{"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/meta-sage-scale-meta-learning-scheduled","title":"Meta-SAGE: Scale Meta-Learning Scheduled Adaptation with Guided Exploration for Mitigating Scale Shift on Combinatorial Optimization","arxiv_id":"2306.02688","date":"2023-06-05","proceeding":null,"authors":["Jiwoo Son","Minsu Kim","Hyeonah Kim","Jinkyoo Park"],"abstract":"This paper proposes Meta-SAGE, a novel approach for improving the scalability of deep reinforcement learning models for combinatorial optimization (CO) tasks. Our method adapts pre-trained models to larger-scale problems in test time by suggesting two components: a scale meta-learner (SML) and scheduled adaptation with guided exploration (SAGE). First, SML transforms the context embedding for subsequent adaptation of SAGE based on scale information. Then, SAGE adjusts the model parameters dedicated to the context embedding for a specific instance. SAGE introduces locality bias, which encourages selecting nearby locations to determine the next location. The locality bias gradually decays as the model is adapted to the target instance. Results show that Meta-SAGE outperforms previous adaptation methods and significantly improves scalability in representative CO tasks. Our source code is available at https://github.com/kaist-silab/meta-sage","url_abs":"https://arxiv.org/abs/2306.02688v2","url_pdf":"https://arxiv.org/pdf/2306.02688v2.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":"meta-sage-scale-meta-learning-scheduled","repo_url":"https://github.com/kaist-silab/meta-sage","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"combinatorial-optimization","task_name":"Combinatorial Optimization"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2306.02688","atlas_url":"https://app.syntology.ai/?focus=2306.02688","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02688"}},"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":"deterministic:regex_extraction","url":"https://github.com/kaist-silab/meta-sage","reach":null}],"summary":{"ran":1,"unverified":6},"by_repo_kind":{"official":{"samples":7,"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":7,"samples":[{"code_sha256_prefix":"4e152320b67d49fd","entry":"EncoderLayer","repo":"kaist-silab/meta-sage","repo_kind":"official","path":"Meta-SAGE/train/POMO/CVRP/2_Meta/SML_Model.py","file_url":"https://github.com/kaist-silab/meta-sage/blob/HEAD/Meta-SAGE/train/POMO/CVRP/2_Meta/SML_Model.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":"4e152320b67d49fd"}},{"code_sha256_prefix":"d4d4b5a5c19abb2f","entry":"CVRPModel","repo":"kaist-silab/meta-sage","repo_kind":"official","path":"Meta-SAGE/train/POMO/CVRP/2_Meta/SML_Model.py","file_url":"https://github.com/kaist-silab/meta-sage/blob/HEAD/Meta-SAGE/train/POMO/CVRP/2_Meta/SML_Model.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":"d4d4b5a5c19abb2f"}},{"code_sha256_prefix":"f062140aa1bdbb2a","entry":"CVRP_Decoder","repo":"kaist-silab/meta-sage","repo_kind":"official","path":"Meta-SAGE/train/POMO/CVRP/2_Meta/SML_Model.py","file_url":"https://github.com/kaist-silab/meta-sage/blob/HEAD/Meta-SAGE/train/POMO/CVRP/2_Meta/SML_Model.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":"f062140aa1bdbb2a"}},{"code_sha256_prefix":"9af783aaecec7c6d","entry":"CVRP_Encoder","repo":"kaist-silab/meta-sage","repo_kind":"official","path":"Meta-SAGE/train/POMO/CVRP/2_Meta/SML_Model.py","file_url":"https://github.com/kaist-silab/meta-sage/blob/HEAD/Meta-SAGE/train/POMO/CVRP/2_Meta/SML_Model.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":"9af783aaecec7c6d"}},{"code_sha256_prefix":"6aec695bf98963f1","entry":"EAS_CVRP_Decoder","repo":"kaist-silab/meta-sage","repo_kind":"official","path":"Meta-SAGE/train/POMO/CVRP/2_Meta/SML_Model.py","file_url":"https://github.com/kaist-silab/meta-sage/blob/HEAD/Meta-SAGE/train/POMO/CVRP/2_Meta/SML_Model.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":"6aec695bf98963f1"}},{"code_sha256_prefix":"f610a53ceb5cf23b","entry":"SML_Model","repo":"kaist-silab/meta-sage","repo_kind":"official","path":"Meta-SAGE/train/POMO/CVRP/2_Meta/SML_Model.py","file_url":"https://github.com/kaist-silab/meta-sage/blob/HEAD/Meta-SAGE/train/POMO/CVRP/2_Meta/SML_Model.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":"f610a53ceb5cf23b"}},{"code_sha256_prefix":"c10e17f8940e2635","entry":"multi_head_attention","repo":"kaist-silab/meta-sage","repo_kind":"official","path":"Meta-SAGE/train/POMO/CVRP/2_Meta/SML_Model.py","file_url":"https://github.com/kaist-silab/meta-sage/blob/HEAD/Meta-SAGE/train/POMO/CVRP/2_Meta/SML_Model.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":"c10e17f8940e2635"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}