Drifting Features: Detection and evaluation in the context of automatic RRLs identification in VVV
This addresses data drift issues in astronomy for researchers using ML on large surveys, but it is incremental as it builds on prior work and shows limited impact on the specific task.
The paper tackles the problem of drifting features, which are small changes in data over time or space that can harm machine learning models, by developing a new ML-based method to detect them in astronomical data. The result shows that the method efficiently identifies a reduced set of features related to tile of origin, but removing these features does not improve the identification of RR Lyrae stars in the VVV survey.
As most of the modern astronomical sky surveys produce data faster than humans can analyze it, Machine Learning (ML) has become a central tool in Astronomy. Modern ML methods can be characterized as highly resistant to some experimental errors. However, small changes on the data over long distances or long periods of time, which cannot be easily detected by statistical methods, can be harmful to these methods. We develop a new strategy to cope with this problem, also using ML methods in an innovative way, to identify these potentially harmful features. We introduce and discuss the notion of Drifting Features, related with small changes in the properties as measured in the data features. We use the identification of RRLs in VVV based on an earlier work and introduce a method for detecting Drifting Features. Our method forces a classifier to learn the tile of origin of diverse sources (mostly stellar 'point sources'), and select the features more relevant to the task of finding candidates to Drifting Features. We show that this method can efficiently identify a reduced set of features that contains useful information about the tile of origin of the sources. For our particular example of detecting RRLs in VVV, we find that Drifting Features are mostly related to color indices. On the other hand, we show that, even if we have a clear set of Drifting Features in our problem, they are mostly insensitive to the identification of RRLs. Drifting Features can be efficiently identified using ML methods. However, in our example, removing Drifting Features does not improve the identification of RRLs.