{"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/sample-efficient-multi-objective-molecular-1","title":"Sample-efficient Multi-objective Molecular Optimization with GFlowNets","arxiv_id":"2302.04040","date":"2023-02-08","proceeding":"NeurIPS 2023 11","authors":["Yiheng Zhu","Jialu Wu","Chaowen Hu","Jiahuan Yan","Chang-Yu Hsieh","Tingjun Hou","Jian Wu"],"abstract":"Many crucial scientific problems involve designing novel molecules with desired properties, which can be formulated as a black-box optimization problem over the discrete chemical space. In practice, multiple conflicting objectives and costly evaluations (e.g., wet-lab experiments) make the diversity of candidates paramount. Computational methods have achieved initial success but still struggle with considering diversity in both objective and search space. To fill this gap, we propose a multi-objective Bayesian optimization (MOBO) algorithm leveraging the hypernetwork-based GFlowNets (HN-GFN) as an acquisition function optimizer, with the purpose of sampling a diverse batch of candidate molecular graphs from an approximate Pareto front. Using a single preference-conditioned hypernetwork, HN-GFN learns to explore various trade-offs between objectives. We further propose a hindsight-like off-policy strategy to share high-performing molecules among different preferences in order to speed up learning for HN-GFN. We empirically illustrate that HN-GFN has adequate capacity to generalize over preferences. Moreover, experiments in various real-world MOBO settings demonstrate that our framework predominantly outperforms existing methods in terms of candidate quality and sample efficiency. The code is available at https://github.com/violet-sto/HN-GFN.","url_abs":"https://arxiv.org/abs/2302.04040v2","url_pdf":"https://arxiv.org/pdf/2302.04040v2.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":"sample-efficient-multi-objective-molecular-1","repo_url":"https://github.com/violet-sto/hn-gfn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"sample-efficient-multi-objective-molecular-1","repo_url":"https://github.com/hyeonahkimm/genetic_gfn","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":"diversity","task_name":"Diversity"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2302.04040","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.04040"}},"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":"deterministic:regex_extraction","url":"https://github.com/violet-sto/HN-GFN","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hyeonahkimm/genetic_gfn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/violet-sto/hn-gfn","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"unverified":4},"by_repo_kind":{"official":{"samples":6,"ran":2,"repositories":1},"listed":{"samples":2,"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":0,"samples":[{"code_sha256_prefix":"7a16eaef3aefaca2","entry":"GraphAgent","repo":"hyeonahkimm/genetic_gfn","repo_kind":"listed","path":"multi_objective/model_block.py","file_url":"https://github.com/hyeonahkimm/genetic_gfn/blob/HEAD/multi_objective/model_block.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7a16eaef3aefaca2"}},{"code_sha256_prefix":"43af903ddff3c3e2","entry":"GraphAgent_Concat","repo":"hyeonahkimm/genetic_gfn","repo_kind":"listed","path":"multi_objective/model_block.py","file_url":"https://github.com/hyeonahkimm/genetic_gfn/blob/HEAD/multi_objective/model_block.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"43af903ddff3c3e2"}},{"code_sha256_prefix":"6b452c8d0cc45c99","entry":"edge_match","repo":"violet-sto/HN-GFN","repo_kind":"official","path":"mol_mdp_ext.py","file_url":"https://github.com/violet-sto/HN-GFN/blob/HEAD/mol_mdp_ext.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6b452c8d0cc45c99"}},{"code_sha256_prefix":"514f704ea4cae3e4","entry":"node_match","repo":"violet-sto/HN-GFN","repo_kind":"official","path":"mol_mdp_ext.py","file_url":"https://github.com/violet-sto/HN-GFN/blob/HEAD/mol_mdp_ext.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"514f704ea4cae3e4"}},{"code_sha256_prefix":"fc7b85a52758c1c3","entry":"mol2graph","repo":"violet-sto/HN-GFN","repo_kind":"official","path":"model_block.py","file_url":"https://github.com/violet-sto/HN-GFN/blob/HEAD/model_block.py","link_basis":"harvester_set","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":"fc7b85a52758c1c3"}},{"code_sha256_prefix":"06477cbf36090384","entry":"mols2batch","repo":"violet-sto/HN-GFN","repo_kind":"official","path":"model_atom.py","file_url":"https://github.com/violet-sto/HN-GFN/blob/HEAD/model_atom.py","link_basis":"harvester_set","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":"06477cbf36090384"}},{"code_sha256_prefix":"e2f61d62c1a23b4e","entry":"mols2batch","repo":"violet-sto/HN-GFN","repo_kind":"official","path":"model_block.py","file_url":"https://github.com/violet-sto/HN-GFN/blob/HEAD/model_block.py","link_basis":"harvester_set","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":"e2f61d62c1a23b4e"}},{"code_sha256_prefix":"32208d4977dcb086","entry":"mols2batch","repo":"violet-sto/HN-GFN","repo_kind":"official","path":"model_fingerprint.py","file_url":"https://github.com/violet-sto/HN-GFN/blob/HEAD/model_fingerprint.py","link_basis":"harvester_set","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":"32208d4977dcb086"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}