cs.CVNov 3, 2026

SWAP-INR: Implicit Neural Representation with Switchable Attention Paths for Time-varying Multivariate Scientific Data Compression

Authors: Hyunsoo Son, Jeonghyun Noh, Chaoli Wang, Won-Ki Jeong

Organizations: Korea University · University of Notre Dame

Abstract

Visualizing multivariate scientific simulation data is essential for understanding complex physical phenomena, yet the massive scale of such data imposes a severe storage bottleneck in high-performance computing environments. Implicit neural representations (INRs) have emerged as a promising continuous alternative to traditional lossy compressors, but existing methods struggle to explicitly capture cross-variable interactions and to adapt to the diverse spectral characteristics of physical variables. To address these limitations, we propose SWAP-INR, an architecture for high-fidelity compression of multivariate, time-varying simulation data. SWAP-INR introduces two key components: (1) The switchable attention path (SWAP) module explicitly models cross-variable interactions through a cross-variable attention layer, then routes each variable to an attention or non-attention path by a deterministic, loss-driven criterion, and prunes the inactive layers for structural compression. (2) The adaptability amplification SIREN (A2-SIREN) replaces rigid frequency scaling with channel-wise learnable modulation, adapting to heterogeneous physical features with negligible overhead. Combined with post-training 16-bit quantization, SWAP-INR achieves state-of-the-art performance on small modular reactor (SMR) datasets and remains competitive on public physics simulation datasets, while maintaining a constrained memory footprint. Our code is https://github.com/hvcl/SWAP-INR.

Figures & tables

Appendix figures & tables16 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. EVOLVE: Efficient Learned Volume Compression with Variable-Rate Encoding on a Cross-Domain Database

    Jul 20, 2026Kaiyuan Tang, Maizhe Yang, Chaoli WangAutoencoders

  2. High-Fidelity Compression of Seismic Velocity Models via SIREN Auto-Decoders

    Mar 15, 2026Caiyun Liu, Xiaoxue Luo, Jie XiongSinusoidal Representation NetworksModel Compression

  3. ANTIC: Adaptive Neural Temporal In-situ Compressor

    Apr 10, 2026Sandeep S. Cranganore, Andrei Bodnar, Gianluca Galletti +2Partial Differential Equations