{"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/cross-problem-learning-for-solving-vehicle","title":"Cross-Problem Learning for Solving Vehicle Routing Problems","arxiv_id":"2404.11677","date":"2024-04-17","proceeding":null,"authors":["Zhuoyi Lin","Yaoxin Wu","Bangjian Zhou","Zhiguang Cao","Wen Song","Yingqian Zhang","Senthilnath Jayavelu"],"abstract":"Existing neural heuristics often train a deep architecture from scratch for each specific vehicle routing problem (VRP), ignoring the transferable knowledge across different VRP variants. This paper proposes the cross-problem learning to assist heuristics training for different downstream VRP variants. Particularly, we modularize neural architectures for complex VRPs into 1) the backbone Transformer for tackling the travelling salesman problem (TSP), and 2) the additional lightweight modules for processing problem-specific features in complex VRPs. Accordingly, we propose to pre-train the backbone Transformer for TSP, and then apply it in the process of fine-tuning the Transformer models for each target VRP variant. On the one hand, we fully fine-tune the trained backbone Transformer and problem-specific modules simultaneously. On the other hand, we only fine-tune small adapter networks along with the modules, keeping the backbone Transformer still. Extensive experiments on typical VRPs substantiate that 1) the full fine-tuning achieves significantly better performance than the one trained from scratch, and 2) the adapter-based fine-tuning also delivers comparable performance while being notably parameter-efficient. Furthermore, we empirically demonstrate the favorable effect of our method in terms of cross-distribution application and versatility.","url_abs":"https://arxiv.org/abs/2404.11677v3","url_pdf":"https://arxiv.org/pdf/2404.11677v3.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":"cross-problem-learning-for-solving-vehicle","repo_url":"https://github.com/zhuoyi-lin/cross_problem_learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"adapter","method_name":"Adapter"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.11677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.11677"}},"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/zhuoyi-lin/cross_problem_learning","reach":null}],"summary":{"ran":5,"ran_draft_wrong":2,"unverified":3},"by_repo_kind":{"official":{"samples":10,"ran":7,"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":"cac5ff2f23d7f0b9","entry":"Adapter","repo":"zhuoyi-lin/cross_problem_learning","repo_kind":"official","path":"nets/attention_model.py","file_url":"https://github.com/zhuoyi-lin/cross_problem_learning/blob/HEAD/nets/attention_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cac5ff2f23d7f0b9"}},{"code_sha256_prefix":"0b295d1d82504304","entry":"AttentionModelFixed","repo":"zhuoyi-lin/cross_problem_learning","repo_kind":"official","path":"nets/attention_model.py","file_url":"https://github.com/zhuoyi-lin/cross_problem_learning/blob/HEAD/nets/attention_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0b295d1d82504304"}},{"code_sha256_prefix":"95828c36546886bb","entry":"MultiHeadAttention","repo":"zhuoyi-lin/cross_problem_learning","repo_kind":"official","path":"nets/attention_model.py","file_url":"https://github.com/zhuoyi-lin/cross_problem_learning/blob/HEAD/nets/attention_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"95828c36546886bb"}},{"code_sha256_prefix":"d7486b45b2dfeb02","entry":"Normalization","repo":"zhuoyi-lin/cross_problem_learning","repo_kind":"official","path":"nets/attention_model.py","file_url":"https://github.com/zhuoyi-lin/cross_problem_learning/blob/HEAD/nets/attention_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d7486b45b2dfeb02"}},{"code_sha256_prefix":"8101e9e48232516f","entry":"SkipConnection","repo":"zhuoyi-lin/cross_problem_learning","repo_kind":"official","path":"nets/attention_model.py","file_url":"https://github.com/zhuoyi-lin/cross_problem_learning/blob/HEAD/nets/attention_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8101e9e48232516f"}},{"code_sha256_prefix":"e9cc8485dbd6af94","entry":"do_batch_rep","repo":"zhuoyi-lin/cross_problem_learning","repo_kind":"official","path":"nets/attention_model.py","file_url":"https://github.com/zhuoyi-lin/cross_problem_learning/blob/HEAD/nets/attention_model.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e9cc8485dbd6af94"}},{"code_sha256_prefix":"c617380b35354072","entry":"sample_many","repo":"zhuoyi-lin/cross_problem_learning","repo_kind":"official","path":"nets/attention_model.py","file_url":"https://github.com/zhuoyi-lin/cross_problem_learning/blob/HEAD/nets/attention_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c617380b35354072"}},{"code_sha256_prefix":"51bd344e0972d3b3","entry":"AttentionModel","repo":"zhuoyi-lin/cross_problem_learning","repo_kind":"official","path":"nets/attention_model.py","file_url":"https://github.com/zhuoyi-lin/cross_problem_learning/blob/HEAD/nets/attention_model.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":"51bd344e0972d3b3"}},{"code_sha256_prefix":"0ef134a41afa9250","entry":"GraphAttentionEncoder","repo":"zhuoyi-lin/cross_problem_learning","repo_kind":"official","path":"nets/attention_model.py","file_url":"https://github.com/zhuoyi-lin/cross_problem_learning/blob/HEAD/nets/attention_model.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":"0ef134a41afa9250"}},{"code_sha256_prefix":"5579c57075af815e","entry":"MultiHeadAttentionLayer","repo":"zhuoyi-lin/cross_problem_learning","repo_kind":"official","path":"nets/attention_model.py","file_url":"https://github.com/zhuoyi-lin/cross_problem_learning/blob/HEAD/nets/attention_model.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":"5579c57075af815e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}