{"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/dsee-dually-sparsity-embedded-efficient-1","title":"DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models","arxiv_id":"2111.00160","date":"2021-10-30","proceeding":null,"authors":["Xuxi Chen","Tianlong Chen","Weizhu Chen","Ahmed Hassan Awadallah","Zhangyang Wang","Yu Cheng"],"abstract":"Gigantic pre-trained models have become central to natural language processing (NLP), serving as the starting point for fine-tuning towards a range of downstream tasks. However, two pain points persist for this paradigm: (a) as the pre-trained models grow bigger (e.g., 175B parameters for GPT-3), even the fine-tuning process can be time-consuming and computationally expensive; (b) the fine-tuned model has the same size as its starting point by default, which is neither sensible due to its more specialized functionality, nor practical since many fine-tuned models will be deployed in resource-constrained environments. To address these pain points, we propose a framework for resource- and parameter-efficient fine-tuning by leveraging the sparsity prior in both weight updates and the final model weights. Our proposed framework, dubbed Dually Sparsity-Embedded Efficient Tuning (DSEE), aims to achieve two key objectives: (i) parameter efficient fine-tuning - by enforcing sparsity-aware low-rank updates on top of the pre-trained weights; and (ii) resource-efficient inference - by encouraging a sparse weight structure towards the final fine-tuned model. We leverage sparsity in these two directions by exploiting both unstructured and structured sparse patterns in pre-trained language models via a unified approach. Extensive experiments and in-depth investigations, with diverse network backbones (i.e., BERT, RoBERTa, and GPT-2) on dozens of datasets, consistently demonstrate impressive parameter-/inference-efficiency, while maintaining competitive downstream performance. For instance, DSEE saves about 25% inference FLOPs while achieving comparable performance, with 0.5% trainable parameters on BERT. Codes are available in https://github.com/VITA-Group/DSEE.","url_abs":"https://arxiv.org/abs/2111.00160v3","url_pdf":"https://arxiv.org/pdf/2111.00160v3.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":"dsee-dually-sparsity-embedded-efficient-1","repo_url":"https://github.com/vita-group/dsee","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"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":"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":"softmax","method_name":"Softmax"},{"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=2111.00160","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.00160"}},"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/vita-group/dsee","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"ran_draft_wrong":1,"ran_fixture":1,"unverified":6},"by_repo_kind":{"official":{"samples":12,"ran":6,"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":"a727df5fd2f5599a","entry":"check_number_comma","repo":"vita-group/dsee","repo_kind":"official","path":"non-GPT-2/src/transformers/convert_slow_tokenizer.py","file_url":"https://github.com/vita-group/dsee/blob/HEAD/non-GPT-2/src/transformers/convert_slow_tokenizer.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":"a727df5fd2f5599a"}},{"code_sha256_prefix":"d770e1dd1d799a47","entry":"ensure_valid_input","repo":"vita-group/dsee","repo_kind":"official","path":"non-GPT-2/src/transformers/convert_graph_to_onnx.py","file_url":"https://github.com/vita-group/dsee/blob/HEAD/non-GPT-2/src/transformers/convert_graph_to_onnx.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":"d770e1dd1d799a47"}},{"code_sha256_prefix":"a4475703ff58ecf9","entry":"gelu_fast","repo":"vita-group/dsee","repo_kind":"official","path":"non-GPT-2/src/transformers/activations.py","file_url":"https://github.com/vita-group/dsee/blob/HEAD/non-GPT-2/src/transformers/activations.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a4475703ff58ecf9"}},{"code_sha256_prefix":"45bb87451230d5e8","entry":"gelu_new","repo":"vita-group/dsee","repo_kind":"official","path":"non-GPT-2/src/transformers/activations.py","file_url":"https://github.com/vita-group/dsee/blob/HEAD/non-GPT-2/src/transformers/activations.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"45bb87451230d5e8"}},{"code_sha256_prefix":"7639bb277f652362","entry":"generate_batch_splits","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"7639bb277f652362"}},{"code_sha256_prefix":"7efe3db5c9e2f94d","entry":"generate_identified_filename","repo":"vita-group/dsee","repo_kind":"official","path":"non-GPT-2/src/transformers/convert_graph_to_onnx.py","file_url":"https://github.com/vita-group/dsee/blob/HEAD/non-GPT-2/src/transformers/convert_graph_to_onnx.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":"7efe3db5c9e2f94d"}},{"code_sha256_prefix":"e21f72f1a9834aef","entry":"quick_gelu","repo":"vita-group/dsee","repo_kind":"official","path":"non-GPT-2/src/transformers/activations.py","file_url":"https://github.com/vita-group/dsee/blob/HEAD/non-GPT-2/src/transformers/activations.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e21f72f1a9834aef"}},{"code_sha256_prefix":"5513be821f28f6c5","entry":"convert_slow_tokenizer","repo":"vita-group/dsee","repo_kind":"official","path":"non-GPT-2/src/transformers/convert_slow_tokenizer.py","file_url":"https://github.com/vita-group/dsee/blob/HEAD/non-GPT-2/src/transformers/convert_slow_tokenizer.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":"5513be821f28f6c5"}},{"code_sha256_prefix":"58e4e5b4f1f2951e","entry":"detect_overflow","repo":"vita-group/dsee","repo_kind":"official","path":"non-GPT-2/src/transformers/debug_utils.py","file_url":"https://github.com/vita-group/dsee/blob/HEAD/non-GPT-2/src/transformers/debug_utils.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":"58e4e5b4f1f2951e"}},{"code_sha256_prefix":"37a5eed2dbd663ca","entry":"gelu_fast","repo":"vita-group/dsee","repo_kind":"official","path":"non-GPT-2/src/transformers/activations_tf.py","file_url":"https://github.com/vita-group/dsee/blob/HEAD/non-GPT-2/src/transformers/activations_tf.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":"37a5eed2dbd663ca"}},{"code_sha256_prefix":"b5db92a796ef38f1","entry":"get_abs_min_max","repo":"vita-group/dsee","repo_kind":"official","path":"non-GPT-2/src/transformers/debug_utils.py","file_url":"https://github.com/vita-group/dsee/blob/HEAD/non-GPT-2/src/transformers/debug_utils.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":"b5db92a796ef38f1"}},{"code_sha256_prefix":"3449d7d975edfb89","entry":"infer_shapes","repo":"vita-group/dsee","repo_kind":"official","path":"non-GPT-2/src/transformers/convert_graph_to_onnx.py","file_url":"https://github.com/vita-group/dsee/blob/HEAD/non-GPT-2/src/transformers/convert_graph_to_onnx.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":"3449d7d975edfb89"}},{"code_sha256_prefix":"cc8c8c3ebf0c343f","entry":"mish","repo":"vita-group/dsee","repo_kind":"official","path":"non-GPT-2/src/transformers/activations_tf.py","file_url":"https://github.com/vita-group/dsee/blob/HEAD/non-GPT-2/src/transformers/activations_tf.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":"cc8c8c3ebf0c343f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}