{"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/comflp-correlation-measure-based-fast-search","title":"CoMFLP: Correlation Measure based Fast Search on ASR Layer Pruning","arxiv_id":"2309.11768","date":"2023-09-21","proceeding":null,"authors":["Wei Liu","Zhiyuan Peng","Tan Lee"],"abstract":"Transformer-based speech recognition (ASR) model with deep layers exhibited significant performance improvement. However, the model is inefficient for deployment on resource-constrained devices. Layer pruning (LP) is a commonly used compression method to remove redundant layers. Previous studies on LP usually identify the redundant layers according to a task-specific evaluation metric. They are time-consuming for models with a large number of layers, even in a greedy search manner. To address this problem, we propose CoMFLP, a fast search LP algorithm based on correlation measure. The correlation between layers is computed to generate a correlation matrix, which identifies the redundancy among layers. The search process is carried out in two steps: (1) coarse search: to determine top $K$ candidates by pruning the most redundant layers based on the correlation matrix; (2) fine search: to select the best pruning proposal among $K$ candidates using a task-specific evaluation metric. Experiments on an ASR task show that the pruning proposal determined by CoMFLP outperforms existing LP methods while only requiring constant time complexity. The code is publicly available at https://github.com/louislau1129/CoMFLP.","url_abs":"https://arxiv.org/abs/2309.11768v1","url_pdf":"https://arxiv.org/pdf/2309.11768v1.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":"comflp-correlation-measure-based-fast-search","repo_url":"https://github.com/louislau1129/comflp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2309.11768","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.11768"}},"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/louislau1129/comflp","reach":{"status":"ok"}}],"summary":{"ran":8,"ran_fixture":2,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":12,"ran":11,"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":12,"samples":[{"code_sha256_prefix":"185e74d9d4ac2f9f","entry":"Distance_Correlation","repo":"louislau1129/comflp","repo_kind":"official","path":"DC.py","file_url":"https://github.com/louislau1129/comflp/blob/HEAD/DC.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"185e74d9d4ac2f9f"}},{"code_sha256_prefix":"f8e8f7a11059e15d","entry":"ResNet18","repo":"louislau1129/comflp","repo_kind":"official","path":"Partial_Distance_Correlation/Diverge_Training/cifar_model.py","file_url":"https://github.com/louislau1129/comflp/blob/HEAD/Partial_Distance_Correlation/Diverge_Training/cifar_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f8e8f7a11059e15d"}},{"code_sha256_prefix":"01472465bed8b268","entry":"compute_ccas","repo":"louislau1129/comflp","repo_kind":"official","path":"svcca/cca_core.py","file_url":"https://github.com/louislau1129/comflp/blob/HEAD/svcca/cca_core.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"01472465bed8b268"}},{"code_sha256_prefix":"89013c5c47a9fbd3","entry":"distance_correlation_from_distmat","repo":"louislau1129/comflp","repo_kind":"official","path":"DC.py","file_url":"https://github.com/louislau1129/comflp/blob/HEAD/DC.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"89013c5c47a9fbd3"}},{"code_sha256_prefix":"eef8e62839bd617b","entry":"distance_matrix","repo":"louislau1129/comflp","repo_kind":"official","path":"DC.py","file_url":"https://github.com/louislau1129/comflp/blob/HEAD/DC.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eef8e62839bd617b"}},{"code_sha256_prefix":"d867f6e42584d29a","entry":"downlayer_copy_weight","repo":"louislau1129/comflp","repo_kind":"official","path":"copy_clipped_model.py","file_url":"https://github.com/louislau1129/comflp/blob/HEAD/copy_clipped_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d867f6e42584d29a"}},{"code_sha256_prefix":"56e1045d5b7e3a09","entry":"downlayer_copy_weight_series","repo":"louislau1129/comflp","repo_kind":"official","path":"copy_clipped_model.py","file_url":"https://github.com/louislau1129/comflp/blob/HEAD/copy_clipped_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"56e1045d5b7e3a09"}},{"code_sha256_prefix":"e939e8a0afab6b00","entry":"find_sv_num","repo":"louislau1129/comflp","repo_kind":"official","path":"SVCCA.py","file_url":"https://github.com/louislau1129/comflp/blob/HEAD/SVCCA.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e939e8a0afab6b00"}},{"code_sha256_prefix":"ea98389a1755bb3f","entry":"positivedef_matrix_sqrt","repo":"louislau1129/comflp","repo_kind":"official","path":"svcca/cca_core.py","file_url":"https://github.com/louislau1129/comflp/blob/HEAD/svcca/cca_core.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ea98389a1755bb3f"}},{"code_sha256_prefix":"ffcbd13c7094948e","entry":"remove_small","repo":"louislau1129/comflp","repo_kind":"official","path":"svcca/cca_core.py","file_url":"https://github.com/louislau1129/comflp/blob/HEAD/svcca/cca_core.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ffcbd13c7094948e"}},{"code_sha256_prefix":"5ffa1732676d27ab","entry":"str2bool","repo":"louislau1129/comflp","repo_kind":"official","path":"utils.py","file_url":"https://github.com/louislau1129/comflp/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5ffa1732676d27ab"}},{"code_sha256_prefix":"4b54c7c9a34d3067","entry":"relocate","repo":"louislau1129/comflp","repo_kind":"official","path":"utils.py","file_url":"https://github.com/louislau1129/comflp/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4b54c7c9a34d3067"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}