{"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/distilling-autoregressive-models-to-obtain","title":"Distilling Autoregressive Models to Obtain High-Performance Non-Autoregressive Solvers for Vehicle Routing Problems with Faster Inference Speed","arxiv_id":"2312.12469","date":"2023-12-19","proceeding":null,"authors":["Yubin Xiao","Di Wang","Boyang Li","Mingzhao Wang","Xuan Wu","Changliang Zhou","You Zhou"],"abstract":"Neural construction models have shown promising performance for Vehicle Routing Problems (VRPs) by adopting either the Autoregressive (AR) or Non-Autoregressive (NAR) learning approach. While AR models produce high-quality solutions, they generally have a high inference latency due to their sequential generation nature. Conversely, NAR models generate solutions in parallel with a low inference latency but generally exhibit inferior performance. In this paper, we propose a generic Guided Non-Autoregressive Knowledge Distillation (GNARKD) method to obtain high-performance NAR models having a low inference latency. GNARKD removes the constraint of sequential generation in AR models while preserving the learned pivotal components in the network architecture to obtain the corresponding NAR models through knowledge distillation. We evaluate GNARKD by applying it to three widely adopted AR models to obtain NAR VRP solvers for both synthesized and real-world instances. The experimental results demonstrate that GNARKD significantly reduces the inference time (4-5 times faster) with acceptable performance drop (2-3\\%). To the best of our knowledge, this study is first-of-its-kind to obtain NAR VRP solvers from AR ones through knowledge distillation.","url_abs":"https://arxiv.org/abs/2312.12469v2","url_pdf":"https://arxiv.org/pdf/2312.12469v2.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":"distilling-autoregressive-models-to-obtain","repo_url":"https://github.com/xybfight/gnarkd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2312.12469","atlas_url":"https://app.syntology.ai/?focus=2312.12469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12469"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/xybfight/gnarkd","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":3,"samples":[{"code_sha256_prefix":"d9ac4f54def47957","entry":"beam_search","repo":"xybfight/gnarkd","repo_kind":"official","path":"GNARKD-POMO/TSP/Test_file.py","file_url":"https://github.com/xybfight/gnarkd/blob/HEAD/GNARKD-POMO/TSP/Test_file.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d9ac4f54def47957"}},{"code_sha256_prefix":"b6bd36e3fcea0e09","entry":"compute_tour_length_all_b","repo":"xybfight/gnarkd","repo_kind":"official","path":"GNARKD-POMO/TSP/Training.py","file_url":"https://github.com/xybfight/gnarkd/blob/HEAD/GNARKD-POMO/TSP/Training.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b6bd36e3fcea0e09"}},{"code_sha256_prefix":"219d6d6b3bd838af","entry":"pomo_beam_search","repo":"xybfight/gnarkd","repo_kind":"official","path":"GNARKD-POMO/TSP/Test_file.py","file_url":"https://github.com/xybfight/gnarkd/blob/HEAD/GNARKD-POMO/TSP/Test_file.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":"219d6d6b3bd838af"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}