{"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/pessimistic-backward-policy-for-gflownets","title":"Pessimistic Backward Policy for GFlowNets","arxiv_id":"2405.16012","date":"2024-05-25","proceeding":null,"authors":["Hyosoon Jang","Yunhui Jang","Minsu Kim","Jinkyoo Park","Sungsoo Ahn"],"abstract":"This paper studies Generative Flow Networks (GFlowNets), which learn to sample objects proportionally to a given reward function through the trajectory of state transitions. In this work, we observe that GFlowNets tend to under-exploit the high-reward objects due to training on insufficient number of trajectories, which may lead to a large gap between the estimated flow and the (known) reward value. In response to this challenge, we propose a pessimistic backward policy for GFlowNets (PBP-GFN), which maximizes the observed flow to align closely with the true reward for the object. We extensively evaluate PBP-GFN across eight benchmarks, including hyper-grid environment, bag generation, structured set generation, molecular generation, and four RNA sequence generation tasks. In particular, PBP-GFN enhances the discovery of high-reward objects, maintains the diversity of the objects, and consistently outperforms existing methods.","url_abs":"https://arxiv.org/abs/2405.16012v3","url_pdf":"https://arxiv.org/pdf/2405.16012v3.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":"pessimistic-backward-policy-for-gflownets","repo_url":"https://github.com/hsjang0/Pessimistic-Backward-Policy-for-GFlowNets","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2405.16012","atlas_url":"https://app.syntology.ai/?focus=2405.16012","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16012"}},"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/hsjang0/Pessimistic-Backward-Policy-for-GFlowNets","reach":{"status":"ok"}}],"summary":{"ran":4,"ran_fixture":1,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":9,"ran":6,"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":9,"samples":[{"code_sha256_prefix":"e62c1b64d8aa2840","entry":"collate_states_scores","repo":"hsjang0/Pessimistic-Backward-Policy-for-GFlowNets","repo_kind":"official","path":"bag_rna-Shen/gflownet/policy.py","file_url":"https://github.com/hsjang0/Pessimistic-Backward-Policy-for-GFlowNets/blob/HEAD/bag_rna-Shen/gflownet/policy.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e62c1b64d8aa2840"}},{"code_sha256_prefix":"2a8ed5bf472b7004","entry":"cross","repo":"hsjang0/Pessimistic-Backward-Policy-for-GFlowNets","repo_kind":"official","path":"Molecule-Recursion/algo/gafn.py","file_url":"https://github.com/hsjang0/Pessimistic-Backward-Policy-for-GFlowNets/blob/HEAD/Molecule-Recursion/algo/gafn.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2a8ed5bf472b7004"}},{"code_sha256_prefix":"240e3fc45661be7a","entry":"log_reward","repo":"hsjang0/Pessimistic-Backward-Policy-for-GFlowNets","repo_kind":"official","path":"grid_PBP-GFN.py","file_url":"https://github.com/hsjang0/Pessimistic-Backward-Policy-for-GFlowNets/blob/HEAD/grid_PBP-GFN.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":"240e3fc45661be7a"}},{"code_sha256_prefix":"9337a834d9e051aa","entry":"make_mlp","repo":"hsjang0/Pessimistic-Backward-Policy-for-GFlowNets","repo_kind":"official","path":"grid_PBP-GFN.py","file_url":"https://github.com/hsjang0/Pessimistic-Backward-Policy-for-GFlowNets/blob/HEAD/grid_PBP-GFN.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9337a834d9e051aa"}},{"code_sha256_prefix":"a508d01ed77ced0b","entry":"shift_right","repo":"hsjang0/Pessimistic-Backward-Policy-for-GFlowNets","repo_kind":"official","path":"Molecule-Recursion/algo/gafn.py","file_url":"https://github.com/hsjang0/Pessimistic-Backward-Policy-for-GFlowNets/blob/HEAD/Molecule-Recursion/algo/gafn.py","link_basis":"plan_row","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":"a508d01ed77ced0b"}},{"code_sha256_prefix":"1c1c49b8bea48852","entry":"toin","repo":"hsjang0/Pessimistic-Backward-Policy-for-GFlowNets","repo_kind":"official","path":"grid_PBP-GFN.py","file_url":"https://github.com/hsjang0/Pessimistic-Backward-Policy-for-GFlowNets/blob/HEAD/grid_PBP-GFN.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1c1c49b8bea48852"}},{"code_sha256_prefix":"797497ec7c51c286","entry":"collate_probs","repo":"hsjang0/Pessimistic-Backward-Policy-for-GFlowNets","repo_kind":"official","path":"bag_rna-Shen/gflownet/policy.py","file_url":"https://github.com/hsjang0/Pessimistic-Backward-Policy-for-GFlowNets/blob/HEAD/bag_rna-Shen/gflownet/policy.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":"797497ec7c51c286"}},{"code_sha256_prefix":"3215acf27eba4238","entry":"subTB","repo":"hsjang0/Pessimistic-Backward-Policy-for-GFlowNets","repo_kind":"official","path":"Molecule-Recursion/algo/gafn.py","file_url":"https://github.com/hsjang0/Pessimistic-Backward-Policy-for-GFlowNets/blob/HEAD/Molecule-Recursion/algo/gafn.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":"3215acf27eba4238"}},{"code_sha256_prefix":"f928c1f4da5deecd","entry":"unique_keep_order_filter_children","repo":"hsjang0/Pessimistic-Backward-Policy-for-GFlowNets","repo_kind":"official","path":"bag_rna-Shen/gflownet/policy.py","file_url":"https://github.com/hsjang0/Pessimistic-Backward-Policy-for-GFlowNets/blob/HEAD/bag_rna-Shen/gflownet/policy.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":"f928c1f4da5deecd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}