MAGNETS learns unsupervised, mask-based concepts to make time-series regression predictions additively interpretable, recovering ground-truth temporal rules on synthetic tasks and beating interpretable baselines on most real datasets.
Interpretable Detection of Partial Discharge in Power Lines with Deep Learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
When, How Long and How Much? Interpretable Neural Networks for Time Series Regression by Learning to Mask and Aggregate
MAGNETS learns unsupervised, mask-based concepts to make time-series regression predictions additively interpretable, recovering ground-truth temporal rules on synthetic tasks and beating interpretable baselines on most real datasets.