{"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/data-efficient-molecular-generation-with","title":"Data-Efficient Molecular Generation with Hierarchical Textual Inversion","arxiv_id":"2405.02845","date":"2024-05-05","proceeding":null,"authors":["Seojin Kim","Jaehyun Nam","Sihyun Yu","Younghoon Shin","Jinwoo Shin"],"abstract":"Developing an effective molecular generation framework even with a limited number of molecules is often important for its practical deployment, e.g., drug discovery, since acquiring task-related molecular data requires expensive and time-consuming experimental costs. To tackle this issue, we introduce Hierarchical textual Inversion for Molecular generation (HI-Mol), a novel data-efficient molecular generation method. HI-Mol is inspired by the importance of hierarchical information, e.g., both coarse- and fine-grained features, in understanding the molecule distribution. We propose to use multi-level embeddings to reflect such hierarchical features based on the adoption of the recent textual inversion technique in the visual domain, which achieves data-efficient image generation. Compared to the conventional textual inversion method in the image domain using a single-level token embedding, our multi-level token embeddings allow the model to effectively learn the underlying low-shot molecule distribution. We then generate molecules based on the interpolation of the multi-level token embeddings. Extensive experiments demonstrate the superiority of HI-Mol with notable data-efficiency. For instance, on QM9, HI-Mol outperforms the prior state-of-the-art method with 50x less training data. We also show the effectiveness of molecules generated by HI-Mol in low-shot molecular property prediction.","url_abs":"https://arxiv.org/abs/2405.02845v3","url_pdf":"https://arxiv.org/pdf/2405.02845v3.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":"data-efficient-molecular-generation-with","repo_url":"https://github.com/seojin-kim/hi-mol","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"drug-discovery","task_name":"Drug Discovery"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"molecular-property-prediction","task_name":"Molecular Property Prediction"},{"task_slug":"property-prediction","task_name":"Property Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.02845","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}