Guardado en:
Detalles Bibliográficos
Autores principales: Wu, Chang, Liu, Zhiyuan, Shu, Wen, Wang, Liang, Luo, Yanchen, Lei, Wenqiang, Bian, Yatao, Fang, Junfeng, Wang, Xiang
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2510.16780
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909864031158272
author Wu, Chang
Liu, Zhiyuan
Shu, Wen
Wang, Liang
Luo, Yanchen
Lei, Wenqiang
Bian, Yatao
Fang, Junfeng
Wang, Xiang
author_facet Wu, Chang
Liu, Zhiyuan
Shu, Wen
Wang, Liang
Luo, Yanchen
Lei, Wenqiang
Bian, Yatao
Fang, Junfeng
Wang, Xiang
contents Masked graph modeling (MGM) is a promising approach for molecular representation learning (MRL).However, extending the success of re-mask decoding from 2D to 3D MGM is non-trivial, primarily due to two conflicting challenges: avoiding 2D structure leakage to the decoder, while still providing sufficient 2D context for reconstructing re-masked atoms. To address these challenges, we propose 3D-GSRD: a 3D Molecular Graph Auto-Encoder with Selective Re-mask Decoding. The core innovation of 3D-GSRD lies in its Selective Re-mask Decoding(SRD), which re-masks only 3D-relevant information from encoder representations while preserving the 2D graph structures. This SRD is synergistically integrated with a 3D Relational-Transformer(3D-ReTrans) encoder alongside a structure-independent decoder. We analyze that SRD, combined with the structure-independent decoder, enhances the encoder's role in MRL. Extensive experiments show that 3D-GSRD achieves strong downstream performance, setting a new state-of-the-art on 7 out of 8 targets in the widely used MD17 molecular property prediction benchmark. The code is released at https://github.com/WuChang0124/3D-GSRD.
format Preprint
id arxiv_https___arxiv_org_abs_2510_16780
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle 3D-GSRD: 3D Molecular Graph Auto-Encoder with Selective Re-mask Decoding
Wu, Chang
Liu, Zhiyuan
Shu, Wen
Wang, Liang
Luo, Yanchen
Lei, Wenqiang
Bian, Yatao
Fang, Junfeng
Wang, Xiang
Machine Learning
Masked graph modeling (MGM) is a promising approach for molecular representation learning (MRL).However, extending the success of re-mask decoding from 2D to 3D MGM is non-trivial, primarily due to two conflicting challenges: avoiding 2D structure leakage to the decoder, while still providing sufficient 2D context for reconstructing re-masked atoms. To address these challenges, we propose 3D-GSRD: a 3D Molecular Graph Auto-Encoder with Selective Re-mask Decoding. The core innovation of 3D-GSRD lies in its Selective Re-mask Decoding(SRD), which re-masks only 3D-relevant information from encoder representations while preserving the 2D graph structures. This SRD is synergistically integrated with a 3D Relational-Transformer(3D-ReTrans) encoder alongside a structure-independent decoder. We analyze that SRD, combined with the structure-independent decoder, enhances the encoder's role in MRL. Extensive experiments show that 3D-GSRD achieves strong downstream performance, setting a new state-of-the-art on 7 out of 8 targets in the widely used MD17 molecular property prediction benchmark. The code is released at https://github.com/WuChang0124/3D-GSRD.
title 3D-GSRD: 3D Molecular Graph Auto-Encoder with Selective Re-mask Decoding
topic Machine Learning
url https://arxiv.org/abs/2510.16780