- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes PINN-ffusion, a physics-informed neural network framework that combines adaptive collocation sampling with anisotropic domain decomposition. Building on PINN-ball, it replaces adversarial sampling with heat-flow smoothing of a residual-informed density and generates collocation points via a probability-flow ODE. It further introduces ellipsoidal subdomains whose geometry is determined by sample covariance and residual-gradient information, allowing local subnetworks to adapt to directional solution structures.
Critical strengths
-
Both proposed modifications are motivated by clear, targeted objectives. The diffusion-based sampling mechanism is designed to enhance sampling stability, while the ellipsoidal subdomain strategy enables local subnetworks to better model solution structures with pronounced directional patterns.
-
The experimental setup delivers rigorous supporting evidence. With matched optimizers and iteration budgets for both PINN-ball and PINN-ffusion, ablation studies confirm the additive contribution of each component.
Critical weaknesses
-
Training stability needs more direct tests as the number of subdomains increases. Table 7 reports results across initializations, and Figure 4 shows training curves for Burgers. However, these tests do not show whether diffusion reduces the training oscillations observed in PINN-ball when more balls are used. Please compare both methods across several subdomain counts and random seeds. Training curves, measures of oscillation, and failure rates would better support the stability claim. The PINN-ball baseline should use a well-tuned learning-rate schedule.
-
The paper tests five PDE benchmarks, including coupled systems and cylinder flow, but the tests remain limited to low-dimensional settings. More demanding cases, such as coupled multiphysics problems, would help assess its wider use. A comparison with a suitable classical numerical solver is also missing. Comparing runtime and memory use at a common accuracy target would help show when the proposed method offers a practical benefit.
Questions for authors
-
Eq. (13) keeps the metric bounded and handles S=0. However, how does the method handle a very small, noisy S? Is there a threshold or smoothing rule to avoid unnecessary geometry changes near convergence?
-
Appendix F.2 states that anisotropic scaling is constrained to avoid unstable training. What exact constraints are used for axis ratios, subdomain sizes, and overlap? How do these rules maintain domain coverage and control the derivatives of the partition weights?
7 comments
Response to Reviewer XCup (2/5)
(W2) Scope of application and comparison with a classical numerical solver.
We thank the reviewer for this valid point. We have strengthened the manuscript in two respects.
First, we have clarified the scope of the method. Our method aims at the stable training of low-regularity solutions of low- to moderate-dimensional spatiotemporal PDEs, which is the common setting of PINN research employing adaptive sampling and domain decomposition. Domain-decomposition PINNs were proposed to handle large domains and multi-scale solutions [1, 2], and adaptive sampling likewise targets low-dimensional, low-regularity problems. The authors of AAS [3] note that the difficulty of high-dimensional problems shares similarities with that of low-dimensional problems of low regularity and adopt a two-dimensional peak problem as their central example, and PINN Balls [4], the direct predecessor that combines the two components, addresses the memory cost of second-order optimizers with experiments that all have at most three inputs. In contrast, high-dimensional PDEs are approached with fundamentally different techniques, such as stochastic dimension gradient descent (SDGD) [5]. Moreover, even in recent work, higher-dimensional problems and multiphysics are treated as separate problems that require sequential training over time slices [6] or dedicated architectures that handle the disparity of gradient scales across fields [7]. This supporting evidence is summarized in Appendix G.3 of the revised manuscript.
The current benchmarks already include a coupled system (Boussinesq–Burger) and a flow around a complex geometry (Navier–Stokes around a cylinder). Since extending the method to -dimensional problems and strongly coupled multiphysics would require mesh-free smoothing as well as field-wise sampling and decomposition, we have stated this extension as future work in Section 6 (Limitations) and Appendix G.3 of the revised manuscript.
Second, we have compared our method with a classical numerical solver. On Burgers, we compare with a recent high-order compact finite-difference (FD) scheme [8]. We implemented this scheme (fourth-order backward differentiation (BDF4) in time, fourth-order Padé and compact differences in space, and an extrapolation-based linearization of the nonlinear term) in one spatial dimension and measured the relative error, run time, and peak memory under grid refinement. The FD error is computed against the exact solution obtained by the Cole–Hopf transformation. This comparison has been added to Appendix G.13 of the revised manuscript (Table 19).
Table 19. Comparison of PINN-ffusion and a classical FD solver on Burgers
| Method | Setting | Rel. L2 error | Time | Peak memory | Hardware |
|---|---|---|---|---|---|
| PINN-ffusion | 5 subdomains, 2,000 epochs | 4.62e-4 | 36.5 s/epoch | 36 GB | GPU (RTX A6000 Ada) |
| FD [8] (matched accuracy) | 510 intervals, | 3.14e-4 | 0.071 s | 0.31 MB | 1 CPU core |
| FD [8] (best accuracy) | 4,080 intervals, | 5.72e-8 | 1.53 s | 1.10 MB | 1 CPU core |
FD reaches the accuracy of PINN-ffusion in 0.07 s with 0.31 MB of memory and reduces the error to within 1.5 s. Consistent with recent systematic comparisons [9, 10], classical solvers are considerably faster and more accurate for forward problems with known solutions.
