Equivariant Representation Learning

Overview

Equivariant representation learning studies how to encode data so that transformations such as rotation or translation produce corresponding, predictable changes in a model’s features. Group-equivariant convolutions, irrep-based graph networks, and equivariant transformers encode these rules directly; data augmentation and self-supervised consistency objectives can encourage them from examples, and some methods learn the transformations themselves. These representations are useful in vision, molecular and physical prediction, robotics, and audio, where they can support data efficiency and generalization across viewpoints or configurations. A central tension is balancing exact symmetry guarantees with flexibility, computational cost, and task accuracy: exact equivariance ensures consistent behavior across transformations but does not guarantee strong predictions, while softer or learned symmetry may be easier to scale but can miss important constraints.

Latest papers

CardsList

64 papers9 papers in the last four weeks, down 25% on the four weeks before. 0.1% of all new papers.

  1. An Algebraic Representation Theorem for Linear GENEOs in Machine Learning

    Jan 7, 2026Francesco Conti, Patrizio Frosini, Nicola QuercioliEquivariant Representation Learning

  2. L-GTA: Latent Generative Modeling for Time Series Augmentation

    Jul 31, 2025Luis Roque, Vitor Cerqueira, Carlos Soares +1Variational AutoencodersSynthetic Data Augmentation

  3. Representation Learning for Equivariant Inference with Guarantees

    May 26, 2025Daniel Ordoñez-Apraez, Vladimir Kostić, Alek Fröhlich +3Disentangled Representation LearningRepresentation Learning