{"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/sparse-weight-activation-training-1","title":"Sparse Weight Activation Training","arxiv_id":"2001.01969","date":"2020-01-07","proceeding":"NeurIPS 2020 12","authors":["Md Aamir Raihan","Tor M. Aamodt"],"abstract":"Neural network training is computationally and memory intensive. Sparse training can reduce the burden on emerging hardware platforms designed to accelerate sparse computations, but it can affect network convergence. In this work, we propose a novel CNN training algorithm Sparse Weight Activation Training (SWAT). SWAT is more computation and memory-efficient than conventional training. SWAT modifies back-propagation based on the empirical insight that convergence during training tends to be robust to the elimination of (i) small magnitude weights during the forward pass and (ii) both small magnitude weights and activations during the backward pass. We evaluate SWAT on recent CNN architectures such as ResNet, VGG, DenseNet and WideResNet using CIFAR-10, CIFAR-100 and ImageNet datasets. For ResNet-50 on ImageNet SWAT reduces total floating-point operations (FLOPS) during training by 80% resulting in a 3.3$\\times$ training speedup when run on a simulated sparse learning accelerator representative of emerging platforms while incurring only 1.63% reduction in validation accuracy. Moreover, SWAT reduces memory footprint during the backward pass by 23% to 50% for activations and 50% to 90% for weights.","url_abs":"https://arxiv.org/abs/2001.01969v3","url_pdf":"https://arxiv.org/pdf/2001.01969v3.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":"sparse-weight-activation-training-1","repo_url":"https://github.com/AamirRaihan/SWAT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"network-pruning","task_name":"Network Pruning"},{"task_slug":"sparse-learning","task_name":"Sparse Learning"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-block","method_name":"Dense Block"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"wide-residual-block","method_name":"Wide Residual Block"},{"method_slug":"wideresnet","method_name":"WideResNet"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2001.01969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.01969"}},"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/AamirRaihan/SWAT","reach":null}],"summary":{"ran":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"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":4,"samples":[{"code_sha256_prefix":"e9a291b3ea1a313b","entry":"CustomBatchNorm","repo":"AamirRaihan/SWAT","repo_kind":"official","path":"SWAT-code/cifar10-100-code/dynamic_sparsity.py","file_url":"https://github.com/AamirRaihan/SWAT/blob/HEAD/SWAT-code/cifar10-100-code/dynamic_sparsity.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e9a291b3ea1a313b"}},{"code_sha256_prefix":"8591416efce8c5b4","entry":"CustomBatchNorm2d","repo":"AamirRaihan/SWAT","repo_kind":"official","path":"SWAT-code/cifar10-100-code/dynamic_sparsity.py","file_url":"https://github.com/AamirRaihan/SWAT/blob/HEAD/SWAT-code/cifar10-100-code/dynamic_sparsity.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"8591416efce8c5b4"}},{"code_sha256_prefix":"f60b53c126f4f8bd","entry":"layerSparsity","repo":"AamirRaihan/SWAT","repo_kind":"official","path":"SWAT-code/cifar10-100-code/dynamic_sparsity.py","file_url":"https://github.com/AamirRaihan/SWAT/blob/HEAD/SWAT-code/cifar10-100-code/dynamic_sparsity.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"f60b53c126f4f8bd"}},{"code_sha256_prefix":"e762eef88ee684f6","entry":"custombatchnorm2d","repo":"AamirRaihan/SWAT","repo_kind":"official","path":"SWAT-code/cifar10-100-code/dynamic_sparsity.py","file_url":"https://github.com/AamirRaihan/SWAT/blob/HEAD/SWAT-code/cifar10-100-code/dynamic_sparsity.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e762eef88ee684f6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}