Bi-HYCO: Bi-Objective Cooperative Learning for PDE Parameter Identification under Fragmented Observations
This work proposes Bi-Objective HYCO (Bi-HYCO), a cooperative framework that retains both representations and their local observational objectives while coupling their predicted states at unlabeled interaction points, and shows that removing state interaction while retaining aggregation deteriorates parameter recovery...
Umberto Biccari, Jun Chen, Roberto Morales et al.
· 0 citations