Domain Adaptation via Minimax Entropy for Real/Bogus Classification of Astronomical Alerts
This work addresses domain adaptation for astronomical alert classification, an incremental improvement for time-domain astronomy.
The paper tackled domain shift in real/bogus classification of astronomical alerts across four datasets (HiTS, DES, ATLAS, ZTF) by applying fine-tuning and Minimax Entropy domain adaptation, finding that both methods significantly improved balanced accuracy with as few as one labeled item per class from the target dataset, while MME maintained performance on the source dataset.
Time domain astronomy is advancing towards the analysis of multiple massive datasets in real time, prompting the development of multi-stream machine learning models. In this work, we study Domain Adaptation (DA) for real/bogus classification of astronomical alerts using four different datasets: HiTS, DES, ATLAS, and ZTF. We study the domain shift between these datasets, and improve a naive deep learning classification model by using a fine tuning approach and semi-supervised deep DA via Minimax Entropy (MME). We compare the balanced accuracy of these models for different source-target scenarios. We find that both the fine tuning and MME models improve significantly the base model with as few as one labeled item per class coming from the target dataset, but that the MME does not compromise its performance on the source dataset.