Response to Reviewer XCup (3/5)
(W2, continued)
However, the motivation of PINN research lies not in replacing classical solvers for such forward problems but in addressing problems that are difficult for classical solvers. Examples include inverse problems and data assimilation, in which unknown coefficients or initial conditions are estimated from sparse and noisy observations; parametric problems and surrogate modeling, which would otherwise require a new solve for every parameter value; and problems on geometries for which mesh generation is difficult, as well as high-dimensional problems. PINNs are well suited to these problems because they combine observational data and governing equations in a single loss and can learn the unknowns jointly through automatic differentiation.
For PINNs to be used in these settings, however, they must first be trained stably and accurately on forward problems with known solutions. Current PINNs frequently exhibit unstable training or failure for solutions with shocks, thin layers, or directional structures, which explains the active research on improving PINN training through adaptive sampling, domain decomposition, and second-order optimizers. Since our benchmarks are designed to measure precisely this training capability against reference solutions, we have clarified in Section 1 (Introduction) and Appendix G.13 of the revised manuscript that our contribution is an improvement in the accuracy and stability of PINN training. In addition, we have stated in Section 6 (Limitations) that applying the improved training to inverse and parametric problems is left for future work.
References
[1] Finite Basis Physics-Informed Neural Networks (FBPINNs): A Scalable Domain Decomposition Approach for Solving Differential Equations (Ben Moseley et al., 2023)
[2] Multilevel Domain Decomposition-based Architectures for Physics-informed Neural Networks (Victorita Dolean et al., 2024)
[3] Adversarial Adaptive Sampling: Unify PINN and Optimal Transport for the Approximation of PDEs (Kejun Tang et al., 2024)
[4] PINN Balls: Scaling Second-Order Methods for PINNs with Domain Decomposition and Adaptive Sampling (Andrea Bonfanti et al., 2025)
[5] Tackling the Curse of Dimensionality with Physics-Informed Neural Networks (Zheyuan Hu et al., 2024)
[6] Time-slices Based Training of Physics-Informed Neural Networks for 3D Non-Stationary Thermal Inversion Simulations (Maciej Sikora and Maciej Paszyński, 2026)
[7] LSTM-PINN for Steady-State Electrothermal Transport: Preserving Multi-Field Consistency in Strongly Coupled Heat and Fluid Flow (Yuqing Zhou et al., 2026)
[8] A New High-order Compact Numerical Method for the Two-dimensional Nonlinear Burgers' Equation (Shengdi Wang et al., 2026)
[9] Can Physics-Informed Neural Networks Beat the Finite Element Method? (Tamara G. Grossmann et al., 2024)
[10] Weak Baselines and Reporting Biases Lead to Overoptimism in Machine Learning for Fluid-related Partial Differential Equations (Nick McGreivy and Ammar Hakim, 2024)
Response to Reviewer XCup (1/5)
We feel grateful for the constructive reviews. We provide responses to the reviews as well as supporting experimental results below. Also, we uploaded the revised manuscript by highlighting our changes in colored fonts. All section, equation, table, and figure numbers below refer to the revised manuscript, in which revised and newly added parts are marked in red. References [1]–[10] are listed at the end of Part 3/5.
(W1) Training stability with respect to the number of subdomains.
We thank the reviewer for the concrete experimental design. Following the suggestion, we have added the comparison to Appendix G.12 of the revised manuscript with the following setup. On Burgers, we vary the number of subdomains as K∈{4,8,16} and repeat each configuration with five random seeds, using the same optimizer and number of iterations for both methods. The learning-rate schedule of PINN-ball (initial value and exponential decay rate) was selected from a grid of three values based on the validation error at K=8 and used for all K, and the same tuning budget was applied to PINN-ffusion.
As the evaluation metric, we report the mean and standard deviation of the relative L2 error (Rel. L2) over the five seeds. The results are reported in Table 18, and the training curves are shown in Fig. 13 (Appendix G.12).
Table 18. Training stability on Burgers with respect to the number of subdomains (five seeds)
For all values of K, the mean error and standard deviation of PINN-ffusion are smaller than those of PINN-ball, and the difference widens as K increases. For PINN-ball, increasing K from 4 to 16 causes the mean error to increase from 7.9×10−4 to 1.2×10−3, and the standard deviation to increase from 1.6×10−4 to 1.1×10−2, a rise of approximately 70 times. In contrast, for PINN-ffusion, the mean error does not increase even as K increases (from 5.4×10−4 to 3.7×10−4), and the standard deviation remains at or below 7.8×10−5 for all values of K. As shown in the learning curve (Fig. 13), PINN-ball exhibits increased oscillations as K increases, whereas PINN-ffusion converges stably for all values of K. In other words, the oscillations and deviations from the seed that increase in PINN-ball when the number of subdomains is increased are significantly reduced in diffusion sampling. This result is consistent with a design that uses a smoothing density without trainable parameters, rather than a trainable adversarial sampler.