Improving Generalizability of ML-enabled Software through Domain Specification
Improving Generalizability of ML-enabled Software through Domain Specification
复制标题
DOI：
10.1145/3522664.3528589
复制
发表时间：
2022-05
期刊：
影响因子：
--
通讯作者：
H. Barzamini;Mona Rahimi;Murteza Shahzad;Hamed Alhoori
中科院分区：
文献类型：
--
作者：
H. Barzamini;Mona Rahimi;Murteza Shahzad;Hamed Alhoori
传统的软件组件实现了预定义的规格，但机器学习（ML）的软件组件（MLSC）从培训样本中学习域规范，MLSC的数据驱动和归纳推理变得非常可靠。培训数据集通常是按临时举止收集的。感知任务理解环境是准确预测的重要因素。要填补目标域概念的概念化与MLSC数据集中的可视化之间的差距，我们建议利用该概念的语义规范以识别概念中缺少的变体我们首先，语义上指定了特定于特定的目标域的概念，其次是指派生的规格，以评估收集的MLSC的多样性和相对完整性。域名，提高了任意收集的数据集的质量，并可能产生更可靠的模型，我们会自动获取现有的语义知识，以指定汽车域概念“增强行人”。因此，评估表明，语义增强在满足MLSC准确性要求中的蛮力机器的概念•软件及其工程→需求分析；
While the conventional software components implement pre-defined specifications, Machine Learning (ML)-enabled Software Components (MLSC) learn the domain specifications from the training samples. Thus, the MLSC’s data-driven and inductive reasoning becomes highly reliant on the quality of the training dataset, which are often arbitrarily collected in ad hoc manners. The random collection of samples leads to a significant gap between the actual specifications of a real-world concept, and the picture that a dataset represents of the concept, reducing MLSC generalizability, particularly in perceptual tasks where understanding the environment is an important factor of accurate prediction.To fill the gap between the conceptualization of a targeted domain’s concept and its visualization in the MLSC dataset, we propose exploiting semantic specification of the concept to identify the concepts’ missing variants in the data. We first, semantically specify hard-to-specify targeted domain’s concepts and second, refer to the derived specifications to evaluate the diversity and relative completeness of MLSC collected datasets. The systematic augmentation of training datasets, with respect to the semantics of the domain, improves the quality of an arbitrarily collected dataset and potentially yields more reliable models. As a proof of concept, we automatically acquired the existing semantic knowledge for specifying the automotive domain concept “pedestrian.” Augmenting the state-of-the-art pedestrian datasets accordingly, the evaluations showed that semantic augmentation outperforms brute-force machine learning in satisfying the MLSC accuracy requirements.CCS CONCEPTS• Software and its engineering → Requirements analysis; Software reliability; • Computing methodologies → Object detection; Semantic networks.