DIF learns and isolates the environment-independent function of a dynamical system from multi-environment trajectories using a causal graph, a hypernetwork, and an adversarial independence constraint.
Scaling up to PDEs also introduces different training dynamics, which may necessitate additional techniques to stabilize and accelerate training
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
-
Discovering Physics Laws of Dynamical Systems via Invariant Function Learning
DIF learns and isolates the environment-independent function of a dynamical system from multi-environment trajectories using a causal graph, a hypernetwork, and an adversarial independence constraint.