{"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/over-parameterized-student-model-via-tensor","title":"Over-parameterized Student Model via Tensor Decomposition Boosted Knowledge Distillation","arxiv_id":"2411.06448","date":"2024-11-10","proceeding":null,"authors":["Yu-Liang Zhan","Zhong-Yi Lu","Hao Sun","Ze-Feng Gao"],"abstract":"Increased training parameters have enabled large pre-trained models to excel in various downstream tasks. Nevertheless, the extensive computational requirements associated with these models hinder their widespread adoption within the community. We focus on Knowledge Distillation (KD), where a compact student model is trained to mimic a larger teacher model, facilitating the transfer of knowledge of large models. In contrast to much of the previous work, we scale up the parameters of the student model during training, to benefit from overparameterization without increasing the inference latency. In particular, we propose a tensor decomposition strategy that effectively over-parameterizes the relatively small student model through an efficient and nearly lossless decomposition of its parameter matrices into higher-dimensional tensors. To ensure efficiency, we further introduce a tensor constraint loss to align the high-dimensional tensors between the student and teacher models. Comprehensive experiments validate the significant performance enhancement by our approach in various KD tasks, covering computer vision and natural language processing areas. Our code is available at https://github.com/intell-sci-comput/OPDF.","url_abs":"https://arxiv.org/abs/2411.06448v1","url_pdf":"https://arxiv.org/pdf/2411.06448v1.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":"over-parameterized-student-model-via-tensor","repo_url":"https://github.com/intell-sci-comput/opdf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"tensor-decomposition","task_name":"Tensor Decomposition"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"focus","method_name":"Focus"},{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.06448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.06448"}},"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/intell-sci-comput/OPDF","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/intell-sci-comput/opdf","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"unverified":4},"by_repo_kind":{"official":{"samples":7,"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":0,"samples":[{"code_sha256_prefix":"940dcf82641060b8","entry":"cal_loss","repo":"intell-sci-comput/OPDF","repo_kind":"official","path":"LGTM/utils_glue.py","file_url":"https://github.com/intell-sci-comput/OPDF/blob/HEAD/LGTM/utils_glue.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"940dcf82641060b8"}},{"code_sha256_prefix":"84cdd837c3bc6ef4","entry":"get_linear_schedule_with_warmup_atleast","repo":"intell-sci-comput/opdf","repo_kind":"official","path":"compress_tools/trainer_bert_4.py","file_url":"https://github.com/intell-sci-comput/opdf/blob/HEAD/compress_tools/trainer_bert_4.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"84cdd837c3bc6ef4"}},{"code_sha256_prefix":"383d339873e8f63f","entry":"get_parameter_number","repo":"intell-sci-comput/opdf","repo_kind":"official","path":"compress_tools/trainer_bert_4.py","file_url":"https://github.com/intell-sci-comput/opdf/blob/HEAD/compress_tools/trainer_bert_4.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"383d339873e8f63f"}},{"code_sha256_prefix":"d34cc0827c3ebfd6","entry":"evaluate","repo":"intell-sci-comput/OPDF","repo_kind":"official","path":"BERT-of-Theseus/run_glue_MPO_losslayer.py","file_url":"https://github.com/intell-sci-comput/OPDF/blob/HEAD/BERT-of-Theseus/run_glue_MPO_losslayer.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":"d34cc0827c3ebfd6"}},{"code_sha256_prefix":"97549800b52bcd2d","entry":"load_and_cache_examples","repo":"intell-sci-comput/OPDF","repo_kind":"official","path":"BERT-of-Theseus/run_glue_MPO_losslayer.py","file_url":"https://github.com/intell-sci-comput/OPDF/blob/HEAD/BERT-of-Theseus/run_glue_MPO_losslayer.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":"97549800b52bcd2d"}},{"code_sha256_prefix":"9ba218848664cb10","entry":"loss_layer_fn","repo":"intell-sci-comput/opdf","repo_kind":"official","path":"LGTM/run_glue_mpo_laterloss.py","file_url":"https://github.com/intell-sci-comput/opdf/blob/HEAD/LGTM/run_glue_mpo_laterloss.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":"9ba218848664cb10"}},{"code_sha256_prefix":"b0cda6f406f25617","entry":"speed_metrics","repo":"intell-sci-comput/OPDF","repo_kind":"official","path":"compress_tools/ChildTuningD.py","file_url":"https://github.com/intell-sci-comput/OPDF/blob/HEAD/compress_tools/ChildTuningD.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":"b0cda6f406f25617"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}