Regularization strategies for interpretable deep models and robust explanations with application to genomics

在已经训练好的机器学习模型中实现透明度的一个流行概念是通过归因进行解释。其目的是解释哪些输入维度对模型得出单个样本的预测最重要。这样的解释可以被可视化并提供给人类用户用于验证和解释。虽然在许多应用中成功使用，但分配给每个输入变量的相关性得分仅传达有限的信息，并且还可能受到各种类型的噪声的影响，使其不足以深入了解数据中的复杂关系和模型的功能。此外，解释可能是正确的，但直观上是人类无法理解的，因此用途有限，例如，这个项目的目标是开发新的方法，使解释更强大和可读的人类专家。我们将讨论模型的影响和解释方法本身。首先，我们将研究指导模型训练的不同参数的影响，以及使用模型正则化技术来改善对理想属性（如（组）稀疏性或鲁棒性）的解释。接下来，我们将直接比较并建议改进当前可解释的AI技术，例如，使用稳健统计学的方法。我们将开发解释的后处理方法，通过有助于提高解释的质量和信息内容或提供人口信息的技术，使人类专家更具可读性。在另一个研究方向，我们将不确定性与解释联系起来，以改善后者。特别是，我们将重新考虑目前的确定性形式的解释预测和联合收割机的不确定性和解释的概念，以产生解释分布，显示整个范围的不同策略，以达到prediction.Our兴趣和应用程序在于在分子序列数据，特别是识别和理解序列模式，通过不同的基因调控机制影响基因表达。这里，特征的（冗余）组合可能导致观察到的效果。虽然一个单一的解释只涉及一部分潜在的生物学，但一个解释分布提供了全貌。总之，通过开发新的正则化技术和全局解释方法，我们希望该项目能够提供新的技术，从而获得更强大和完整的解释，以及对模型预测策略的人性化见解。

One of the prevailing concepts to achieve transparency in already trained machine learning models is explanation through attribution. Its aim is to explain which input dimensions have been most important for the model to arrive at its prediction for an individual sample. Such explanations can be visualized and provided to the human user for verification and interpretation. While successfully used in many applications, relevance scores assigned to each input variable convey only limited information and may also be affected by various types of noise, rendering them insufficient to gain deeper insights into the complex relations in the data and the functioning of the model. Additionally, explanations may be correct, but be intuitively not understandable to humans and as such of limited use, e.g., when the model operates on an input domain which does not correspond to human sensory input.The goal of this project is to develop novel methods for making explanations more robust and readable for the human expert. We will address both the impact of the model and the explanation method itself. First we will investigate the effect of different parameters guiding the model training as well as the use of model regularization techniques for improving explanations with respect to desirable properties such as (group) sparsity or robustness. Next, we will directly compare and suggest improvements for current explainable AI techniques, e.g., using methods from robust statistics. We will develop post-processing methods for explanations, making them more readable for the human expert, via techniques which help improve the quality and information content of explanations, or which will provide information on the population. In another research direction, we will connect uncertainty with explanation in order to improve the latter. In particular, we will reconsider the current deterministic form of explaining predictions and combine the concept of uncertainty and explanation in order to generate explanation distributions, showing the whole range of different strategies to arrive at a prediction.Our interest and application lies in molecular sequence data, specifically to identify and understand sequence patterns that influence gene expression via different mechanisms of gene regulation. Here, (redundant) combinations of features may lead to an observed effect. While a single explanation would only relate to a part of the underlying biology, an explanation distribution provides the full picture. In summary, by developing novel regularization techniques and global interpretation methods, we expect this project to provide new techniques that lead to more robust and complete explanations, as well as to humanly accessible insights into the model's prediction strategies.