pyDRESCALk: Python Distributed Non Negative RESCAL Decomposition with Determination of Latent Features

pyDRESCALk: Python Distributed Non Negative RESCAL with determination of hidden features is a software package for applying non-negative RESCAL decomposition in a distributed fashion to large datasets. It can be utilized for decomposing relational datasets. It can minimize the difference between reconstructed data and the original data through Frobenius norm. Additionally, the Custom Clustering algorithm allows for automated determination for the number of Latent features.

Features:

• Ability to decompose relational datasets.
• Utilization of MPI4py for distributed operation.
• Distributed random initializations.
• Distributed Custom Clustering algorithm for estimating automated latent feature number (k) determination.
• Objective of minimization of Frobenius norm.
• Support for distributed CPUs/GPUs.
• Support for Dense/Sparse data.
• Demonstrated scaling performance upto 10TB of dense and 9Exabytes of Sparse data.