paper-with-me

Papers

Self-Supervised Learning by Curvature Alignment

2025-11-21 · Benyamin Ghojogh, M. Hadi Sepanj, Paul Fieguth arxiv

Self-supervised learning (SSL) has recently advanced through non-contrastive methods that couple an invariance term with variance, covariance, or redundancy-reduction penalties. While such objectives shape first- and second-order statistics of the representation, they largely ignore the local geometry of the underlying data manifold. In this paper, we introduce CurvSSL, a curvature-regularized self-supervised learning framework, and its RKHS extension, kernel CurvSSL. Our approach retains a standard two-view encoder-projector architecture with a Barlow Twins-style redundancy-reduction loss on projected features, but augments it with a curvature-based regularizer. Each embedding is treated as a vertex whose $k$ nearest neighbors define a discrete curvature score via cosine interactions on the unit hypersphere; in the kernel variant, curvature is computed from a normalized local Gram matrix in an RKHS. These scores are aligned and decorrelated across augmentations by a Barlow-style loss on a curvature-derived matrix, encouraging both view invariance and consistency of local manifold bending. Experiments on MNIST and CIFAR-10 datasets with a ResNet-18 backbone show that curvature-regularized SSL yields competitive or improved linear evaluation performance compared to Barlow Twins and VICReg. Our results indicate that explicitly shaping local geometry is a simple and effective complement to purely statistical SSL regularizers.

📄 PDF Abstract BibTeX arXiv:2511.17426

Code (0)

등록된 구현이 없습니다.

Tasks

Self-Supervised Learning

Similar Papers 제목 키워드 기반

A Self-supervised Riemannian GNN with Time Varying Curvature for Temporal Graph Learning

2022-08-30 · Li Sun, Junda Ye, Hao Peng, Philip S. Yu

Representation learning on temporal graphs has drawn considerable research attention owing to its fundamental importance in a wide spectrum of real-world applications. Though a number of studies succeed in obtaining time…

Graph LearningGraph Neural NetworkGraph Representation LearningRepresentation Learning+1

A Self-supervised Mixed-curvature Graph Neural Network

2021-12-10 · Li Sun, Zhongbao Zhang, Junda Ye, Hao Peng 외

Graph representation learning received increasing attentions in recent years. Most of existing methods ignore the complexity of the graph structures and restrict graphs in a single constant-curvature representation space…

Contrastive LearningGraph Neural NetworkGraph Representation LearningRepresentation Learning

CASL: Curvature-Augmented Self-supervised Learning for 3D Anomaly Detection

2025-11-17 · Yaohua Zha, Xue Yuerong, Chunlin Fan, Yuansong Wang 외 arxiv

Deep learning-based 3D anomaly detection methods have demonstrated significant potential in industrial manufacturing. However, many approaches are specifically designed for anomaly detection tasks, which limits their gen…

Point Cloud ClassificationSelf-Supervised LearningRepresentation LearningAnomaly Classification

DeepRicci: Self-supervised Graph Structure-Feature Co-Refinement for Alleviating Over-squashing

2024-01-23 · Li Sun, Zhenhao Huang, Hua Wu, Junda Ye 외

Graph Neural Networks (GNNs) have shown great power for learning and mining on graphs, and Graph Structure Learning (GSL) plays an important role in boosting GNNs with a refined graph. In the literature, most GSL solutio…

Contrastive LearningGraph structure learningNode Classification

Curvature-Aware PCA with Geodesic Tangent Space Aggregation for Semi-Supervised Learning

2026-04-20 · Alexandre L. M. Levada arxiv

Principal Component Analysis (PCA) is a fundamental tool for representation learning, but its global linear formulation fails to capture the structure of data supported on curved manifolds. In contrast, manifold learning…

Dimensionality ReductionRepresentation Learning