MapReduce: simplified data processing on large clusters

By Muthu Dayalan. 2008

26,488 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Hardware and Architecture, Information Systems, ML Systems & Hardware

How researchers see this paper

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

In Computer Networks and Communications

In Hardware and Architecture

In Information Systems

In ML Systems & Hardware

Citations in the corpus

Pretrained Transformers for Text Ranking: BERT and Beyond (2020, background): “There are many examples of previous Google innovation that were shared in papers only, without a corresponding open source code release; MapReduce [Dean and Ghemawat, 2004] and the Google File System [Ghemawat et al.”
TensorFlow: A system for large-scale machine learning (2016, neutral): “Batch dataﬂow systems Starting with MapReduce [22], batch dataﬂow systems have been applied to a large number of machine learning algorithms [71], and more recent systems have focused on increasing expressivity and performance.”
Hogwild: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent (2011, background): “, “find all the urls from a 100TB of Web data”) that was designed to ensure fault tolerance and to simplify the maintenance and programming of large clusters of machines [9].”
From Frequency to Meaning: Vector Space Models of Semantics (2010, background): “Dean and Ghemawat (2008) provide a good primer on MapReduce programming.”
Federated Learning and Differential Privacy: Software tools analysis, the Sherpa.ai FL framework and methodological guidelines for preserving data privacy (2020, background): “A distributed model that suits privacy restrictions is MapReduce [43].”
Data Encoding for Byzantine-Resilient Distributed Optimization (2019, methodology): “MAP-REDUCE architecture [4] is implemented in many distributed learning tasks, where there is one designated machine (called the master) that computes the model iteratively, based on the inputs from the worker machines at each iteration, typically using descent techniques, like (proximal) gradient d”
Towards Federated Learning at Scale: System Design (2019, background): “These very spe-ciﬁc requirements are better dealt with by a domain speciﬁc framework than a generic MapReduce.”
Staircase-PIR: Universally Robust Private Information Retrieval (2018, background): “The robustness property is motivated by the need to mitigate the effect of stragglers [3]–[14], i.”
Distributed Statistical Machine Learning in Adversarial Settings (2017, background): “Many efficient distributed machine learning algorithms [6, 13] and system implementations [24, 28, 10, 19] have been proposed and studied.”
Federated Optimization: Distributed Machine Learning for On-Device Intelligence (2016, methodology): “By communication round we typically understand a single MapReduce operation [24], implemented efficiently for iterative procedures [36], such as optimization algorithms.”
Benchmark and Survey of Automated Machine Learning Frameworks (2019, background): “A common strategy for solving a computational heavy problem is parallelization on multiple cores or within a cluster (e.g., Buyya, 1999; Dean & Ghemawat, 2008). scikit-learn (Pedregosa et al., 2011), which is used by most evaluated frameworks (see Section 8), already implements optimizations to…”
Survey on Automated Machine Learning (2019, background): “A common strategy for solving a computational heavy problem is parallelization on multiple cores or within a cluster, e.g., (Buyya, 1999; Dean and Ghemawat, 2008).”
Gradient Sparsification for Communication-Efficient Distributed Optimization (2017, background): “Modern large-scale machine learning applications require scaling stochastic optimization algorithms [30, 28, 15, 11] to distributed computational architectures [10, 39, 12, 20, 19, 38] or multicore systems [26, 9, 22, 25].”
Speeding Up Distributed Machine Learning Using Codes (2015, background): “In [28], Zaharia et al. propose a modification to the existing straggler detection algorithm and show that the proposed solution can effectively reduce the completion time of MapReduce tasks.”
SparkNet: Training Deep Networks in Spark (2015, background): “For some of these systems, preprocessing must be done separately by a MapReduce style framework, and data is written to disk between segments of the pipeline.”
MLlib: Machine Learning in Apache Spark (2015, background): “Keywords: Scalable Machine Learning, Distributed Algorithms, Apache Spark”
Distributed Robust Learning (2014, methodology): “The implementation of DRL follows the strategy similar to map-reduce [7]: DRL ﬁrst distributes all the samples evenly onto k machines.”