PLANET: Massively Parallel Learning of Tree Ensembles with MapReduce

By Biswanath Panda, Josh Herbach, Sugato Basu, Roberto J. Bayardo Jr.. 2009

320 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems

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 Information Systems

Citations in the corpus

MLlib: Machine Learning in Apache Spark (2015, background): “l. recommendation makes careful use of blocking to reduce JVM garbage collection overhead and to utilize higher-level linear algebra operations. Decision trees use many ideas from the PLANET project (Panda et al., 2009), such as data-dependent feature discretization to reduce communication costs, an”
Bayesian and Empirical Bayesian Forests (2015, methodology): “SSF is a commonly applied strategy (e.g., see mention, but not recommendation, of it in Panda et al., 2009), but it implies using only partial data for learning deep tree structure.”
Automating model search for large scale machine learning (2015, methodology): “For instance, efﬁcient distributed implementations of linear regression [36], tree based models [38], Naive Bayes classiﬁers [36], and k -means clustering [36] all follow this same access pattern.”
PowerLyra: Differentiated Graph Computation and Partitioning on Skewed Graphs (2019, background): “Graph-structured computation has be come increasingly popular, which is evidenced by its adoption in a wide range of areas including social computation, web search, natural language processing, and recommendation systems [5, 25, 54, 67, 88, 98].”
Training Efficient Tree-Based Models for Document Ranking (2013, unknown): “There has been work on efficiently training tree-based models on large datasets using distributed approaches [7, 8].”
TuPAQ: An Efficient Planner for Large-scale Predictive Analytic Queries (2015, methodology): “[7, 40, 36] Unfortunately, the application of supervised learning techniques to a new input dataset is computationally demanding and technically challenging.”
GraphLab: A New Framework For Parallel Machine Learning (2010, methodology): “For example, the MapReduce abstraction [Dean and Ghemawat, 2004] has been successfully applied to a broad range of ML applications [Chu et al., 2006, Wolfe et al., 2008, Panda et al., 2009, Ye et al., 2009].”
VHT: Vertical hoeffding tree (2016, background): “PLANET [15] is a framework for learning tree models on massive datasets.”
Multi-label learning with millions of labels: recommending advertiser bid phrases for web pages (2013, background): “Planet [31] provides an implementation of a single label, single shallow tree model with tens of features.”
Supervised Neighborhoods for Distributed Nonparametric Regression (2016, methodology): “However, approximations based on binning data, extracting order statistics, and using randomized searches for split-points has led to several scalable implementations of distributed random forests [11], [28].”
Interpretable models from distributed data via merging of decision trees (2013, background): “There has been many excellent works on supervised learning in this domain [4], [5], [2].”
Parallel boosted regression trees for web search ranking (2011, methodology): “Most of the previous work on parallelizing boosting focuses on parallel construction of the weak learners [23] or on the original AdaBoost algorithm [19, 29] instead of gradient boosting.”
Intelligible models for classification and regression (2012, methodology): “Gradient boosting is easier to parallelize [17] than backfitting (Gauss-Seidel).”
A Parallel Random Forest Algorithm for Big Data in a Spark Cloud Computing Environment (2017, background): “Finally, Section 6 presents a conclusion and future work.”
MoDNN: Local distributed mobile computing system for Deep Neural Network (2017, background): “Its effectiveness has been proven in many machine learning applications through maximizing the usage of computing resources of the nodes in a computing cluster [8].”