{"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/discovering-long-term-effects-on-parameter","title":"SAN: Hypothesizing Long-Term Synaptic Development and Neural Engram Mechanism in Scalable Model's Parameter-Efficient Fine-Tuning","arxiv_id":"2409.06706","date":"2024-08-24","proceeding":null,"authors":["Gaole Dai","Chun-Kai Fan","Yiming Tang","Zhi Zhang","Yuan Zhang","Yulu Gan","Qizhe Zhang","Cheng-Ching Tseng","Shanghang Zhang","Tiejun Huang"],"abstract":"Advances in Parameter-Efficient Fine-Tuning (PEFT) bridged the performance gap with Full Fine-Tuning (FFT) through sophisticated analysis of pre-trained parameter spaces. Starting from drawing insights from Neural Engrams (NE) in Biological Neural Networks (BNNs), we establish a connection between the low-rank property observed during PEFT's parameter space shifting and neurobiological mechanisms. This observation leads to our proposed method, Synapse and Neuron (SAN), which decomposes and propagates scaling components from anterior feature adjusting vectors towards posterior weight matrices. Our approach is theoretically grounded in Long-Term Potentiation/Depression (LTP/D) phenomena, which govern synapse development through neurotransmitter release modulation. Extensive experiments demonstrate its effectiveness: on \\textbf{vision tasks} across VTAB, FGVC, and GIC (25 datasets) using ViT, SwinT and ConvNeXt, SAN outperforms FFT up to 8.7% and LoRA by 3.2%; on language tasks using Commonsense Reasoning (8 datasets) with LLaMA models (all generations), surpassing ChatGPT up to 8.5% and LoRA by 4.7%; on visual-language tasks using Mixed Visual Instruction (7 datasets) with LLaVA models, it exceeds FFT up to 2.4% and LoRA by 1.9%. Our code and W&B log will be released.","url_abs":"https://arxiv.org/abs/2409.06706v3","url_pdf":"https://arxiv.org/pdf/2409.06706v3.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":"discovering-long-term-effects-on-parameter","repo_url":"https://github.com/daviddaiiiii/san-peft","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"visual-prompt-tuning","task_name":"Visual Prompt Tuning"},{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[{"method_slug":"convnext","method_name":"ConvNeXt"},{"method_slug":"gic","method_name":"GIC"},{"method_slug":"llama","method_name":"LLaMA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.06706","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.06706"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/daviddaiiiii/san-peft","reach":{"status":"ok"}}],"summary":{"ran":6,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":10,"ran":7,"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":10,"samples":[{"code_sha256_prefix":"84b4f842f04e1d85","entry":"create_loss_fn","repo":"daviddaiiiii/san-peft","repo_kind":"official","path":"train_code/SAN_base.py","file_url":"https://github.com/daviddaiiiii/san-peft/blob/HEAD/train_code/SAN_base.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":"84b4f842f04e1d85"}},{"code_sha256_prefix":"88f4962784e09b88","entry":"param_groups_weight_decay","repo":"daviddaiiiii/san-peft","repo_kind":"official","path":"utils/optim_factory.py","file_url":"https://github.com/daviddaiiiii/san-peft/blob/HEAD/utils/optim_factory.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"88f4962784e09b88"}},{"code_sha256_prefix":"59db0073c086bf60","entry":"pil_loader","repo":"daviddaiiiii/san-peft","repo_kind":"official","path":"utils/io_utils.py","file_url":"https://github.com/daviddaiiiii/san-peft/blob/HEAD/utils/io_utils.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":"59db0073c086bf60"}},{"code_sha256_prefix":"6957ddf9520c3d71","entry":"resize_pos_embed","repo":"daviddaiiiii/san-peft","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/daviddaiiiii/san-peft/blob/HEAD/utils/utils.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":"6957ddf9520c3d71"}},{"code_sha256_prefix":"0eae5b409f8d3a5b","entry":"resize_pos_embed_cait","repo":"daviddaiiiii/san-peft","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/daviddaiiiii/san-peft/blob/HEAD/utils/utils.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":"0eae5b409f8d3a5b"}},{"code_sha256_prefix":"f553c9b260a0e6e3","entry":"resize_pos_embed_nocls","repo":"daviddaiiiii/san-peft","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/daviddaiiiii/san-peft/blob/HEAD/utils/utils.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":"f553c9b260a0e6e3"}},{"code_sha256_prefix":"7ba3eaccb626f19f","entry":"train","repo":"daviddaiiiii/san-peft","repo_kind":"official","path":"train_code/SAN_base.py","file_url":"https://github.com/daviddaiiiii/san-peft/blob/HEAD/train_code/SAN_base.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":"7ba3eaccb626f19f"}},{"code_sha256_prefix":"efeb37d90ba28266","entry":"group_parameters","repo":"daviddaiiiii/san-peft","repo_kind":"official","path":"utils/optim_factory.py","file_url":"https://github.com/daviddaiiiii/san-peft/blob/HEAD/utils/optim_factory.py","link_basis":"plan_row","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":"efeb37d90ba28266"}},{"code_sha256_prefix":"0332519996466b5a","entry":"group_with_matcher","repo":"daviddaiiiii/san-peft","repo_kind":"official","path":"utils/optim_factory.py","file_url":"https://github.com/daviddaiiiii/san-peft/blob/HEAD/utils/optim_factory.py","link_basis":"plan_row","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":"0332519996466b5a"}},{"code_sha256_prefix":"02603976c91a1244","entry":"read_json","repo":"daviddaiiiii/san-peft","repo_kind":"official","path":"utils/io_utils.py","file_url":"https://github.com/daviddaiiiii/san-peft/blob/HEAD/utils/io_utils.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":"02603976c91a1244"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}