{"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/learnable-embedding-space-for-efficient","title":"Learnable Embedding Space for Efficient Neural Architecture Compression","arxiv_id":"1902.00383","date":"2019-02-01","proceeding":"ICLR 2019 5","authors":["Shengcao Cao","Xiaofang Wang","Kris M. Kitani"],"abstract":"We propose a method to incrementally learn an embedding space over the domain\nof network architectures, to enable the careful selection of architectures for\nevaluation during compressed architecture search. Given a teacher network, we\nsearch for a compressed network architecture by using Bayesian Optimization\n(BO) with a kernel function defined over our proposed embedding space to select\narchitectures for evaluation. We demonstrate that our search algorithm can\nsignificantly outperform various baseline methods, such as random search and\nreinforcement learning (Ashok et al., 2018). The compressed architectures found\nby our method are also better than the state-of-the-art manually-designed\ncompact architecture ShuffleNet (Zhang et al., 2018). We also demonstrate that\nthe learned embedding space can be transferred to new settings for architecture\nsearch, such as a larger teacher network or a teacher network in a different\narchitecture family, without any training. Code is publicly available here:\nhttps://github.com/Friedrich1006/ESNAC .","url_abs":"http://arxiv.org/abs/1902.00383v2","url_pdf":"http://arxiv.org/pdf/1902.00383v2.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":"learnable-embedding-space-for-efficient","repo_url":"https://github.com/Friedrich1006/ESNAC","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"learnable-embedding-space-for-efficient","repo_url":"https://github.com/KlabCMU/ESNAC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"bayesian-optimization","task_name":"Bayesian Optimization"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement 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":"channel-shuffle","method_name":"Channel Shuffle"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"grouped-convolution","method_name":"Grouped Convolution"},{"method_slug":"groupwise-point-convolution","method_name":"Groupwise Point Convolution"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"random-search","method_name":"Random Search"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"shufflenet","method_name":"ShuffleNet"},{"method_slug":"shufflenet-block","method_name":"ShuffleNet Block"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1902.00383","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.00383"}},"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/KlabCMU/ESNAC","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Friedrich1006/ESNAC","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"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":"eed18f59e16f9652","entry":"init_model","repo":"KlabCMU/ESNAC","repo_kind":"listed","path":"training.py","file_url":"https://github.com/KlabCMU/ESNAC/blob/HEAD/training.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":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"eed18f59e16f9652"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}