← 研踪 PaperTrailarXiv:2611.19650 · v1
With the Right Representation, Classical Machine Learning Rivals Deep Models for Olfactory Mixture Similarity
首次提交 2026-11-15 06:42
版本更新 2026-11-15 06:42
雷达观测 2026-11-17 12:06
摘要
Modeling olfactory mixtures remains a critical challenge in machine olfaction because the task requires reasoning over relationships between sets of odorants rather than over individual molecules in isolation. However, prior comparisons between deep and classical approaches also varied how the relationship between the two mixtures was represented, since the classical baselines primarily relied on weak representations that described each mixture independently and provided little direct signal about how the mixtures differed. In this work, we revisit classical learning using explicit symmetric comparison features on unordered pairs of mixtures, evaluating these representations with XGBoost and kernel ridge regression (KRR). We find that XGBoost with explicit comparison features achieves performance competitive with specialized deep mixture models on the main benchmark. Ablation studies show that coordinate-wise absolute differences alone provide strong predictive performance, while combining them with sums and products yields further improvements. KRR also benefits substantially from explicit comparison features, with further gains from appropriate kernel choice and preprocessing. Overall, these results suggest that explicitly encoding how two mixtures differ is an important ingredient for classical machine learning in low-data olfactory mixture prediction.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-15 06:42 · 最新观测版本
With the Right Representation, Classical Machine Learning Rivals Deep Models for Olfactory Mixture Similarity
Modeling olfactory mixtures remains a critical challenge in machine olfaction because the task requires reasoning over relationships between sets of odorants rather than over individual molecules in isolation. However, prior comparisons between deep and classical approaches also varied how the relationship between the two mixtures was represented, since the classical baselines primarily relied on weak representations that described each mixture independently and provided little direct signal about how the mixtures differed. In this work, we revisit classical learning using explicit symmetric comparison features on unordered pairs of mixtures, evaluating these representations with XGBoost and kernel ridge regression (KRR). We find that XGBoost with explicit comparison features achieves performance competitive with specialized deep mixture models on the main benchmark. Ablation studies show that coordinate-wise absolute differences alone provide strong predictive performance, while combining them with sums and products yields further improvements. KRR also benefits substantially from explicit comparison features, with further gains from appropriate kernel choice and preprocessing. Overall, these results suggest that explicitly encoding how two mixtures differ is an important ingredient for classical machine learning in low-data olfactory mixture prediction.
查看此版本解读 →查看此版本原文 ↗