{"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/quasi-conservative-score-based-generative","title":"On Investigating the Conservative Property of Score-Based Generative Models","arxiv_id":"2209.12753","date":"2022-09-26","proceeding":null,"authors":["Chen-Hao Chao","Wei-Fang Sun","Bo-Wun Cheng","Chun-Yi Lee"],"abstract":"Existing Score-Based Models (SBMs) can be categorized into constrained SBMs (CSBMs) or unconstrained SBMs (USBMs) according to their parameterization approaches. CSBMs model probability density functions as Boltzmann distributions, and assign their predictions as the negative gradients of some scalar-valued energy functions. On the other hand, USBMs employ flexible architectures capable of directly estimating scores without the need to explicitly model energy functions. In this paper, we demonstrate that the architectural constraints of CSBMs may limit their modeling ability. In addition, we show that USBMs' inability to preserve the property of conservativeness may lead to degraded performance in practice. To address the above issues, we propose Quasi-Conservative Score-Based Models (QCSBMs) for keeping the advantages of both CSBMs and USBMs. Our theoretical derivations demonstrate that the training objective of QCSBMs can be efficiently integrated into the training processes by leveraging the Hutchinson's trace estimator. In addition, our experimental results on the CIFAR-10, CIFAR-100, ImageNet, and SVHN datasets validate the effectiveness of QCSBMs. Finally, we justify the advantage of QCSBMs using an example of a one-layered autoencoder.","url_abs":"https://arxiv.org/abs/2209.12753v3","url_pdf":"https://arxiv.org/pdf/2209.12753v3.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":"quasi-conservative-score-based-generative","repo_url":"https://github.com/chen-hao-chao/qcsbm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-imagenet-32x32","task":"Image Generation","dataset":"ImageNet 32x32","model":"QC-NCSN++","rank_in_archive_order":13,"of":35,"metrics":{"FID":"19.62","Inception score":"9.94"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2209.12753","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.12753"}},"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/chen-hao-chao/qcsbm","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2,"unverified":8},"by_repo_kind":{"official":{"samples":10,"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":"8ff7c24dade9904c","entry":"get_optimizer","repo":"chen-hao-chao/qcsbm","repo_kind":"official","path":"real_world/losses.py","file_url":"https://github.com/chen-hao-chao/qcsbm/blob/HEAD/real_world/losses.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8ff7c24dade9904c"}},{"code_sha256_prefix":"366bb8c7035a2fc8","entry":"optimization_manager","repo":"chen-hao-chao/qcsbm","repo_kind":"official","path":"real_world/losses.py","file_url":"https://github.com/chen-hao-chao/qcsbm/blob/HEAD/real_world/losses.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"366bb8c7035a2fc8"}},{"code_sha256_prefix":"079c57a39a6c5cba","entry":"from_flattened_numpy","repo":"chen-hao-chao/qcsbm","repo_kind":"official","path":"2d_examples/likelihood.py","file_url":"https://github.com/chen-hao-chao/qcsbm/blob/HEAD/2d_examples/likelihood.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"079c57a39a6c5cba"}},{"code_sha256_prefix":"fc7647832d475a31","entry":"get_div_fn","repo":"chen-hao-chao/qcsbm","repo_kind":"official","path":"2d_examples/likelihood.py","file_url":"https://github.com/chen-hao-chao/qcsbm/blob/HEAD/2d_examples/likelihood.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fc7647832d475a31"}},{"code_sha256_prefix":"40193c964ac8904e","entry":"get_ode_sampler","repo":"chen-hao-chao/qcsbm","repo_kind":"official","path":"2d_examples/sampling_fn.py","file_url":"https://github.com/chen-hao-chao/qcsbm/blob/HEAD/2d_examples/sampling_fn.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"40193c964ac8904e"}},{"code_sha256_prefix":"22392e9874fb3431","entry":"get_step_fn","repo":"chen-hao-chao/qcsbm","repo_kind":"official","path":"2d_examples/losses.py","file_url":"https://github.com/chen-hao-chao/qcsbm/blob/HEAD/2d_examples/losses.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"22392e9874fb3431"}},{"code_sha256_prefix":"f3f215c2361c2958","entry":"scan","repo":"chen-hao-chao/qcsbm","repo_kind":"official","path":"2d_examples/sde_lib.py","file_url":"https://github.com/chen-hao-chao/qcsbm/blob/HEAD/2d_examples/sde_lib.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f3f215c2361c2958"}},{"code_sha256_prefix":"4c6099d480772401","entry":"to_flattened_numpy","repo":"chen-hao-chao/qcsbm","repo_kind":"official","path":"2d_examples/likelihood.py","file_url":"https://github.com/chen-hao-chao/qcsbm/blob/HEAD/2d_examples/likelihood.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4c6099d480772401"}},{"code_sha256_prefix":"0d480a5e5f4ef7a9","entry":"to_sliced_tensor","repo":"chen-hao-chao/qcsbm","repo_kind":"official","path":"2d_examples/losses.py","file_url":"https://github.com/chen-hao-chao/qcsbm/blob/HEAD/2d_examples/losses.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0d480a5e5f4ef7a9"}},{"code_sha256_prefix":"94885b5b78ee8716","entry":"to_sliced_vector","repo":"chen-hao-chao/qcsbm","repo_kind":"official","path":"2d_examples/losses.py","file_url":"https://github.com/chen-hao-chao/qcsbm/blob/HEAD/2d_examples/losses.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"94885b5b78ee8716"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}