Open Source
Manifold Approximation leads to Robust Kernel Alignment
arXiv stat.ML0 views
arXiv:2510.22953v3 Announce Type: replace-cross Abstract: Centered kernel alignment (CKA) is a popular metric for comparing representations, determining equivalence of networks, and conducting neuroscience research. However, CKA does not account for the underlying manifold and relies on numerous heuristics that cause it to behave differently at different scales of data. In this work, we propose Manifold-approximated Kernel Alignment (MKA), which incorporates manifold geometry (i.e., local neighborhood) into the alignment task. We derive a theoretical framework for MKA. Our construction removes representation-dependent degree weighting, yields a closed-form alignment score, and gives each row a probabilistic interpretation as a local Markov transition distribution. We further establish kernel- and score-level stability with respect to the neighborhood size. We perform empirical evaluations on synthetic datasets and real-world examples to characterize and compare MKA to its contemporaries. In controlled synthetic experiments, MKA is consistently less sensitive to hyperparameters and captures the selected topology-preserving relationships. On the large-scale benchmark, MKA achieves its strongest aggregate performance in vision, is competitive on graphs, and is weaker than CKA in several NLP evaluations. Our findings suggest that manifold-aware kernel alignment provides a robust foundation for measuring representations and is potentially useful when local neighborhood geometry is important, with possible applications in representation learning.
Source:https://arxiv.org/abs/2510.22953PreviousToric geometry of ReLU neural networksNextDeep Multivariate Models with Parametric Conditionals
Related posts
aisync: one local hub for rules and coordination across AI coding agents
0dev.to Productivity
Robots that Collaborate: Sequential Asymmetric Imitation for Learning Coupled Robot Policies
0arXiv cs.RO
Kawaiintu OS Architecture: Decoupling Assets via GitHub & Two-Stage Dynamic GNOME Shell Theme Compilation
0dev.to Linux
Show HN: CFP Tracker – Track Conference CFPs in Obsidian
0Hacker News New
Do Underwater Image Quality Metrics Agree with Human Perception? A Benchmark with Human Choices, Simple Edits and Generative Drift
0arXiv eess.IV
X-Strata: Separating Aneurysms and Overlapping Vessels into Layers from 2D X-ray Angiography
0arXiv eess.IV