b3b995f032f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}