{"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/low-rank-interconnected-adaptation-across","title":"Low-Rank Interconnected Adaptation across Layers","arxiv_id":"2407.09946","date":"2024-07-13","proceeding":null,"authors":["Yibo Zhong","Yao Zhou"],"abstract":"Low-rank adaptation (LoRA) is a powerful parameter-efficient fine-tuning method that utilizes low-rank projectors $A$ and $B$ to learn weight updates $\\Delta W$ for adaptation targets $W$. Previous research has shown that LoRA is essentially a gradient compressor, performing random projections on the gradient using a fixed projection matrix $A_0$. However, this setup restricts the overall weight update to be low-rank, which limits the adaptation performance. In this paper, we propose low-rank interconnected adaptation across layers (Lily). Specifically, we employ a hierarchical framework where low-dimensional projectors (LPs) retained for downward projection at a particular level, while globally-shared high-dimensional projector (HP) experts perform upward projection across all levels of layers. Lily uniquely connects each LP to all HP experts, therefore the gradient projections are no longer dominated by fixed projection matrices, but rather by selective combinations of all the projectors, thereby breaking the low-rank constraint of LoRA. Furthermore, Lily's cross-layer connections facilitate the capture of intricate information and dependencies across different layers, thereby enhancing the model's representational capabilities. Experiments across various modalities, architectures, and model sizes underscore Lily's great performance and efficiency. Code is available on github https://github.com/yibozhong/lily.","url_abs":"https://arxiv.org/abs/2407.09946v2","url_pdf":"https://arxiv.org/pdf/2407.09946v2.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":"low-rank-interconnected-adaptation-across","repo_url":"https://github.com/yibozhong/lily","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[{"method_slug":"adapter","method_name":"Adapter"},{"method_slug":"moe","method_name":"MoE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.09946","atlas_url":"https://app.syntology.ai/?focus=2407.09946","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.09946"}},"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/yibozhong/lily","reach":{"status":"ok"}}],"summary":{"ran":6,"ran_draft_wrong":3,"unverified":4},"by_repo_kind":{"official":{"samples":13,"ran":9,"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":13,"samples":[{"code_sha256_prefix":"03e1c6795642a8db","entry":"determine_scheduler_type","repo":"yibozhong/lily","repo_kind":"official","path":"subject-driven-generation/train_lily.py","file_url":"https://github.com/yibozhong/lily/blob/HEAD/subject-driven-generation/train_lily.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":"03e1c6795642a8db"}},{"code_sha256_prefix":"f7d42195b9365611","entry":"feed_forward_chunk_lily","repo":"yibozhong/lily","repo_kind":"official","path":"natural-language-understanding/lily.py","file_url":"https://github.com/yibozhong/lily/blob/HEAD/natural-language-understanding/lily.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":"f7d42195b9365611"}},{"code_sha256_prefix":"6e1edecf32659658","entry":"forward_attn_lily","repo":"yibozhong/lily","repo_kind":"official","path":"natural-language-understanding/lily.py","file_url":"https://github.com/yibozhong/lily/blob/HEAD/natural-language-understanding/lily.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":"6e1edecf32659658"}},{"code_sha256_prefix":"38a21650f4660a75","entry":"forward_attn_lily_kv","repo":"yibozhong/lily","repo_kind":"official","path":"visual-adaptation-benchmark/vit/lily.py","file_url":"https://github.com/yibozhong/lily/blob/HEAD/visual-adaptation-benchmark/vit/lily.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":"38a21650f4660a75"}},{"code_sha256_prefix":"7054afa64407297c","entry":"forward_mlp_lily","repo":"yibozhong/lily","repo_kind":"official","path":"visual-adaptation-benchmark/vit/lily.py","file_url":"https://github.com/yibozhong/lily/blob/HEAD/visual-adaptation-benchmark/vit/lily.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":"7054afa64407297c"}},{"code_sha256_prefix":"56e674752db00649","entry":"generate_prompt","repo":"yibozhong/lily","repo_kind":"official","path":"commonsense-reasoning/finetune_llama.py","file_url":"https://github.com/yibozhong/lily/blob/HEAD/commonsense-reasoning/finetune_llama.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":"56e674752db00649"}},{"code_sha256_prefix":"1c6b8be890b6118a","entry":"generate_prompt","repo":"yibozhong/lily","repo_kind":"official","path":"commonsense-reasoning/evaluate_llama.py","file_url":"https://github.com/yibozhong/lily/blob/HEAD/commonsense-reasoning/evaluate_llama.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1c6b8be890b6118a"}},{"code_sha256_prefix":"56a9466ff35b35bb","entry":"load_data","repo":"yibozhong/lily","repo_kind":"official","path":"commonsense-reasoning/evaluate_llama.py","file_url":"https://github.com/yibozhong/lily/blob/HEAD/commonsense-reasoning/evaluate_llama.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":"56a9466ff35b35bb"}},{"code_sha256_prefix":"a9b94b97e3bc2c8c","entry":"prepare_model_for_int8_training","repo":"yibozhong/lily","repo_kind":"official","path":"commonsense-reasoning/finetune_mamba.py","file_url":"https://github.com/yibozhong/lily/blob/HEAD/commonsense-reasoning/finetune_mamba.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":"a9b94b97e3bc2c8c"}},{"code_sha256_prefix":"86965b6bae051ea4","entry":"import_model_class_from_model_name_or_path","repo":"yibozhong/lily","repo_kind":"official","path":"subject-driven-generation/train_lily.py","file_url":"https://github.com/yibozhong/lily/blob/HEAD/subject-driven-generation/train_lily.py","link_basis":"harvester_set","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":"86965b6bae051ea4"}},{"code_sha256_prefix":"f7160c65cac52b2f","entry":"load_lily","repo":"yibozhong/lily","repo_kind":"official","path":"subject-driven-generation/infer_lily.py","file_url":"https://github.com/yibozhong/lily/blob/HEAD/subject-driven-generation/infer_lily.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":"f7160c65cac52b2f"}},{"code_sha256_prefix":"8e69377cf4c6f413","entry":"main","repo":"yibozhong/lily","repo_kind":"official","path":"commonsense-reasoning/evaluate_llama.py","file_url":"https://github.com/yibozhong/lily/blob/HEAD/commonsense-reasoning/evaluate_llama.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":"8e69377cf4c6f413"}},{"code_sha256_prefix":"b0b4ac66dc9563ab","entry":"main","repo":"yibozhong/lily","repo_kind":"official","path":"commonsense-reasoning/evaluate_mamba.py","file_url":"https://github.com/yibozhong/lily/blob/HEAD/commonsense-reasoning/evaluate_mamba.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":"b0b4ac66dc9563ab"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}