Invariant Representation Learning

Overview

Invariant representation learning studies how to encode data so that changes such as viewpoint, sensor, speaker, environment, or input format do not obscure task-relevant information. Approaches include symmetry-aware architectures, contrastive and predictive self-supervision, and methods that disentangle stable features from domain-specific variation or align representations across environments. These ideas are used in vision, graphs, speech, biomedical signals, robotics, and scientific data, often evaluated on shifted domains, unseen transformations, or cross-subject and cross-device benchmarks. A central tension is that removing variation can improve robustness but also discard useful signal; invariance alone does not guarantee reliable transfer, fairness, or generalization when the target itself changes across environments.

Latest papers

CardsList

242 papers13 papers in the last four weeks, down 63% on the four weeks before. 0.1% of all new papers.

  1. Rotation-Invariant Machine Learning for Highly Symmetric Molecular Configurations

    Nov 16, 2026Logan Bolton, Tomas Karella, Nicholas Lubbers +5Invariant Representation LearningMachine Learning Interatomic Potentials

  2. Towards Microphone-Invariant Speech Representations for Transformer-Based Voice Disorder Detection

    Nov 16, 2026Iva Ewert, Felix Putze, Marvin Borsdorf +1Speech ProcessingInvariant Representation Learning

  3. Toward Planning Representations That Separate Task Structure from Visual Content

    Nov 14, 2026Aarav Srivastava, Vishwas Sathish, Rajesh P. N. RaoObject-Goal NavigationDomain Generalization

  4. Metamorphic testing of learned AC optimal power flow surrogates reveals representation dependence

    Nov 10, 2026Stephen Peng, Vineet Jagadeesan NairOptimal Power FlowNeural Surrogate Modeling

  5. Enforcing Symmetries on Pre-trained ML Models for Physics

    Nov 6, 2026Wenjie Zhou, Valentino F. Foit, David W. Hogg +1Equivariant Representation LearningInvariant Representation Learning

  6. Invariance before structure: two modes of emergent compression in representation learning

    Nov 5, 2026Hardik Rajpal, Dan GoodmanInvariant Representation LearningTemporal Representation Learning

  7. CARE: Contrastive Representation Learning with Environment-Invariance Regularization for Behavioural Intention Prediction

    Nov 2, 2026Shang Gao, Zhixin Huang, Franz Götz-Hahn +2Trajectory Representation LearningContrastive Learning

  8. Overcoming the Representational Limitations of Amplitude Encoding for Quantum Neural Networks

    Oct 30, 2026Vincent Gurgul, David PrinzQuantum Data EncodingQuantum Neural Networks

  9. Spectral Invariant Fusion and Refinement for Domain Generalized Semantic Segmentation

    Oct 29, 2026Yansong Bai, Yunzhi Zhuge, Xinzhuo Yu +4Domain Generalization for Semantic SegmentationInvariant Representation Learning

  10. Intersectional Invariant Learning for Fair Deepfake Detection

    Oct 27, 2026Uzoamaka Ezeakunne, Taiwo Olabamipe, Deevesh Jain +1Deepfake DetectionIntersectional Fairness

  11. Beyond Invariance: Factor-wise Selective Treatment of Shifts for Multimodal Learning

    Oct 15, 2026Guimin Hu, Qiwei Peng, Boyan Xu +1Distribution Shift RobustnessMultimodal Robustness

  12. Monotone Piecewise-Linear Harmonization of Multitemporal Multispectral Surface Reflectance With Unsupervised Deep Multiview Pseudoinvariant Features Learning

    Oct 15, 2026Lino Garda Denaro, Chia-Hsiang LinRemote SensingInvariant Representation Learning

  13. SIEVE: Overcoming Topological Obstruction in Equivariant Self-Supervised Learning

    Oct 15, 2026Jongann Lee, Sun Woo Park, Yun Young ChoiSelf-Supervised Point Cloud LearningPoint Cloud Learning

  14. DR-VLA: Learning Human-Like Quadruped Navigation from Egocentric Web Videos via Domain-Invariant Scene Representations

    Oct 13, 2026Jun Tian, Yingjie Niu, Ruo Chen +2Quadruped Robot NavigationRobot Navigation

  15. On Making SE(2)\mathrm{SE}(2)-Invariant Networks Optimal

    Oct 12, 2026Tomas Karella, Emily Shinkle, Alice Elisabeth Anastasia Allen +3Invariant Representation LearningEquivariant Neural Networks

  16. LexiCan: Lexicographic Canonicalization of Point Clouds for Machine Learning Applications

    Oct 10, 2026Daniel Sanchez, Djordje Mihajlovic, Federica Valeau +4Invariant Representation LearningMolecular Representation Learning

  17. DEFT: Disentanglement-Enhanced Fine-Tuning for EEG Foundation Models

    Oct 10, 2026Yuqiu Deng, Muyun Jiang, Zongpeng Zhang +8EEG Foundation ModelsCross-Subject EEG Decoding

  18. SplitJEPA: Learning Invariant and Variant Latent Worlds without Reconstruction

    Oct 8, 2026Ruijin Hua, Zichuan Liu, Zhuokai Zhao +1Representation LearningInvariant Representation Learning

  19. A Structural Theory of Cognitive Representation and Problem Solving,Contexts, Invariance, and the Knowledge Space

    Oct 8, 2026Antal Jakovác, András TelcsKnowledge RepresentationComputational Cognitive Modeling

  20. GlucoPRISM: Protocol-Supervised Pretraining for Cross-Cohort Glucose Transfer

    Oct 8, 2026Adinath Madhavrao Dukre, Abdullah Mohammad, Yifan Lu +3Continuous Glucose MonitoringCross-Domain Transfer Learning

  21. How Do Transformers Learn to Represent Symmetries?

    Oct 7, 2026Eduardo Santos-Escriche, Valerie Engelmayer, Ya-Wei Eileen Lin +1Invariant Representation LearningTransformer

  22. Mathematical Invariant-Enabled Topological Neural Networks for Molecular and Materials Property Prediction

    Oct 6, 2026Yiming Ren, Xiang Liu, Mustafa Hajij +2Materials Property PredictionMolecular Property Prediction

  23. Scale-Invariant Training for Time Series Foundation Models

    Oct 5, 2026Ignacy Stepka, Willa Potosnak, Kin G. Olivares +1Time Series ForecastingInvariant Representation Learning

  24. SPDAlign: Interpretable Riemannian Alignment for EEG Forward Modeling Shifts

    Oct 5, 2026Shanglin Li, Shiwen Chu, Okan Koç +5Cross-Subject EEG DecodingUnsupervised Domain Adaptation