Consistent Semi-Supervised Graph Regularization for High Dimensional Data
Semi-supervised Laplacian regularization, a standard graph-based approach for learning from both labelled and unlabelled data, was recently demonstrated to have an insignificant high dimensional learning efficiency with respect to unlabelled data (Mai and Couillet 2018), causing it to be outperformed by its unsupervised counterpart, spectral clustering, given sufficient unlabelled data. Following a detailed discussion on the origin of this inconsistency problem, a novel regularization approach involving centering operation is proposed as solution, supported by both theoretical analysis and empirical results.
Code (0)
등록된 구현이 없습니다.
Tasks
ClusteringVocal Bursts Intensity PredictionSimilar Papers 제목 키워드 기반
Efficient Distributed Semi-Supervised Learning using Stochastic Regularization over Affinity Graphs
We describe a computationally efficient, stochastic graph-regularization technique that can be utilized for the semi-supervised training of deep neural networks in a parallel or distributed setting. We utilize a techniqu…
GraphMix: Regularized Training of Graph Neural Networks for Semi-Supervised Learning
We present GraphMix, a regularization technique for Graph Neural Network based semi-supervised object classification, leveraging the recent advances in the regularization of classical deep neural networks. Specifically, …
Graph Neural NetworkSemi-Supervised Phone Classification using Deep Neural Networks and Stochastic Graph-Based Entropic Regularization
We describe a graph-based semi-supervised learning framework in the context of deep neural networks that uses a graph-based entropic regularizer to favor smooth solutions over a graph induced by the data. The main contri…
DiversityGeneral ClassificationGraphMix: Improved Training of GNNs for Semi-Supervised Learning
We present GraphMix, a regularization method for Graph Neural Network based semi-supervised object classification, whereby we propose to train a fully-connected network jointly with the graph neural network via parameter…
Generalization BoundsGraph AttentionGraph Neural NetworkNode ClassificationRegularizing Semi-supervised Graph Convolutional Networks with a Manifold Smoothness Loss
Existing graph convolutional networks focus on the neighborhood aggregation scheme. When applied to semi-supervised learning, they often suffer from the overfitting problem as the networks are trained with the cross-entr…