Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Mitigating Propagation Failures in Physics-informed Neural Networks using Retain-Resample-Release (R3) Sampling

About

Despite the success of physics-informed neural networks (PINNs) in approximating partial differential equations (PDEs), PINNs can sometimes fail to converge to the correct solution in problems involving complicated PDEs. This is reflected in several recent studies on characterizing the "failure modes" of PINNs, although a thorough understanding of the connection between PINN failure modes and sampling strategies is missing. In this paper, we provide a novel perspective of failure modes of PINNs by hypothesizing that training PINNs relies on successful "propagation" of solution from initial and/or boundary condition points to interior points. We show that PINNs with poor sampling strategies can get stuck at trivial solutions if there are propagation failures, characterized by highly imbalanced PDE residual fields. To mitigate propagation failures, we propose a novel Retain-Resample-Release sampling (R3) algorithm that can incrementally accumulate collocation points in regions of high PDE residuals with little to no computational overhead. We provide an extension of R3 sampling to respect the principle of causality while solving time-dependent PDEs. We theoretically analyze the behavior of R3 sampling and empirically demonstrate its efficacy and efficiency in comparison with baselines on a variety of PDE problems.

Arka Daw, Jie Bu, Sifan Wang, Paris Perdikaris, Anuj Karpatne• 2022

Related benchmarks

TaskDatasetResultRank
PDE solvingKlein-Gordon equation
Relative L2 Error1.5
31
Forward PDE solvingHelmholtz
Relative Error0.0267
26
Forward PDE solvingForward benchmarks 5 PDEs
P(A<B)100
21
Forward PDE problem solvingBurgers
Relative L2 Error0.0046
19
Forward PDE solvingAllen–Cahn 10K-epoch
Relative L2 Error1.6
16
Forward PDE solvingHelmholtz 10K-epoch
Relative L2 Error1.4
16
Forward PDE solvingKlein-Gordon 10K-epoch
Relative L2 Error2.5
16
Forward PDE solvingBurgers 10K-epoch
Relative L2 Error4.7
16
Forward PDE solvingConv-Diff 10K-epoch
Relative L2 Error3.55
16
Solving coupled thermoelastic PDEsNatural coupled thermoelastic K = 4 1.0 (val)
L2 Error1.04
10
Showing 10 of 43 rows

Other info

Follow for update