{"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/advancing-parameter-efficiency-in-fine-tuning","title":"Advancing Parameter Efficiency in Fine-tuning via Representation Editing","arxiv_id":"2402.15179","date":"2024-02-23","proceeding":null,"authors":["Muling Wu","Wenhao Liu","Xiaohua Wang","Tianlong Li","Changze Lv","Zixuan Ling","Jianhao Zhu","Cenyuan Zhang","Xiaoqing Zheng","Xuanjing Huang"],"abstract":"Parameter Efficient Fine-Tuning (PEFT) techniques have drawn significant attention due to their ability to yield competitive results while updating only a small portion of the adjustable parameters. However, existing PEFT methods pose challenges in hyperparameter selection, such as choosing the rank for LoRA or Adapter, or specifying the length of soft prompts. To address these challenges, we propose a novel fine-tuning approach for neural models, named Representation EDiting (RED), which modifies the representations generated at some layers through the application of scaling and biasing operations. While existing PEFT methods still demonstrate over-parameterization that could potentially undermine the generalization ability acquired from pre-training, RED can substantially reduce the number of trainable parameters by a factor of 25, 700 compared to full parameter fine-tuning and by a factor of 32 relative to LoRA. Remarkably, RED achieves results comparable or superior to both full parameter fine-tuning and other PEFT methods. Extensive experiments across various model architectures and scales, including RoBERTa, GPT-2, T5, and LLaMA-2, have demonstrated the effectiveness and efficiency of RED1, thereby positioning it as a promising PEFT strategy for large-scale neural models.","url_abs":"https://arxiv.org/abs/2402.15179v3","url_pdf":"https://arxiv.org/pdf/2402.15179v3.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":"advancing-parameter-efficiency-in-fine-tuning","repo_url":"https://github.com/mlwu22/red","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"advancing-parameter-efficiency-in-fine-tuning","repo_url":"https://github.com/explainableml/delora","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[{"method_slug":"adafactor","method_name":"Adafactor"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"adapter","method_name":"Adapter"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"discriminative-fine-tuning","method_name":"Discriminative Fine-Tuning"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-2","method_name":"GPT-2"},{"method_slug":"glu","method_name":"Gated Linear Unit"},{"method_slug":"inverse-square-root-schedule","method_name":"Inverse Square Root Schedule"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"roberta","method_name":"RoBERTa"},{"method_slug":"sentencepiece","method_name":"SentencePiece"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"t5","method_name":"T5"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.15179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15179"}},"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/mlwu22/red","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/explainableml/delora","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/mlwu22/RED","reach":{"status":"ok"}}],"summary":{"ran":2},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"7a6bbc394c0f5543","entry":"ActivationLayer","repo":"mlwu22/RED","repo_kind":"official","path":"model.py","file_url":"https://github.com/mlwu22/RED/blob/HEAD/model.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":"7a6bbc394c0f5543"}},{"code_sha256_prefix":"2c84c67f9b5e3fc9","entry":"DeloraLayer","repo":"explainableml/delora","repo_kind":"listed","path":"peft/src/peft/tuners/delora.py","file_url":"https://github.com/explainableml/delora/blob/HEAD/peft/src/peft/tuners/delora.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":"2c84c67f9b5e3fc9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}