Manifold for Machine Learning Assurance
This addresses the need for quality assurance in ML systems used for critical tasks, representing a novel method for a known bottleneck rather than a foundational breakthrough.
The paper tackles the problem of verifying and validating machine learning systems in critical applications by proposing a manifold-based approach using variational autoencoders to extract low-dimensional structures from training data. Preliminary experiments show this approach drives test diversity, generates realistic fault-revealing test cases, and provides runtime monitoring for trust assessment.
The increasing use of machine-learning (ML) enabled systems in critical tasks fuels the quest for novel verification and validation techniques yet grounded in accepted system assurance principles. In traditional system development, model-based techniques have been widely adopted, where the central premise is that abstract models of the required system provide a sound basis for judging its implementation. We posit an analogous approach for ML systems using an ML technique that extracts from the high-dimensional training data implicitly describing the required system, a low-dimensional underlying structure--a manifold. It is then harnessed for a range of quality assurance tasks such as test adequacy measurement, test input generation, and runtime monitoring of the target ML system. The approach is built on variational autoencoder, an unsupervised method for learning a pair of mutually near-inverse functions between a given high-dimensional dataset and a low-dimensional representation. Preliminary experiments establish that the proposed manifold-based approach, for test adequacy drives diversity in test data, for test generation yields fault-revealing yet realistic test cases, and for runtime monitoring provides an independent means to assess trustability of the target system's output.