{"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/shiftaddnas-hardware-inspired-search-for-more-1","title":"ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks","arxiv_id":"2205.08119","date":"2022-05-17","proceeding":null,"authors":["Haoran You","Baopu Li","Huihong Shi","Yonggan Fu","Yingyan Lin"],"abstract":"Neural networks (NNs) with intensive multiplications (e.g., convolutions and transformers) are capable yet power hungry, impeding their more extensive deployment into resource-constrained devices. As such, multiplication-free networks, which follow a common practice in energy-efficient hardware implementation to parameterize NNs with more efficient operators (e.g., bitwise shifts and additions), have gained growing attention. However, multiplication-free networks usually under-perform their vanilla counterparts in terms of the achieved accuracy. To this end, this work advocates hybrid NNs that consist of both powerful yet costly multiplications and efficient yet less powerful operators for marrying the best of both worlds, and proposes ShiftAddNAS, which can automatically search for more accurate and more efficient NNs. Our ShiftAddNAS highlights two enablers. Specifically, it integrates (1) the first hybrid search space that incorporates both multiplication-based and multiplication-free operators for facilitating the development of both accurate and efficient hybrid NNs; and (2) a novel weight sharing strategy that enables effective weight sharing among different operators that follow heterogeneous distributions (e.g., Gaussian for convolutions vs. Laplacian for add operators) and simultaneously leads to a largely reduced supernet size and much better searched networks. Extensive experiments and ablation studies on various models, datasets, and tasks consistently validate the efficacy of ShiftAddNAS, e.g., achieving up to a +7.7% higher accuracy or a +4.9 better BLEU score compared to state-of-the-art NN, while leading to up to 93% or 69% energy and latency savings, respectively. Codes and pretrained models are available at https://github.com/RICE-EIC/ShiftAddNAS.","url_abs":"https://arxiv.org/abs/2205.08119v3","url_pdf":"https://arxiv.org/pdf/2205.08119v3.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":"shiftaddnas-hardware-inspired-search-for-more-1","repo_url":"https://github.com/rice-eic/shiftaddnas","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2205.08119","atlas_url":"https://app.syntology.ai/?focus=2205.08119","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.08119"}},"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/rice-eic/shiftaddnas","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"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":"60f59600934df5ba","entry":"lightweight","repo":"rice-eic/shiftaddnas","repo_kind":"official","path":"NLP/en-de/sim/ShiftAddNAS.py","file_url":"https://github.com/rice-eic/shiftaddnas/blob/HEAD/NLP/en-de/sim/ShiftAddNAS.py","link_basis":"harvester_set","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":"60f59600934df5ba"}},{"code_sha256_prefix":"feb0251826142c84","entry":"mlp","repo":"rice-eic/shiftaddnas","repo_kind":"official","path":"NLP/en-de/sim/ShiftAddNAS.py","file_url":"https://github.com/rice-eic/shiftaddnas/blob/HEAD/NLP/en-de/sim/ShiftAddNAS.py","link_basis":"harvester_set","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":"feb0251826142c84"}},{"code_sha256_prefix":"b3a2d2310366d914","entry":"mlp","repo":"rice-eic/shiftaddnas","repo_kind":"official","path":"NLP/en-de/sim/ShiftAddNAS_all_shift.py","file_url":"https://github.com/rice-eic/shiftaddnas/blob/HEAD/NLP/en-de/sim/ShiftAddNAS_all_shift.py","link_basis":"harvester_set","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":"b3a2d2310366d914"}},{"code_sha256_prefix":"3f1e1ab9f4c7f030","entry":"self_attention","repo":"rice-eic/shiftaddnas","repo_kind":"official","path":"NLP/en-de/sim/ShiftAddNAS.py","file_url":"https://github.com/rice-eic/shiftaddnas/blob/HEAD/NLP/en-de/sim/ShiftAddNAS.py","link_basis":"harvester_set","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":"3f1e1ab9f4c7f030"}},{"code_sha256_prefix":"3553eb2f49982ebd","entry":"shift_mlp","repo":"rice-eic/shiftaddnas","repo_kind":"official","path":"NLP/en-de/sim/ShiftAddNAS_shift_ffn_v1.py","file_url":"https://github.com/rice-eic/shiftaddnas/blob/HEAD/NLP/en-de/sim/ShiftAddNAS_shift_ffn_v1.py","link_basis":"harvester_set","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":"3553eb2f49982ebd"}},{"code_sha256_prefix":"65361b392e8996d3","entry":"get_acc","repo":"rice-eic/shiftaddnas","repo_kind":"official","path":"CV/plot_supernet.py","file_url":"https://github.com/rice-eic/shiftaddnas/blob/HEAD/CV/plot_supernet.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":"65361b392e8996d3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}