{"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/a-general-and-efficient-training-for","title":"A General and Efficient Training for Transformer via Token Expansion","arxiv_id":"2404.00672","date":"2024-03-31","proceeding":"CVPR 2024 1","authors":["Wenxuan Huang","Yunhang Shen","Jiao Xie","Baochang Zhang","Gaoqi He","Ke Li","Xing Sun","Shaohui Lin"],"abstract":"The remarkable performance of Vision Transformers (ViTs) typically requires an extremely large training cost. Existing methods have attempted to accelerate the training of ViTs, yet typically disregard method universality with accuracy dropping. Meanwhile, they break the training consistency of the original transformers, including the consistency of hyper-parameters, architecture, and strategy, which prevents them from being widely applied to different Transformer networks. In this paper, we propose a novel token growth scheme Token Expansion (termed ToE) to achieve consistent training acceleration for ViTs. We introduce an \"initialization-expansion-merging\" pipeline to maintain the integrity of the intermediate feature distribution of original transformers, preventing the loss of crucial learnable information in the training process. ToE can not only be seamlessly integrated into the training and fine-tuning process of transformers (e.g., DeiT and LV-ViT), but also effective for efficient training frameworks (e.g., EfficientTrain), without twisting the original training hyper-parameters, architecture, and introducing additional training strategies. Extensive experiments demonstrate that ToE achieves about 1.3x faster for the training of ViTs in a lossless manner, or even with performance gains over the full-token training baselines. Code is available at https://github.com/Osilly/TokenExpansion .","url_abs":"https://arxiv.org/abs/2404.00672v1","url_pdf":"https://arxiv.org/pdf/2404.00672v1.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":"a-general-and-efficient-training-for","repo_url":"https://github.com/osilly/tokenexpansion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"deit","method_name":"DeiT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.00672","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00672"}},"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/osilly/tokenexpansion","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/Osilly/TokenExpansion","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":2,"ran":3,"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"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":"144d10b49baeb8a6","entry":"window_partition","repo":"osilly/tokenexpansion","repo_kind":"official","path":"ToE/EfficientTrain/models/swin.py","file_url":"https://github.com/osilly/tokenexpansion/blob/HEAD/ToE/EfficientTrain/models/swin.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"144d10b49baeb8a6"}},{"code_sha256_prefix":"ed66abf8ce1543ae","entry":"TokenSelect","repo":"Osilly/TokenExpansion","repo_kind":"official","path":"ToE/EfficientTrain/models/deit_expansion.py","file_url":"https://github.com/Osilly/TokenExpansion/blob/HEAD/ToE/EfficientTrain/models/deit_expansion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ed66abf8ce1543ae"}},{"code_sha256_prefix":"cd3815bc733c3af8","entry":"build_dataset","repo":"osilly/tokenexpansion","repo_kind":"official","path":"ToE/EfficientTrain/datasets.py","file_url":"https://github.com/osilly/tokenexpansion/blob/HEAD/ToE/EfficientTrain/datasets.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":"cd3815bc733c3af8"}},{"code_sha256_prefix":"60fc00ee96a43cdf","entry":"build_transform","repo":"osilly/tokenexpansion","repo_kind":"official","path":"ToE/EfficientTrain/datasets.py","file_url":"https://github.com/osilly/tokenexpansion/blob/HEAD/ToE/EfficientTrain/datasets.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":"60fc00ee96a43cdf"}},{"code_sha256_prefix":"39b18f062e0cc6d9","entry":"img2windows","repo":"osilly/tokenexpansion","repo_kind":"official","path":"ToE/EfficientTrain/models/cswin.py","file_url":"https://github.com/osilly/tokenexpansion/blob/HEAD/ToE/EfficientTrain/models/cswin.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"39b18f062e0cc6d9"}},{"code_sha256_prefix":"61bf152e6a42a184","entry":"window_reverse","repo":"osilly/tokenexpansion","repo_kind":"official","path":"ToE/EfficientTrain/models/swin.py","file_url":"https://github.com/osilly/tokenexpansion/blob/HEAD/ToE/EfficientTrain/models/swin.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"61bf152e6a42a184"}},{"code_sha256_prefix":"ab01fbfe58c75b08","entry":"windows2img","repo":"osilly/tokenexpansion","repo_kind":"official","path":"ToE/EfficientTrain/models/cswin.py","file_url":"https://github.com/osilly/tokenexpansion/blob/HEAD/ToE/EfficientTrain/models/cswin.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ab01fbfe58c75b08"}},{"code_sha256_prefix":"4f40d9a1fc241aab","entry":"VisionTransformerExpansion","repo":"Osilly/TokenExpansion","repo_kind":"official","path":"ToE/EfficientTrain/models/deit_expansion.py","file_url":"https://github.com/Osilly/TokenExpansion/blob/HEAD/ToE/EfficientTrain/models/deit_expansion.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":"4f40d9a1fc241aab"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}