{"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/flora-fine-grained-low-rank-architecture","title":"FLORA: Fine-grained Low-Rank Architecture Search for Vision Transformer","arxiv_id":"2311.03912","date":"2023-11-07","proceeding":null,"authors":["Chi-Chih Chang","Yuan-Yao Sung","Shixing Yu","Ning-Chi Huang","Diana Marculescu","Kai-Chiang Wu"],"abstract":"Vision Transformers (ViT) have recently demonstrated success across a myriad of computer vision tasks. However, their elevated computational demands pose significant challenges for real-world deployment. While low-rank approximation stands out as a renowned method to reduce computational loads, efficiently automating the target rank selection in ViT remains a challenge. Drawing from the notable similarity and alignment between the processes of rank selection and One-Shot NAS, we introduce FLORA, an end-to-end automatic framework based on NAS. To overcome the design challenge of supernet posed by vast search space, FLORA employs a low-rank aware candidate filtering strategy. This method adeptly identifies and eliminates underperforming candidates, effectively alleviating potential undertraining and interference among subnetworks. To further enhance the quality of low-rank supernets, we design a low-rank specific training paradigm. First, we propose weight inheritance to construct supernet and enable gradient sharing among low-rank modules. Secondly, we adopt low-rank aware sampling to strategically allocate training resources, taking into account inherited information from pre-trained models. Empirical results underscore FLORA's efficacy. With our method, a more fine-grained rank configuration can be generated automatically and yield up to 33% extra FLOPs reduction compared to a simple uniform configuration. More specific, FLORA-DeiT-B/FLORA-Swin-B can save up to 55%/42% FLOPs almost without performance degradtion. Importantly, FLORA boasts both versatility and orthogonality, offering an extra 21%-26% FLOPs reduction when integrated with leading compression techniques or compact hybrid structures. Our code is publicly available at https://github.com/shadowpa0327/FLORA.","url_abs":"https://arxiv.org/abs/2311.03912v1","url_pdf":"https://arxiv.org/pdf/2311.03912v1.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":"flora-fine-grained-low-rank-architecture","repo_url":"https://github.com/shadowpa0327/flora","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"aware","method_name":"AWARE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2311.03912","atlas_url":"https://app.syntology.ai/?focus=2311.03912","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.03912"}},"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/shadowpa0327/flora","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"unverified":4},"by_repo_kind":{"official":{"samples":7,"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":0,"samples":[{"code_sha256_prefix":"8c9ea560af0ebcee","entry":"get_config_with_highest_accuracy_from_ea_result","repo":"shadowpa0327/flora","repo_kind":"official","path":"get_subnet_cfg_from_ea.py","file_url":"https://github.com/shadowpa0327/flora/blob/HEAD/get_subnet_cfg_from_ea.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":"8c9ea560af0ebcee"}},{"code_sha256_prefix":"18f248d183adcbf3","entry":"get_model_type_name","repo":"shadowpa0327/flora","repo_kind":"official","path":"get_subnet_cfg_from_ea.py","file_url":"https://github.com/shadowpa0327/flora/blob/HEAD/get_subnet_cfg_from_ea.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":"18f248d183adcbf3"}},{"code_sha256_prefix":"110668d45ac91016","entry":"get_subnet_config","repo":"shadowpa0327/flora","repo_kind":"official","path":"get_subnet_cfg_from_ea.py","file_url":"https://github.com/shadowpa0327/flora/blob/HEAD/get_subnet_cfg_from_ea.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":"110668d45ac91016"}},{"code_sha256_prefix":"111ef03a046897da","entry":"build_model","repo":"shadowpa0327/flora","repo_kind":"official","path":"models/build.py","file_url":"https://github.com/shadowpa0327/flora/blob/HEAD/models/build.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"111ef03a046897da"}},{"code_sha256_prefix":"07e8b4b487c0abb6","entry":"build_scheduler","repo":"shadowpa0327/flora","repo_kind":"official","path":"lr_scheduler.py","file_url":"https://github.com/shadowpa0327/flora/blob/HEAD/lr_scheduler.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"07e8b4b487c0abb6"}},{"code_sha256_prefix":"80450600f7f09b0a","entry":"create_logger","repo":"shadowpa0327/flora","repo_kind":"official","path":"logger.py","file_url":"https://github.com/shadowpa0327/flora/blob/HEAD/logger.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"80450600f7f09b0a"}},{"code_sha256_prefix":"f7150553127fec49","entry":"get_config","repo":"shadowpa0327/flora","repo_kind":"official","path":"config.py","file_url":"https://github.com/shadowpa0327/flora/blob/HEAD/config.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f7150553127fec49"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}