FlexiFaCT: Scalable Flexible Factorization of Coupled Tensors on Hadoop

By Alex Beutel, Partha P. Talukdar, Abhimanu Kumar, Christos Faloutsos, Evangelos E. Papalexakis, Eric P. Xing. 2014

122 citations recorded by the source corpus.

Given multiple data sets of relational data that share a number of dimensions, how can we efficiently decompose our data into the latent factors? Factorization of a single matrix or tensor has attracted much attention, as, e.g., in the Netflix challenge, with users rating movies. However, we often have additional, side, information, like, e.g., demographic data about the users, in the Netflix example above. Incorporating the additional information leads to the coupled factorization problem. So far, it has been solved for relatively small datasets. We provide a distributed, scalable method for decomposing matrices, tensors, and coupled data sets through stochastic gradient descent on a variety of objective functions. We offer the following contributions: (1) Versatility: Our algorithm can perform matrix, tensor, and coupled factorization, with flexible objective functions including the Frobenius norm, Frobenius norm with an `1 induced sparsity, and non-negative factorization. (2) Scalability: FlexiFaCT scales to unprecedented sizes in both the data and model, with up to billions of parameters. FlexiFaCT runs on standard Hadoop. (3) Convergence proofs showing that FlexiFaCT converges on the variety of objective functions, even with projections.

Subfields: Artificial Intelligence, Computational Mathematics, Computational Mechanics

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 Computational Mechanics

Citations in the corpus

Privacy-Preserving Tensor Factorization for Collaborative Health Data Analysis (2019, methodology): “FlexiFaCT [3] is a scalable MapReduce algorithm for coupled matrix-tensor decomposition using stochastic gradient descent (SGD).”
Tensors for Data Mining and Data Fusion (2016, methodology): “The work of Beutel et al. [2014], however, introduces a Map/Reduce algorithm based on Distributed Stochastic Gradient Descent.”
TensorCast: forecasting and mining with coupled tensors (2018, background): “Whenever the side information available is dynamic (time-evolving), a model where two tensors are coupled along (at least) one of the dimensions is more appropriate, as the time component can be preserved: where Many techniques have been proposed to solve this nonnegative optimization problem, such ”