# Diffusion-Guided Feature Selection via Nishimori Temperature: Noise-Based Spectral Embedding

Source: [Diffusion-Guided Feature Selection via Nishimori Temperature: Noise-Based Spectral Embedding](<https://www.sota2.com/research/paper/69f03f5e55a3c32af89fa3e3>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-29T05:00:19.306Z

Authors: Vasiliy S. Usatyuk, Denis A. Sapozhnikov, Sergey I. Egorov

Published: 2026-04-27T16:53:40.000Z

## Abstract

We propose Noise-Based Spectral Embedding (NBSE), a physics-informed framework for selecting informative features from high-dimensional data without greedy search. NBSE constructs a sparse similarity graph on the samples and identifies the Nishimori temperature $\\beta\_N$ the critical inverse temperature at which the Bethe Hessian becomes singular. The corresponding smallest eigenvector captures the dominant mode of an intrinsically degree-corrected diffusion process, naturally reweighting nodes to prevent hub dominance. By transposing the data matrix and applying NBSE in feature space, we obtain a one-dimensional spectral embedding that reveals groups of redundant or semantically related dimensions; balanced binning then selects one representative per group. We prove that coloured Gaussian perturbations shift $\\beta\_N$ by at most $O(\\bar\\sigma^2)$, guaranteeing robustness to measurement noise. Experiments on ImageNet embeddings from MobileNetV2 and EfficientNet-B4 show that NBSE preserves classification accuracy even under aggressive compression: on EfficientNet-B4 the accuracy drop is below $1\\%$ when retaining only $30\\%$ of features, outperforming ANOVA $F$-test and random selection by up to $6.8\\%$.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.24692>)

[PDF](<https://arxiv.org/pdf/2604.24692.pdf>)
