arXiv Machine Learning
Consistency of augmentation graph and network approximability in contrastive learning
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Sep 24
Graph Learning with Spectral Connectivity Priors for Scarce Data
The paper introduces Spectral Connectivity-Regularized Graph Learning (SCoGL), a method for learning sparse graphs from limited data by incorporating Laplacian spectral priors that promote global connectivity. SCoGL extends the graphical lasso objective with a connectivity prior derived from Laplacian eigenvalues and uses projected gradient descent with Armijo backtracking for optimization. Experiments demonstrate that SCoGL improves graph recovery and enhances downstream tasks such as graph signal denoising when observations are scarce.
arXiv Machine Learning
Aug 14
Difference-of-Convex Regularization for Graph Learning by Differentiable Programming
arXiv:2608. 12757v1 Announce Type: cross Abstract: Laplacian-regularized minimization is fundamental in signal processing and machine learning, but is limited by the dense and ill-conditioned nature of the graph Laplacian pseudoinverse.
arXiv AI
1d ago
Consistent Geometric Deep Learning via Hilbert Bundles and Cellular Sheaves
arXiv:2605.06395v3 Announce Type: replace-cross Abstract: Modern deep learning architectures increasingly contend with sophisticated signals that are natively infinite-dimensional, such as time serie...
arXiv Machine Learning
Jun 2
From Moments to Models: Graphon-Mixture Learning for Mixup and Contrastive Learning
arXiv:2510. 03690v4 Announce Type: replace Abstract: Real-world graph datasets often arise from mixtures of populations, where graphs are generated by multiple distinct underlying distributions.
arXiv Machine Learning
Jun 19
Toward General Digraph Contrastive Learning: A Dual Spatial Perspective
arXiv:2510. 16311v3 Announce Type: replace Abstract: Graph Contrastive Learning (GCL) has emerged as a powerful tool for extracting consistent representations from graphs, independent of labeled information.
arXiv Machine Learning
Oct 15
GLL: A Differentiable Graph Learning Layer for Neural Networks
arXiv:2412.08016v3 Announce Type: replace Abstract: Standard deep learning architectures used for classification generate label predictions with a projection head and softmax activation function. Alt...