归因方法可以告诉我们关于化学语言模型的什么?
Stefan Hödl1, Tal Kachman2, Yoram Bachrach3
1Physical Organic Chemistry, Radboud University Heyendaalseweg 135 6525AJ Nijmegen The Netherlands william.robinson@ru.nl.
概括
这项研究探讨了化学语言模型中的可解释性,用于预测分子性质. 结果显示,虽然SHAP提供了洞察力,但变压器特定的方法更好地反映了模型的内部分子表示.
科学领域:
- 计算化学的计算化学
- 机器学习 机器学习
- 化学信息学 化学信息学
背景情况:
- 语言模型擅长分子串预测,但缺乏用于实际应用的可解释性.
- 可解释性对于理解化学模型预测背后的理由至关重要.
研究的目的:
- 研究化学语言模型的可解释性技术.
- 适应和比较变压器特定和模型不可知输入归因方法.
- 分析模型表示来预测水溶性.
主要方法:
- 微调一个预训练的语言模型用于水溶性预测.
- 调整SHAP (夏普利添加式扩展) 和输入归因的变压器特定技术.
- 在不同的模型变体中评估和可视化归因的相关性.
主要成果:
- SHAP的归因突出了个别的负电子原子,而不是功能组.
- 变压器特定的归属是稀疏的,并映射到模型的潜在空间,表明分子相似性特征.
- 两种方法都没有直接解释基于可溶性相关的功能组的预测.
结论:
- 化学语言模型可能代表分子相似性,而不是在潜在空间中的明确功能组.
- 了解这些内部表示是开发更准确和可解释的化学AI的关键.
- 利用这些见解可以为设计更好的化学空间提供信息,以进行先进的模型培训.
相关概念视频
Molecular Models
38.0K
Physical models representing molecular architectures of chemical compounds play essential roles in understanding chemistry. The use of molecular models makes it easier to visualize the structures and shapes of atoms and molecules.
38.0K
Attribution Theory
12.9K
Behavior is a product of both the situation (e.g., cultural influences, social roles, and the presence of bystanders) and of the person (e.g., personality characteristics). Subfields of psychology tend to focus on one influence or behavior over others. Situationism is the view that our behavior and actions are determined by our immediate environment and surroundings. In contrast, dispositionism holds that our behavior is determined by internal factors (Heider, 1958).
12.9K
Mechanistic Models: Compartment Models in Individual and Population Analysis
33
Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least...
33
Fundamental Attribution Error
12.8K
According to some social psychologists, people tend to overemphasize internal factors as explanations—or attributions—for the behavior of other people. They tend to assume that the behavior of another person is a trait of that person, and to underestimate the power of the situation on the behavior of others. They tend to fail to recognize when the behavior of another is due to situational variables, and thus to the person’s state. This erroneous assumption is...
12.8K
Inductive Effects on Chemical Shift: Overview
1.1K
The protons in unsubstituted alkanes are strongly shielded with chemical shifts below 1.8 ppm. Methine, methylene, and methyl protons appear at approximately 1.7, 1.2 and 0.7 ppm, while the proton signal from methane appears at 0.23 ppm. An electronegative substituent, such as chlorine, withdraws the electron density from the protons, increasing their chemical shift. Progressive substitution of the hydrogens in methane by chlorine shifts the proton signals increasingly downfield, to 3.05 ppm in...
1.1K
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
45
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
45


