Pith. sign in

REVIEW 6 cited by

ConFIG: Towards Conflict-free Training of Physics Informed Neural Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2408.11104 v3 pith:6ZWVANJ7 submitted 2024-08-20 cs.LG

classification cs.LG
keywords configlossmethodtermschallengingconflict-freegradienthighly
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

The loss functions of many learning problems contain multiple additive terms that can disagree and yield conflicting update directions. For Physics-Informed Neural Networks (PINNs), loss terms on initial/boundary conditions and physics equations are particularly interesting as they are well-established as highly difficult tasks. To improve learning the challenging multi-objective task posed by PINNs, we propose the ConFIG method, which provides conflict-free updates by ensuring a positive dot product between the final update and each loss-specific gradient. It also maintains consistent optimization rates for all loss terms and dynamically adjusts gradient magnitudes based on conflict levels. We additionally leverage momentum to accelerate optimizations by alternating the back-propagation of different loss terms. We provide a mathematical proof showing the convergence of the ConFIG method, and it is evaluated across a range of challenging PINN scenarios. ConFIG consistently shows superior performance and runtime compared to baseline methods. We also test the proposed method in a classic multi-task benchmark, where the ConFIG method likewise exhibits a highly promising performance. Source code is available at https://tum-pbs.github.io/ConFIG

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Lantern: Conflict-Aware Gradient Blending for Physics-Guided Diffusion Models in Calorimeter Simulation

    cs.LG 2026-07 conditional novelty 6.5 of 10

    GradBlend anchors diffusion updates to denoising while admitting physics auxiliaries, improving calorimeter shower FPD and CFD where PCGrad, GradNorm, IMTL-G, and ConFIG inflate FPD by 2–100×.

  2. Finite basis physics-informed neural networks with hard constraints for viscous fluid flow in highly perforated domains

    physics.flu-dyn 2026-08 conditional novelty 6.0 of 10

    Combining finite basis PINNs with hard boundary constraints keeps Stokes-flow errors near one percent as the number of perforations grows to 100.

  3. KKANs: Kurkova-Kolmogorov-Arnold Networks and Their Learning Dynamics

    cs.LG 2024-12 conditional novelty 6.0 of 10

    KKANs, a two-block KART-based architecture with MLP inner functions and basis-function outer functions, universally approximate continuous functions and empirically outperform MLP and cKAN baselines in regression, PIN...

  4. Fitting Coarse-Grained Models to Macroscopic Experimental Data via Automatic Differentiation

    physics.bio-ph 2024-11 conditional novelty 6.0 of 10

    Trajectory reweighting and implicit differentiation are combined to fit coarse-grained DNA, RNA, and DNA-protein models to structural, mechanical, and thermodynamic experimental targets in a single gradient-based framework.

  5. Sobolev Training of End-to-End Optimization Proxies

    cs.LG 2025-05 conditional novelty 5.0 of 10

    Adding solver sensitivity information to the training loss of optimization proxies reduces prediction error and constraint violations on AC-OPF benchmarks and improves self-supervised portfolio proxies in the medium-r...

  6. Mask-PINNs: Mitigating Internal Covariate Shift in Physics-Informed Neural Networks

    cs.LG 2025-05 conditional novelty 5.0 of 10

    A learnable mask F(z)=1-exp(-α²z²), applied pointwise before activation, improves PINN accuracy and stability on several PDE benchmarks and activation functions.

Pith tools