{"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/re-balancing-variational-autoencoder-loss-for","title":"Re-balancing Variational Autoencoder Loss for Molecule Sequence Generation","arxiv_id":"1910.00698","date":"2019-10-01","proceeding":null,"authors":["Chaochao Yan","Sheng Wang","Jinyu Yang","Tingyang Xu","Junzhou Huang"],"abstract":"Molecule generation is to design new molecules with specific chemical properties and further to optimize the desired chemical properties. Following previous work, we encode molecules into continuous vectors in the latent space and then decode the vectors into molecules under the variational autoencoder (VAE) framework. We investigate the posterior collapse problem of current RNN-based VAEs for molecule sequence generation. For the first time, we find that underestimated reconstruction loss leads to posterior collapse, and provide both theoretical and experimental evidence. We propose an effective and efficient solution to fix the problem and avoid posterior collapse. Without bells and whistles, our method achieves SOTA reconstruction accuracy and competitive validity on the ZINC 250K dataset. When generating 10,000 unique valid SMILES from random prior sampling, it costs JT-VAE1450s while our method only needs 9s. Our implementation is at https://github.com/chaoyan1037/Re-balanced-VAE.","url_abs":"https://arxiv.org/abs/1910.00698v2","url_pdf":"https://arxiv.org/pdf/1910.00698v2.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":"re-balancing-variational-autoencoder-loss-for","repo_url":"https://github.com/chaoyan1037/Re-balanced-VAE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1910.00698","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.00698"}},"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/chaoyan1037/Re-balanced-VAE","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"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":"6c74edc2c0dc695e","entry":"compute_kernel_numpy","repo":"chaoyan1037/Re-balanced-VAE","repo_kind":"official","path":"bo/gauss.py","file_url":"https://github.com/chaoyan1037/Re-balanced-VAE/blob/HEAD/bo/gauss.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":"6c74edc2c0dc695e"}},{"code_sha256_prefix":"efe304eb2d1e874e","entry":"load_object","repo":"chaoyan1037/Re-balanced-VAE","repo_kind":"official","path":"bo/print_result.py","file_url":"https://github.com/chaoyan1037/Re-balanced-VAE/blob/HEAD/bo/print_result.py","link_basis":"first_harvest_node","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":"efe304eb2d1e874e"}},{"code_sha256_prefix":"0a5b664a833db116","entry":"load_object","repo":"chaoyan1037/Re-balanced-VAE","repo_kind":"official","path":"bo/run_bo.py","file_url":"https://github.com/chaoyan1037/Re-balanced-VAE/blob/HEAD/bo/run_bo.py","link_basis":"first_harvest_node","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":"0a5b664a833db116"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}