@inproceedings{7b692f103e5847459a0ff2aa6619ae98,
title = "A hybrid approach for automatic model recommendation",
abstract = "One of the challenges of automating machine learning applications is the automatic selection of an algorithmic model for a given problem. We present AutoDi, a novel and resource-efficient approach for model selection. Our approach combines two sources of information: metafeatures extracted from the data itself and word-embedding features extracted from a large corpus of academic publications. This hybrid approach enables AutoDi to select top-performing algorithms both for widely and rarely used datasets by utilizing its two types of feature sets. We demonstrate the effectiveness of our proposed approach on a large dataset of 119 datasets and 179 classification algorithms grouped into 17 families. We show that AutoDi can reach an average of 98.8% of optimal accuracy and select the optimal classification algorithm in 49.5% of all cases.",
keywords = "Algorithm Recommendation, Classification, Classifier Families, Dataset Meta-features, Expert System, Meta-Learning, Scholarly Big Data, Word Embedding",
author = "Roman Vainshtein and Asnat Greenstein-Messica and Gilad Katz and Bracha Shapira and Lior Rokach",
note = "Funding Information: using our approach as a preliminary step for more computationally-intensive solutions such as AutoWeka [13]. ACKNOWLEDGMENTS This work has been supported in part by the Defense Advanced Research Projects Agency (DARPA) Data-Driven Discovery of Models (D3M) Program. REFERENCES Funding Information: This work has been supported in part by the Defense Advanced Research Projects Agency (DARPA) Data-Driven Discovery of Models (D3M) Program. Publisher Copyright: {\textcopyright} 2018 Association for Computing Machinery.; 27th ACM International Conference on Information and Knowledge Management, CIKM 2018 ; Conference date: 22-10-2018 Through 26-10-2018",
year = "2018",
month = oct,
day = "17",
doi = "10.1145/3269206.3269299",
language = "English",
series = "International Conference on Information and Knowledge Management, Proceedings",
publisher = "Association for Computing Machinery",
pages = "1623--1626",
editor = "Norman Paton and Selcuk Candan and Haixun Wang and James Allan and Rakesh Agrawal and Alexandros Labrinidis and Alfredo Cuzzocrea and Mohammed Zaki and Divesh Srivastava and Andrei Broder and Assaf Schuster",
booktitle = "CIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management",
}