SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.02845 · ICML · 2024

Data-Efficient Molecular Generation with Hierarchical Textual Inversion

Jinwoo Shin, Sihyun Yu, Jaehyun Nam, Seojin Kim, Younghoon Shin

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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 coarseand fine-grained features, in understanding the molecule distribution. We propose to use multilevel 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-ofthe-art method with 50× less training data. We also show the effectiveness of molecules generated by HI-Mol in low-shot molecular property prediction. Code is available at https: //github.com/Seojin-Kim/HI-Mol.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2405.02845")
get_code_for_paper("2405.02845")
have("2405.02845")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2405.02845.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2405.02845.svg)](https://syntology.ai/paper/2405.02845)

Connect an agent — have() is free.