Representation Identifiability

Ask about this topic

Overview

Representation identifiability asks whether learned codes correspond to recoverable features of the data or world, rather than one of many equally valid internal coordinate systems. Researchers use nonlinear independent component analysis, multi-view and temporal data, sparsity or orthogonality constraints, and symmetry-breaking interventions to establish when recovery is possible. Guarantees may identify individual factors only up to permutation and scaling, or recover just shared subspaces and invariant geometry, in settings from generative models to neural networks. A central tension is that results depend on assumptions about the data, model, and measurements: identical predictions can arise from different representations, and evaluation metrics can themselves change under function-preserving reparameterizations.

Latest papers

CardsList

41 papers12 papers in the last four weeks, up 200% on the four weeks before. 0.1% of all new papers.

  1. Where Latents Belong and How They Flow: Joint Identification of Structural Roles

    Oct 16, 2026Xintong Li, Kun Zhang, Yujia ZhengLatent Dynamics ModelingRepresentation Identifiability

    CMU · MBZUAI · UIUC

  2. Complete or Sparse: A Tale of Two Identifiabilities

    Oct 14, 2026Junze Zhou, David KlindtRepresentation IdentifiabilityRepresentation Learning

    Cold Spring Harbor Laboratory

  3. Linear Independence of Polynomial Compositions with Bounded Input Degree

    Oct 14, 2026Xiaotian Chang, Yacoub HendiRepresentation IdentifiabilityParameter Identifiability

  4. Identication and Estimation of Nonsymmetric Determinantal Point Processes

    Oct 10, 2026Christian Gouriéroux, Yang LuDeterminantal Point ProcessRepresentation Identifiability

    University of Toronto, Toulouse School of Economics and CREST · Department of Mathematics and Statistics, Concordia University, Montreal, Canada

  5. Intervention anchors and scientific verification in synthetic vascular predictive representations

    Oct 8, 2026Lingsen You, Yujun Guo, Xinyu Zhong +4Representation IdentifiabilityPredictive Representation Learning

    Department of Cardiology, Zhongshan Hospital, Fudan University, Shanghai Institute of Cardiovascular Diseases, State Key Laboratory of Cardiovascular Diseases, NHC Key Laboratory of Ischemic Heart Diseases, National Clinical Research Center for Interventional Medicine, Key Laboratory of Viral Heart Diseases, Chinese Academy of Medical Sciences, Shanghai 200032, China. · Institutes of Biomedical Sciences, Fudan University, Shanghai 200030, China. · College of Biomedical Engineering, Fudan University, Shanghai 200438, China. +1

  6. The Identifiability and Observability of Deep Normalized Attention

    Oct 7, 2026Pranav Venkata KondaAttention MechanismsRepresentation Identifiability

    Columbia University

  7. DSReg: Provably Recovering Individual World Latents without Reconstruction

    Oct 7, 2026Yujia Zheng, David Klindt, Randall Balestriero +1Representation IdentifiabilityLatent World Models

    University of Illinois Urbana-Champaign · Cold Spring Harbor Laboratory · Brown University +2

  8. Decoy and disclosure radii of invariant shape descriptors

    Oct 6, 2026Tanush Shaska, Lubjana BeshajRepresentation Identifiability

  9. When Can We Trust the Matching Principle? Robust Deployment Geometry Under Finite-Sample and Model Uncertainty

    Oct 2, 2026Vishal RajputRobust EstimationUncertainty Quantification

    Independent researcher Leuven, Belgium

  10. Parameter symmetries determine representational geometry in overparameterized nonlinear networks

    Sep 30, 2026Marvin Theiss, Lukas Braun, Andrew M. Saxe +1Overparameterized Neural NetworkNeural Representation Geometry

    University of Tübingen · International Max Planck Research School for Intelligent Systems · Allen Institute for Neural Dynamics +4

  11. Predictive Self-Supervised Learning Provably Identifies Stochastic Signals under Nuisance

    Sep 29, 2026Fabian A. Mikulasch, Friedemann ZenkeLatent Variable ModelsRepresentation Identifiability

    Friedrich Miescher Institute for Biomedical Research, Basel, Switzerland · Faculty of Science, University of Basel, Switzerland

  12. Identifying ODEs from Unstructured Data with Causal Representation Learning

    Sep 29, 2026Alessandro Trenta, Riccardo Massidda, Davide Bacciu +1Causal Representation LearningRepresentation Identifiability

    Department of Computer Science University of Pisa · Saarland Informatics Campus Saarland University & University of Amsterdam

  13. Towards Identifiable Representations under Misspecified Structure

    Sep 27, 2026Yuke Li, Yujia Zheng, Ziyi Chen +2Latent Variable ModelsRepresentation Identifiability

    University of Maryland College Park, College Park, MD, USA · Carnegie Mellon University, Pittsburgh PA, USA

  14. Discovering Physical Representation Languages

    Sep 20, 2026Linzhe Zhang, Changming XuRepresentation Identifiability

    Graduate School, Northeastern University.

