Galaxy interaction classification remains challenging due to complex morphological patterns and the limited interpretability of deep learning models. We propose an attentive neural ensemble that combines AG-XCaps, H-SNN, and ResNet-GRU architectures, trained on the Galaxy Zoo DESI dataset and enhanced with LIME to enable explainable predictions. The model achieves Precision = 0.95, Recall = 1.00, F1 = 0.97, and Accuracy = 96%, outperforming a Random Forest baseline by significantly reducing false positives (23 vs. 70). This lightweight (0.45 MB) and scalable framework provides an interpretable and efficient solution for large-scale surveys such as Euclid and LSST, advancing data-driven studies of galaxy evolution.
@article{arxiv.2601.08872,
title = {Explainable Galaxy Interaction Prediction with Hybrid Attention Mechanisms},
author = {Sathwik Narkedimilli and Satvik Raghav and Om Mishra and Mohan Kumar and Aswath Babu H and Tereza Jerabkova and Manish M and Sai Prashanth Mallellu},
journal= {arXiv preprint arXiv:2601.08872},
year = {2026}
}