Fixes That Fail: Self-Defeating Improvements in Machine-Learning Systems
This addresses a critical problem for developers of complex ML systems like self-driving cars, highlighting an incremental but important issue in system-level optimization.
The paper investigates whether improving individual machine-learning models can degrade overall system performance, finding that such self-defeating improvements occur due to model entanglement, as demonstrated in a stereo-based detection system for cars and pedestrians.
Machine-learning systems such as self-driving cars or virtual assistants are composed of a large number of machine-learning models that recognize image content, transcribe speech, analyze natural language, infer preferences, rank options, etc. Models in these systems are often developed and trained independently, which raises an obvious concern: Can improving a machine-learning model make the overall system worse? We answer this question affirmatively by showing that improving a model can deteriorate the performance of downstream models, even after those downstream models are retrained. Such self-defeating improvements are the result of entanglement between the models in the system. We perform an error decomposition of systems with multiple machine-learning models, which sheds light on the types of errors that can lead to self-defeating improvements. We also present the results of experiments which show that self-defeating improvements emerge in a realistic stereo-based detection system for cars and pedestrians.