Beyond streams and graphs: dynamic tensor analysis

By Jimeng Sun, Dacheng Tao, Christos Faloutsos. Knowledge Discovery and Data Mining, 2006

532 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Mathematics, Information Systems

View Paper: https://www.semanticscholar.org/paper/19680a17240eb1eab6cfec04e3faa2bd5be61ab9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Mathematics

In Information Systems

Citations in the corpus

Tensor Networks for Dimensionality Reduction and Large-scale Optimization: Part 1 Low-Rank Tensor Decompositions (2016, unknown): “Multilinear products of a tensor by matrices or vectors play a key role in deterministic methods for the reshaping of tensors and dimensionality reduction, as well as in statitistical/probabilistic methods for randomization/sketching procedures and in random projections of tensors into matrices or v”
Multilayer networks (2013, background): “, by using dynamic tensor analysis [323] to study multiplex networks that change in time.”
Outlier Analysis (2013, methodology): “In addition, a variety of spectral methods [229, 429, 430, 432] can be used, when it is required to use only the linkage structure for analysis.”
FlexiFaCT: Scalable Flexible Factorization of Coupled Tensors on Hadoop (2014, background): “In [18], the authors propose algorithms for incremental computation of the tensor decomposition, where the tensor is a stream.”
TensorCast: forecasting and mining with coupled tensors (2018, background): “As a consequence,theyareapopularchoiceinvariousapplicationsincludingrepresentingtime-evolving relations,suchasFacebookinteractions[28],sensornetworks[37],EEGdatafordetecting the origin of epilepsy seizures [1], fMRI analysis [40], image classiﬁcation [38], or heterogeneous graph analysis [33].”
Tensor Decompositions and Applications (2009, background): “[209, 210] have written a pair of papers on dynamically updating a Tucker approximation, with applications ranging from text analysis to environmental and network modeling.”
Microscopic Social Influence (2012, methodology): “Mean-while, product network, especially Kronecker product has been applied to model graph generation [25] and dynamic tensor analysis [26].”
A survey of multilinear subspace learning for tensor data (2011, methodology): “Some tensor-based techniques have been developed in these fields [15,16] and further investigation of MSL for these applications under the framework presented in this paper can be fruitful.”
Fast Random Walk Graph Kernel (2012, methodology): “For dynamic graphs, a lot of SVD based techniques have been proposed, such as dynamic tensor analysis [37], incremental spectral clustering [26] etc.”
Tensor Analyzers (2013, methodology): “While TAs and the above models take as input i.i.d. data vectors, there exists a plethora of tensor decomposition (TD) methods when the data comes in the form of N-way tensors (Tucker, 1963; Carroll & Chang, 1970; Lathauwer & Vandewalle, 2004; Wang & Ahuja, 2003; Sun et al., 2006).”
Scalable Tensor Decompositions for Multi-aspect Data Mining (2008, methodology): “As a higher-order generalization of SVD and PCA, Tucker decomposition has widely been used as a core technique for analyzing sparse tensors [19, 20, 8].”
A Three-Way Model for Collective Learning on Multi-Relational Data (2011, methodology): “(Sun et al., 2006) presents methods for dynamic and streaming tensor analysis.”
MACH: Fast Randomized Tensor Decompositions (2009, methodology): “This is of significant practical value and can be used also in conjunction with DTA [35] to perform dynamic tensor analysis in larger time windows.”
Efficient MATLAB Computations with Sparse and Factored Tensors (2007, unknown): “More recently, these methods have been applied to signal processing [10, 11], image processing [52, 54, 57, 53], data mining [43, 46, 1, 45], scientific computing [6], and elsewhere [26, 36].”
Tensors for Data Mining and Data Fusion (2016, background): “In cases where the tensor is dynamically created or viewed as a stream of incoming slices, Sun et al. [2006] introduce an algorithm that can track the decomposition without recomputing it for every incoming slice.”
Anomaly detection in dynamic networks: a survey (2015, methodology): “Vertex detection [55, 56, 67, 106] Subgraph detection [3, 13, 30, 31] Change detection [38] Edge detection [22] Change detection [112] Vertex detection [129] Event detection [68, 72, 75, 77, 83, 84, 93, 113, 114, 115, 122] Change detection [7, 65, 66] Edge detection [1, 80] Subgraph detection [60, 8”