TFT-based transfer learning with probe-only fine-tuning reaches TRI of 3097 on real cross-building energy data from Denmark and Switzerland, with MC dropout achieving 93.2% prediction interval coverage.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Uncertainty-Aware Transfer Learning for Cross-Building Energy Forecasting: Toward Robust and Scalable District-Level Energy Management
TFT-based transfer learning with probe-only fine-tuning reaches TRI of 3097 on real cross-building energy data from Denmark and Switzerland, with MC dropout achieving 93.2% prediction interval coverage.