DeepDebugger: An Interactive Time-Travelling Debugging Approach for Deep Classifiers

"A deep classifier is usually trained to (i) learn the numeric representation vector of samples and (ii) classify sample representations with learned classification boundaries. Time-travelling visualization, as an explainable AI technique, is designed to transform the model training dynamics into an animation of canvas with colorful dots and territories. Despite that the training dynamics of the high-level concepts such as sample representations and classification boundaries are now observable, the model developers can still be overwhelmed by tens of thousands of moving dots in hundreds of training epochs (i.e., frames in the animation), which makes them miss important training events such as abnormal movement dynamics (i.e., learning behavior) of certain samples. In this work, we make the first attempt to develop the model time-travelling visualizers to the model time-travelling debuggers, for its practical use in model debugging tasks. Specifically, given an animation of model training dynamics of sample representation and classification landscape, we propose DeepDebugger solution to recommend the samples of user interest in a human-in-the-loop manner. On one hand, DeepDebugger monitors the training dynamics of samples and recommends suspicious samples based on the abnormality of their training dynamics and model prediction. On the other hand, our recommendation is interactive and fault-resilient for the model developers to explore the training process. By learning users’ feedback, DeepDebugger refines its recommendation to fit their intention. Our extensive experiments on applying DeepDebugger on the known time-travelling visualizers show that DeepDebugger can (1) detect the majority of the abnormal movement of the training samples on canvas; (2) significantly boost the recommendation performance of samples of interest (5-10X more accurate than the baselines) with the runtime overhead of 0.015s per feedback; (3) be resilient under the 3%, 5%, 10% mistaken user feedback. Our user study, consisting of 16 participants on two model debugging tasks, shows that the interactive recommendation of DeepDebugger can help the participants accomplish the debugging tasks by saving 18.1% completion time or boosting the performance by 20.3%."