{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/anytime-neural-prediction-via-slicing","title":"Anytime Neural Prediction via Slicing Networks Vertically","arxiv_id":"1807.02609","date":"2018-07-07","proceeding":null,"authors":["Hankook Lee","Jinwoo Shin"],"abstract":"The pioneer deep neural networks (DNNs) have emerged to be deeper or wider\nfor improving their accuracy in various applications of artificial\nintelligence. However, DNNs are often too heavy to deploy in practice, and it\nis often required to control their architectures dynamically given computing\nresource budget, i.e., anytime prediction. While most existing approaches have\nfocused on training multiple shallow sub-networks jointly, we study training\nthin sub-networks instead. To this end, we first build many inclusive thin\nsub-networks (of the same depth) under a minor modification of existing\nmulti-branch DNNs, and found that they can significantly outperform the\nstate-of-art dense architecture for anytime prediction. This is remarkable due\nto their simplicity and effectiveness, but training many thin sub-networks\njointly faces a new challenge on training complexity. To address the issue, we\nalso propose a novel DNN architecture by forcing a certain sparsity pattern on\nmulti-branch network parameters, making them train efficiently for the purpose\nof anytime prediction. In our experiments on the ImageNet dataset, its\nsub-networks have up to $43.3\\%$ smaller sizes (FLOPs) compared to those of the\nstate-of-art anytime model with respect to the same accuracy. Finally, we also\npropose an alternative task under the proposed architecture using a\nhierarchical taxonomy, which brings a new angle for anytime prediction.","url_abs":"http://arxiv.org/abs/1807.02609v1","url_pdf":"http://arxiv.org/pdf/1807.02609v1.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":"anytime-neural-prediction-via-slicing","repo_url":"https://github.com/hankook/IResNeXt","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1807.02609","atlas_url":"https://app.syntology.ai/?focus=1807.02609","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1807.02609"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1807.02609\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1807.02609"},"call":"get_concepts_for_paper(arxiv_id=\"1807.02609\")"}],"by_repo":[{"repo":"hankook/IResNeXt","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"bc5aaa927eaf351370ec94f9a3ca652594ba6e3650fc40941a28f01f422a0692","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}