Inverting Self-Organizing Maps: A Unified Activation-Based Framework

• URL: http://arxiv.org/abs/2601.13851v1
• Date: Tue, 20 Jan 2026 11:02:54 GMT
• Title: Inverting Self-Organizing Maps: A Unified Activation-Based Framework
• Authors: Alessandro Londei, Matteo Benati, Denise Lanzieri, Vittorio Loreto,
• Abstract summary: We show that the activation pattern of a SOM can be inverted to recover the exact input under mild geometric conditions.<n>We introduce the Manifold-Aware Unified SOM Inversion and Control (MUSIC) update rule.<n>We validate the approach using synthetic Gaussian mixtures, the MNIST and the Faces in the Wild dataset.
• Score: 39.146761527401424
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Self-Organizing Maps provide topology-preserving projections of high-dimensional data and have been widely used for visualization, clustering, and vector quantization. In this work, we show that the activation pattern of a SOM - the squared distances to its prototypes - can be inverted to recover the exact input under mild geometric conditions. This follows from a classical fact in Euclidean distance geometry: a point in $D$ dimensions is uniquely determined by its distances to $D{+}1$ affinely independent references. We derive the corresponding linear system and characterize the conditions under which the inversion is well-posed. Building upon this mechanism, we introduce the Manifold-Aware Unified SOM Inversion and Control (MUSIC) update rule, which enables controlled, semantically meaningful trajectories in latent space. MUSIC modifies squared distances to selected prototypes while preserving others, resulting in a deterministic geometric flow aligned with the SOM's piecewise-linear structure. Tikhonov regularization stabilizes the update rule and ensures smooth motion on high-dimensional datasets. Unlike variational or probabilistic generative models, MUSIC does not rely on sampling, latent priors, or encoder-decoder architectures. If no perturbation is applied, inversion recovers the exact input; when a target cluster or prototype is specified, MUSIC produces coherent semantic variations while remaining on the data manifold. This leads to a new perspective on data augmentation and controllable latent exploration based solely on prototype geometry. We validate the approach using synthetic Gaussian mixtures, the MNIST and the Faces in the Wild dataset. Across all settings, MUSIC produces smooth, interpretable trajectories that reveal the underlying geometry of the learned manifold, illustrating the advantages of SOM-based inversion over unsupervised clustering.

Related papers

• Bayesian Matrix Completion Under Geometric Constraints [3.5522446024799064]
  The completion of a Euclidean distance matrix from sparse and noisy observations is a fundamental challenge in signal processing.<n>Traditional approaches, such as rank-constrained optimization and semidefinite programming, enforce geometric constraints but often struggle under sparse or noisy conditions.<n>This paper introduces a hierarchical Bayesian framework that places structured priors directly on the latent point set generating the EDM, naturally embedding geometric constraints.
  arXiv  Detail & Related papers  (2026-01-30T09:45:34Z)
• Geometric Operator Learning with Optimal Transport [77.16909146519227]
  We propose integrating optimal transport (OT) into operator learning for partial differential equations (PDEs) on complex geometries.<n>For 3D simulations focused on surfaces, our OT-based neural operator embeds the surface geometry into a 2D parameterized latent space.<n> Experiments with Reynolds-averaged Navier-Stokes equations (RANS) on the ShapeNet-Car and DrivAerNet-Car datasets show that our method achieves better accuracy and also reduces computational expenses.
  arXiv  Detail & Related papers  (2025-07-26T21:28:25Z)
• Enforcing Latent Euclidean Geometry in Single-Cell VAEs for Manifold Interpolation [79.27003481818413]
  We introduce FlatVI, a training framework that regularises the latent manifold of discrete-likelihood variational autoencoders towards Euclidean geometry.<n>By encouraging straight lines in the latent space to approximate geodesics on the decoded single-cell manifold, FlatVI enhances compatibility with downstream approaches.
  arXiv  Detail & Related papers  (2025-07-15T23:08:14Z)
• STREAM: A Universal State-Space Model for Sparse Geometric Data [2.9483719973596303]
  Handling unstructured geometric data, such as point clouds or event-based vision, is a pressing challenge in the field of machine vision. We propose to encode geometric structure explicitly into the parameterization of a state-space model. Our model deploys the Mamba selective state-space model with a modified kernel to efficiently map sparse data to modern hardware.
  arXiv  Detail & Related papers  (2024-11-19T16:06:32Z)
• EqNIO: Subequivariant Neural Inertial Odometry [33.96552018734359]
  We show that IMU data transforms equivariantly, when rotated around the gravity vector and reflected with respect to arbitrary planes parallel to gravity. We then map the IMU data into this frame, thereby achieving an invariant canonicalization that can be directly used with off-the-shelf inertial odometry networks.
  arXiv  Detail & Related papers  (2024-08-12T17:42:46Z)
• Disentanglement via Latent Quantization [60.37109712033694]
  In this work, we construct an inductive bias towards encoding to and decoding from an organized latent space. We demonstrate the broad applicability of this approach by adding it to both basic data-re (vanilla autoencoder) and latent-reconstructing (InfoGAN) generative models.
  arXiv  Detail & Related papers  (2023-05-28T06:30:29Z)
• VTAE: Variational Transformer Autoencoder with Manifolds Learning [144.0546653941249]
  Deep generative models have demonstrated successful applications in learning non-linear data distributions through a number of latent variables. The nonlinearity of the generator implies that the latent space shows an unsatisfactory projection of the data space, which results in poor representation learning. We show that geodesics and accurate computation can substantially improve the performance of deep generative models.
  arXiv  Detail & Related papers  (2023-04-03T13:13:19Z)
• OST: Efficient One-stream Network for 3D Single Object Tracking in Point Clouds [6.661881950861012]
  We propose a novel one-stream network with the strength of the instance-level encoding, which avoids the correlation operations occurring in previous Siamese network. The proposed method has achieved considerable performance not only for class-specific tracking but also for class-agnostic tracking with less computation and higher efficiency.
  arXiv  Detail & Related papers  (2022-10-16T12:31:59Z)
• Geometry-Contrastive Transformer for Generalized 3D Pose Transfer [95.56457218144983]
  The intuition of this work is to perceive the geometric inconsistency between the given meshes with the powerful self-attention mechanism. We propose a novel geometry-contrastive Transformer that has an efficient 3D structured perceiving ability to the global geometric inconsistencies. We present a latent isometric regularization module together with a novel semi-synthesized dataset for the cross-dataset 3D pose transfer task.
  arXiv  Detail & Related papers  (2021-12-14T13:14:24Z)
• LOCA: LOcal Conformal Autoencoder for standardized data coordinates [6.608924227377152]
  We present a method for learning an embedding in $mathbbRd$ that is isometric to the latent variables of the manifold. Our embedding is obtained using a LOcal Conformal Autoencoder (LOCA), an algorithm that constructs an embedding to rectify deformations. We also apply LOCA to single-site Wi-Fi localization data, and to $3$-dimensional curved surface estimation.
  arXiv  Detail & Related papers  (2020-04-15T17:49:37Z)
• Learning Flat Latent Manifolds with VAEs [16.725880610265378]
  We propose an extension to the framework of variational auto-encoders, where the Euclidean metric is a proxy for the similarity between data points. We replace the compact prior typically used in variational auto-encoders with a recently presented, more expressive hierarchical one. We evaluate our method on a range of data-sets, including a video-tracking benchmark.
  arXiv  Detail & Related papers  (2020-02-12T09:54:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.