MC-INR: Efficient Encoding of Multivariate Scientific Simulation Data using Meta-Learning and Clustered Implicit Neural Representations

TL;DR

This paper introduces MC-INR, a novel neural network framework that efficiently encodes complex multivariate scientific data on unstructured grids by combining meta-learning, clustering, and dynamic re-clustering mechanisms.

Contribution

MC-INR is the first method to effectively encode multivariate data on unstructured grids using meta-learning and clustering, addressing limitations of existing INR approaches.

Findings

MC-INR outperforms existing methods in scientific data encoding tasks.

The dynamic re-clustering mechanism improves local error handling.

The branched layer effectively leverages multivariate data.

Abstract

Implicit Neural Representations (INRs) are widely used to encode data as continuous functions, enabling the visualization of large-scale multivariate scientific simulation data with reduced memory usage. However, existing INR-based methods face three main limitations: (1) inflexible representation of complex structures, (2) primarily focusing on single-variable data, and (3) dependence on structured grids. Thus, their performance degrades when applied to complex real-world datasets. To address these limitations, we propose a novel neural network-based framework, MC-INR, which handles multivariate data on unstructured grids. It combines meta-learning and clustering to enable flexible encoding of complex structures. To further improve performance, we introduce a residual-based dynamic re-clustering mechanism that adaptively partitions clusters based on local error. We also propose a branched layer to leverage multivariate data through independent branches simultaneously. Experimental results demonstrate that MC-INR outperforms existing methods on scientific data encoding tasks.