Centered Kernel Alignment

Also known as CKA

Follow this topic Ask about this topic

Latest papers

9 papers2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Measuring Learned Equivariance: An Information Theoretic Approach
Oct 12, 2026Claire Schlesinger, Wolfgang Gatterbauer, Robin WaltersCentered Kernel Alignment Equivariant Representation Learning
Khoury College of Computer Sciences Northeastern University Boston, MA 02115, USA
Surfing the Activation Wave: Analyzing the Information and Geometry of LLM Hidden States for Speculative Decoding
Oct 9, 2026Raghavv Goel, Sudhanshu Agrawal, Mukul Gagrani +2Centered Kernel Alignment Speculative Decoding
Qualcomm AI Research · Stanford University
FedCKA: Representation-Guided Layer Personalization for Federated 3D Perception Across Driving Domains
Oct 1, 2026Jolle Verhoog, Ali Burak Ünal, Holger CaesarDomain Generalization Centered Kernel Alignment
faculty of Cognitive Robotics, Mechanical Engineering, TU Delft, Delft, Netherlands
Contrastive-Difference CKA Reveals Concept-Specific Structural Alignment Across Language Model Architectures
Jun 15, 2026Xueping GaoCentered Kernel Alignment Kernel Methods
Alibaba Cloud
Beyond Output Matching: Preserving Internal Geometry in NVFP4 LLM Distillation
Jun 4, 2026Fangbo Tu, Junhua Zhao, Chi Liu +4LLM Quantization Centered Kernel Alignment
PayPal, Inc.
From Layers to Networks: Comparing Neural Representations via Diffusion Geometry
May 15, 2026Atharva Khandait, Jan E. GerkenRepresentational Similarity Analysis Neural Representation Geometry
Department of Mathematical Sciences, Chalmers University of Technology and the University of Gothenburg, SE-412 96 Gothenburg, Sweden.
Mean-Pooled Cosine Similarity is Not Length-Invariant: Theory and Cross-Domain Evidence for a Length-Invariant Alternative
May 8, 2026Sibayan Mitra, Dhruv KumarNeural Representation Geometry Centered Kernel Alignment
BITS Pilani · Birla Institute of Technology and Science, Pilani, India.
Federated learning for unpaired multimodal data
Jan 25, 2026Anders EklundCentered Kernel Alignment Multimodal Federated Learning
Department of Biomedical Engineering, Linköping University, Sweden · Department of Computer and Information Science, Linköping University, Sweden · Center for Medical Image Science and Visualization (CMIV), Linköping University, Sweden
Manifold Approximation leads to Robust Kernel Alignment
Oct 27, 2025Mohammad Tariqul Islam, Du Liu, Deblina SarkarCentered Kernel Alignment Kernel Methods
MIT

Oct 12, 2026J/K move · Enter open · S save

Measuring Learned Equivariance: An Information Theoretic Approach

Claire Schlesinger, Wolfgang Gatterbauer, Robin Walters

Khoury College of Computer Sciences Northeastern University Boston, MA 02115, USA

Centered Kernel Alignment Equivariant Representation Learning

Open paper AskPDF arXiv

Learning symmetries through data augmentation offers an alternative to architectural equivariance, but does not guarantee that a network respects those symmetries. Measuring learned equivariance is especially difficult for intermediate representations, whose group actions are not specified. In a finite discrete setting, we show that equivariance requires representations of original and transformed inputs to determine one another exactly, yielding a test based on normalized mutual information (NMI). For high-dimensional activations, we use centered kernel alignment (CKA) as a scalable test, with an exact guarantee for orthogonal feature transformations. Across architectures and tasks, augmentation usually increases transformation consistency, showing that learned equivariance can be probed directly from representations without recovering the hidden transformation rules that relate them.