  15. Kinks vs. Smoothness: Identifiability of Real Analytic nICA for Laplace-like Sources

    Sep 18, 2026Isaac Manring, Kejun HuangIndependent Component AnalysisRepresentation Identifiability

    Department of Computer Science University of Florida Gainesville, FL 32611, USA

  16. Converse and Collision-Based Achievability for Node Localization with Hybrid Distance-Spectral Graph Positional Encodings

    Aug 31, 2026Zimo Yan, Yifan Li, Hao Li +4Representation IdentifiabilityPositional Encoding

    National University of Defense Technology, Changsha, China · Wuhan University, Wuhan, China

  17. More Data Cannot Break a Symmetry: Identifiability by Design

    Aug 27, 2026Jing Xu, Christopher KananRepresentation IdentifiabilityParameter Identifiability

    Department of Computer Science, University of Rochester

  18. Representation Measurements Under Function-Preserving Reparameterizations

    Aug 27, 2026Abdullah KarasanIntrinsic DimensionalityRepresentation Identifiability

    University of Maryland, Baltimore County 1000 Hilltop Circle, Baltimore, MD 21250, USA

  19. Low-Interaction-Rank Learning: Unifying Multiplicative Dual-Encoder Heads

    Aug 12, 2026Zijian Zhao, Sen LiRepresentation IdentifiabilityMultimodal Contrastive Learning

    The Hong Kong University of Science and Technology · The Hong Kong University of Science and Technology (Guangzhou)

  20. Intrinsic Structure: Spectral Identifiability for Mechanistic Interpretability

    Aug 10, 2026Ashim Dhor, Pin-Yu ChenRepresentation IdentifiabilityParameter Identifiability

    1IISER Bhopal · 2IBM Research

  21. Beyond ICA: Identifiability by Symmetry Breaking

    Jul 25, 2026Pengzhou WuLatent Variable ModelsRepresentation Identifiability

    SANKEN, University of Osaka

  22. Teacher Supervision over Representation Equivalence Classes

    Jul 3, 2026Sang Il HanRepresentation IdentifiabilityLanguage Model Distillation

    Korea University of Technology and Education · Biomonster Co.

  23. Disentangling Continuous-Time Latent Dynamics: Identifiability of Latent SDEs via Diffusion Shifts

    Jun 26, 2026Yuanyuan Wang, Wenjie Wang, Haoxuan Li +2Stochastic Differential EquationsCausal Representation Learning

    Mohamed bin Zayed University of Artificial Intelligence · The University of Melbourne · Peking University +1

  24. Unsupervised Disentanglement Without Compromises : How Functional Orthogonality Enforces Identifiability

    Jun 19, 2026Mathieu Cyrille Simon, Pascal Frossard, Christophe De VleeschouwerUnsupervised LearningDisentangled Representation Learning

    1UCLouvain, ICTEAM, Louvain-la-Neuve, Belgium · 2EPFL, LTS4 laboratory, Lausanne, Switzerland.

  25. Unstable Features, Reproducible Subspaces: Understanding Seed Dependence in Sparse Autoencoders

    Jun 10, 2026Gleb Gerasimov, Timofei Rusalev, Nikita Balagansky +3Representation IdentifiabilitySparse Autoencoders

    T-Tech

  26. Identifiability Without Gaussianity: Symbolic World Models and Near-Infinite Temporal Consistency

    Jun 9, 2026Seth Dobrin, Łukasz ChmielLatent Variable ModelsCausal Representation Learning

    1ARYA Labs, PBC

  27. A Fiber Criterion for Representation Identifiability in Supervised Learning

    May 31, 2026Vasileios SevetlidisRepresentation IdentifiabilityParameter Identifiability

    Athena Research Center, Kimmeria Campus, Xanthi, Greece · Democritus University of Thrace, Vas. Sofias Campus, Xanthi, Greece · International Hellenic University, Serres, Greece

  28. When Does LeJEPA Learn a World Model?

    May 25, 2026David Klindt, Yann LeCun, Randall BalestrieroWorld Model LearningRepresentation Identifiability

    Cold Spring Harbor Laboratory · New York University · Brown University

  29. Multimodal LLMs under Pairwise Modalities

    May 20, 2026Yan Li, Yunlong Deng, Yuewen Sun +3Cross-Modal LearningRepresentation Identifiability

    Mohamed bin Zayed University of Artificial Intelligence · Carnegie Mellon University

  30. Content-Style Identification via Differential Independence

    May 18, 2026Subash Timilsina, Hoang-Son Nguyen, Sagar Shrestha +1Representation IdentifiabilityCausal Counterfactual Generation

    School of Electrical Engineering and Computer Science, Oregon State University, Corvallis, Oregon, USA.