构建嗅觉多模态对齐模型，让分子、受体与语言描述在特征空间中精准对应。
NOSE: Neural Olfactory-Semantic Embedding with Tri-Modal Orthogonal Contrastive Learning
- 通过正交约束解耦分子、受体与语言三模态信息，避免混淆
- 在稀疏嗅觉语料下仍实现最优零样本泛化性能
- 适合气味生成、跨模态检索等应用研究者参考
嗅觉涉及化学结构、神经编码和语言感知的交叉，但现有表征方法未能完整捕捉这一路径。当前方法通常仅建模嗅觉通路中的孤立片段，忽略了从分子到受体再到语言描述的完整链条，导致学习到的嵌入缺乏生物依据和语义可解释性。我们提出NOSE（Neural Olfactory-Semantic Embedding），一个将分子结构、受体序列和自然语言描述沿嗅觉通路对齐的表示学习框架。不同于简单融合信号，我们通过正交约束解耦各模态贡献，保留各自独特信息。为应对嗅觉语言数据稀疏问题，引入弱正样本策略校准语义相似度，防止特征空间中相似气味被错误排斥。大量实验表明，NOSE达到最先进（SOTA）性能并具备出色的零样本泛化能力，证实其表示空间与人类嗅觉直觉高度一致。代码与数据见https://github.com/Xianyusyy/NOSE。
原文摘要 · Abstract (English)
Olfaction lies at the intersection of chemical structure, neural encoding, and linguistic perception, yet existing representation methods fail to fully capture this pathway. Current approaches typically model only isolated segments of the olfactory pathway, overlooking the complete chain from molecule to receptors to linguistic descriptions. Such fragmentation yields learned embeddings that lack both biological grounding and semantic interpretability. We propose NOSE (Neural Olfactory-Semantic Embedding), a representation learning framework that aligns three modalities along the olfactory pathway: molecular structure, receptor sequence, and natural language description. Rather than simply fusing these signals, we decouple their contributions via orthogonal constraints, preserving the unique encoded information of each modality. To address the sparsity of olfactory language, we introduce a weak positive sample strategy to calibrate semantic similarity, preventing erroneous repulsion of similar odors in the feature space. Extensive experiments demonstrate that NOSE achieves state-of-the-art (SOTA) performance and excellent zero-shot generalization, confirming the strong alignment between its representation space and human olfactory intuition.Code and data are available at https://github.com/Xianyusyy/NOSE
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。