{"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/shiftaddnet-a-hardware-inspired-deep-network","title":"ShiftAddNet: A Hardware-Inspired Deep Network","arxiv_id":"2010.12785","date":"2020-10-24","proceeding":"NeurIPS 2020 12","authors":["Haoran You","Xiaohan Chen","Yongan Zhang","Chaojian Li","Sicheng Li","Zihao Liu","Zhangyang Wang","Yingyan Lin"],"abstract":"Multiplication (e.g., convolution) is arguably a cornerstone of modern deep neural networks (DNNs). However, intensive multiplications cause expensive resource costs that challenge DNNs' deployment on resource-constrained edge devices, driving several attempts for multiplication-less deep networks. This paper presented ShiftAddNet, whose main inspiration is drawn from a common practice in energy-efficient hardware implementation, that is, multiplication can be instead performed with additions and logical bit-shifts. We leverage this idea to explicitly parameterize deep networks in this way, yielding a new type of deep network that involves only bit-shift and additive weight layers. This hardware-inspired ShiftAddNet immediately leads to both energy-efficient inference and training, without compromising the expressive capacity compared to standard DNNs. The two complementary operation types (bit-shift and add) additionally enable finer-grained control of the model's learning capacity, leading to more flexible trade-off between accuracy and (training) efficiency, as well as improved robustness to quantization and pruning. We conduct extensive experiments and ablation studies, all backed up by our FPGA-based ShiftAddNet implementation and energy measurements. Compared to existing DNNs or other multiplication-less models, ShiftAddNet aggressively reduces over 80% hardware-quantified energy cost of DNNs training and inference, while offering comparable or better accuracies. Codes and pre-trained models are available at https://github.com/RICE-EIC/ShiftAddNet.","url_abs":"https://arxiv.org/abs/2010.12785v1","url_pdf":"https://arxiv.org/pdf/2010.12785v1.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":"shiftaddnet-a-hardware-inspired-deep-network","repo_url":"https://github.com/RICE-EIC/ShiftAddNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2010.12785","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.12785"}},"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":"deterministic:regex_extraction","url":"https://github.com/RICE-EIC/ShiftAddNet","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"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":"f0c9a29156911331","entry":"accuracy","repo":"RICE-EIC/ShiftAddNet","repo_kind":"official","path":"generate_feature.py","file_url":"https://github.com/RICE-EIC/ShiftAddNet/blob/HEAD/generate_feature.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":"f0c9a29156911331"}},{"code_sha256_prefix":"1294aa155bf8944f","entry":"adder2d_function","repo":"RICE-EIC/ShiftAddNet","repo_kind":"official","path":"models/adder.py","file_url":"https://github.com/RICE-EIC/ShiftAddNet/blob/HEAD/models/adder.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":"1294aa155bf8944f"}},{"code_sha256_prefix":"82606b9cae77b5bf","entry":"load_add_state_dict","repo":"RICE-EIC/ShiftAddNet","repo_kind":"official","path":"generate_feature.py","file_url":"https://github.com/RICE-EIC/ShiftAddNet/blob/HEAD/generate_feature.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":"82606b9cae77b5bf"}},{"code_sha256_prefix":"5733b68d3e817cf1","entry":"load_shiftadd_state_dict","repo":"RICE-EIC/ShiftAddNet","repo_kind":"official","path":"generate_feature.py","file_url":"https://github.com/RICE-EIC/ShiftAddNet/blob/HEAD/generate_feature.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":"5733b68d3e817cf1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}