Partitioning and Communication Strategies for Sparse Non-negative Matrix Factorization

Conference · Wed Aug 01 04:00:00 EDT 2018

DOI:https://doi.org/10.1145/3225058.3225127· OSTI ID:1470857

Kaya, Oguz ^[1]; Kannan, Ramakrishnan {ramki} ^[2]; Ballard, Grey ^[3]

---

1. Inria Bordeaux
2. ORNL
3. Wake Forest University, Winston-Salem

Non-negative matrix factorization (NMF), the problem of finding two non-negative low-rank factors whose product approximates an input matrix, is a useful tool for many data mining and scientific applications such as topic modeling in text mining and unmixing in microscopy. In this paper, we focus on scaling algorithms for NMF to very large sparse datasets and massively parallel machines by employing effective algorithms, communication patterns, and partitioning schemes that leverage the sparsity of the input matrix. We consider two previous works developed for related problems, one that uses a fine-grained partitioning strategy using a point-to-point communication pattern and one that uses a Cartesian, or checkerboard, partitioning strategy using a collective-based communication pattern. We show that a combination of the previous approaches balances the demands of the various computations within NMF algorithms and achieves high efficiency and scalability. From the experiments, we see that our proposed strategy runs up to 10x faster than the state of the art on real-world datasets.

• Research Organization: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
• Sponsoring Organization: USDOE
• DOE Contract Number: AC05-00OR22725
• OSTI ID: 1470857
• Country of Publication: United States
• Language: English