Towards Cross-Modal Text-Molecule Retrieval with Better Modality Alignment

October 31, 2024 Β· Declared Dead Β· πŸ› IEEE International Conference on Bioinformatics and Biomedicine

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Jia Song, Wanru Zhuang, Yujie Lin, Liang Zhang, Chunyan Li, Jinsong Su, Song He, Xiaochen Bo arXiv ID 2410.23715 Category cs.IR: Information Retrieval Citations 4 Venue IEEE International Conference on Bioinformatics and Biomedicine Last Checked 4 months ago
Abstract
Cross-modal text-molecule retrieval model aims to learn a shared feature space of the text and molecule modalities for accurate similarity calculation, which facilitates the rapid screening of molecules with specific properties and activities in drug design. However, previous works have two main defects. First, they are inadequate in capturing modality-shared features considering the significant gap between text sequences and molecule graphs. Second, they mainly rely on contrastive learning and adversarial training for cross-modality alignment, both of which mainly focus on the first-order similarity, ignoring the second-order similarity that can capture more structural information in the embedding space. To address these issues, we propose a novel cross-modal text-molecule retrieval model with two-fold improvements. Specifically, on the top of two modality-specific encoders, we stack a memory bank based feature projector that contain learnable memory vectors to extract modality-shared features better. More importantly, during the model training, we calculate four kinds of similarity distributions (text-to-text, text-to-molecule, molecule-to-molecule, and molecule-to-text similarity distributions) for each instance, and then minimize the distance between these similarity distributions (namely second-order similarity losses) to enhance cross-modal alignment. Experimental results and analysis strongly demonstrate the effectiveness of our model. Particularly, our model achieves SOTA performance, outperforming the previously-reported best result by 6.4%.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Information Retrieval

Died the same way β€” πŸ‘» Ghosted