An Efficient and Scalable Approach to Build Co-occurrence Matrix for DNN's Embedding Layer

Authors: Petit, Quentin, Li, Chong, Emad, Nahid

Contributors: Petit, Quentin, Huawei Technologies France, Huawei Technologies France Boulogne-Billancourt, Maison de la Simulation (MDLS), Université de Versailles Saint-Quentin-en-Yvelines (UVSQ)-Institut National de Recherche en Informatique et en Automatique (Inria)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS), Université Paris-Saclay, Laboratoire d'Informatique Parallélisme Réseaux Algorithmes Distribués (LI-PaRAD), Université de Versailles Saint-Quentin-en-Yvelines (UVSQ)

Source: Proceedings of the 38th ACM International Conference on Supercomputing. :286-297

Subject Terms: [INFO.INFO-CC]Computer Science [cs]/Computational Complexity [cs.CC], [INFO.INFO-DC]Computer Science [cs]/Distributed, Information extraction, Natural language processing, [INFO.INFO-DS]Computer Science [cs]/Data Structures and Algorithms [cs.DS], [INFO.INFO-DS] Computer Science [cs]/Data Structures and Algorithms [cs.DS], Parallel, Distributed computing, Sparse matrix, Computing methodologies → Massively parallel algorithms, and Cluster Computing [cs.DC], Large-scale data analytics, Control methods Deep Learning, [INFO.INFO-DC] Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC], [INFO.INFO-CC] Computer Science [cs]/Computational Complexity [cs.CC], Co-occurrence matrix, Computing methodologies → Massively parallel algorithms Natural language processing Information extraction Control methods Deep Learning, Embedding

File Description: application/pdf

Access URL: https://hal.science/hal-04719623v1
https://hal.science/hal-04719623v1/document
https://doi.org/10.1145/3650200.3656629