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

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

31 Oct 2024arXiv:2410.23715archive 2025-07-28

Jia Song, Wanru Zhuang, Yujie Lin, Liang Zhang, Chunyan Li, Jinsong Su, Song He, Xiaochen Bo

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%.

PaperPDFCode

Code

DeepLearnXMU/CMTMR officialpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Contrastive LearningCross-Modal RetrievalDrug DesignRetrievalcross-modal alignmenttext similarity

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Cross-Modal Retrieval ChEBI-20 Song et al. Hits@1 56.5 #3 of 9 Archive leaderboard report
Cross-Modal Retrieval ChEBI-20 Song et al. Hits@10 94.1 #3 of 9 Archive leaderboard report
Cross-Modal Retrieval ChEBI-20 Song et al. Mean Rank 12.66 #3 of 9 Archive leaderboard report
Cross-Modal Retrieval ChEBI-20 Song et al. Test MRR 70.2 #3 of 9 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Contrastive LearningFocus

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections