Learning Deep Representations By Distributed Random Samplings
In this paper, we propose an extremely simple deep model for the unsupervised nonlinear dimensionality reduction -- deep distributed random samplings, which performs like a stack of unsupervised bootstrap aggregating. First, its network structure is novel: each layer of the network is a group of mutually independent $k$-centers clusterings. Second, its learning method is extremely simple: the $k$ centers of each clustering are only $k$ randomly selected examples from the training data; for small-scale data sets, the $k$ centers are further randomly reconstructed by a simple cyclic-shift operation. Experimental results on nonlinear dimensionality reduction show that the proposed method can learn abstract representations on both large-scale and small-scale problems, and meanwhile is much faster than deep neural networks on large-scale problems.
Code (0)
등록된 구현이 없습니다.
Tasks
ClusteringDimensionality ReductionSimilar Papers 제목 키워드 기반
Deep Distributed Random Samplings for Supervised Learning: An Alternative to Random Forests?
In (\cite{zhang2014nonlinear,zhang2014nonlinear2}), we have viewed machine learning as a coding and dimensionality reduction problem, and further proposed a simple unsupervised dimensionality reduction method, entitled d…
Dimensionality ReductionCoordinate Descent with Arbitrary Sampling II: Expected Separable Overapproximation
The design and complexity analysis of randomized coordinate descent methods, and in particular of variants which update a random subset (sampling) of coordinates in each iteration, depends on the notion of expected separ…
BiasedWalk: Biased Sampling for Representation Learning on Graphs
Network embedding algorithms are able to learn latent feature representations of nodes, transforming networks into lower dimensional vector representations. Typical key applications, which have effectively been addressed…
Community DetectionGeneral ClassificationLink PredictionNetwork Embedding+2Diffusion Based Network Embedding
In network embedding, random walks play a fundamental role in preserving network structures. However, random walk based embedding methods have two limitations. First, random walk methods are fragile when the sampling fre…
Network EmbeddingNode ClassificationDeepSphere: towards an equivariant graph-based spherical CNN
Spherical data is found in many applications. By modeling the discretized sphere as a graph, we can accommodate non-uniformly distributed, partial, and changing samplings. Moreover, graph convolutions are computationally…
Graph Neural Network