“…In recent years, machine learning (ML) applications in electronics design automation (EDA) have started to attract wide attention. They have enabled fast estimation on many important metrics for chip design, including timing [2], power [16,42], design rule violation [20,34,39], crosstalk [21], testability [26], lithography hotspots [37,40], clock tree's quality [25], placement solution [27], routing solution [43], and IR drop [10,12,15,23,28,30,35,36]. There have been many ML-based IR drop estimators targeting at various design stages with different emphasis.…”