Weight-Space Mixture-of-Experts for Implicit Neural Representation Classification

2026-07-31

AI Summary

This work addresses the challenge of directly classifying implicit neural representations (INRs) due to the high dimensionality and complex structure of their weight spaces, as well as the unclear mechanisms governing the distribution of discriminative information. To tackle this, the authors propose a structure-aware hierarchical mixture-of-experts (HMoE) Transformer integrated within a meta-learning framework, enabling conditional computation in weight space. They introduce, for the first time, a structure-aligned MoE architecture for INR learning and develop weight attribution and structured pruning techniques to uncover class-specific substructures, substantially enhancing model interpretability. The proposed method achieves state-of-the-art accuracy on multiple benchmarks, including ImageNet-1K, demonstrating its effectiveness across both low- and high-resolution data.

Abstract

Implicit Neural Representations (INRs) encode signals as the weights of a coordinate-based neural network and have recently been proposed as an alternative domain for downstream learning. While promising, classification directly in weight space remains challenging due to the high dimensionality and complex structure of INR parameters. Furthermore, the way discriminative information is distributed across INR weights remains poorly understood. We propose a hierarchical Mixture-of-Experts (HMoE) Transformer that processes INR weights using conditional computation aligned with the structure of the underlying implicit network. Coupled with a meta-learning framework that shapes INR parameters for downstream tasks, our model achieves state-of-the-art accuracy across standard benchmarks, ranging from low-resolution datasets to high-resolution ImageNet-1K. To gain insight into how INRs encode discriminative information, we develop weight-space attribution and pruning methods that identify parameters most relevant for classification. These analyses reveal how class-specific structure emerges within INR layers and support the suitability of MoE architectures for weight-space learning. Our approach advances both the performance and interpretability of weight-space classifiers.

Problem

• Implicit Neural Representations
• weight-space classification
• high dimensionality
• discriminative information
• parameter structure

Innovation

• Implicit Neural Representations
• Mixture-of-Experts
• Weight-Space Learning
• Meta-Learning
• Interpretability