Deep learning for inferring cause of data anomalies
This provides a tool for data quality monitoring in large-scale experiments like CMS, assisting managers in cross-checking and identifying good channels in anomalous samples, though it is incremental as it adapts deep learning to a specific domain problem.
The paper tackles the problem of identifying specific sub-detector channels causing data anomalies in large-scale experiments, introducing a deep learning model that learns to identify affected channels using only a global anomaly flag without per-channel labels, and demonstrates its ability to decompose anomalies by separate channels on CMS data from 2010.
Daily operation of a large-scale experiment is a resource consuming task, particularly from perspectives of routine data quality monitoring. Typically, data comes from different sub-detectors and the global quality of data depends on the combinatorial performance of each of them. In this paper, the problem of identifying channels in which anomalies occurred is considered. We introduce a generic deep learning model and prove that, under reasonable assumptions, the model learns to identify 'channels' which are affected by an anomaly. Such model could be used for data quality manager cross-check and assistance and identifying good channels in anomalous data samples. The main novelty of the method is that the model does not require ground truth labels for each channel, only global flag is used. This effectively distinguishes the model from classical classification methods. Being applied to CMS data collected in the year 2010, this approach proves its ability to decompose anomaly by separate channels.