Domain Adaptation via Minimax Entropy for Real/Bogus Classification of Astronomical Alerts

TL;DR

This paper explores domain adaptation techniques, including fine tuning and minimax entropy, to improve real/bogus classification of astronomical alerts across multiple datasets with minimal labeled data.

Contribution

It introduces the use of minimax entropy for semi-supervised domain adaptation in astronomical alert classification, demonstrating significant accuracy improvements.

Findings

Both fine tuning and MME significantly improve accuracy with minimal labeled data.

MME maintains performance on source datasets while adapting to target datasets.

Few labeled examples per class are sufficient for effective domain adaptation.

Abstract

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.