Semi-greedy heuristics for feature selection with test cost constraints

Abstract

In real-world applications, the test cost of data collection should not exceed a given budget. The problem of selecting an informative feature subset under this budget is referred to as feature selection with test cost constraints. Greedy heuristics are a natural and efficient method for this kind of combinatorial optimization problem. However, the recursive selection of locally optimal choices means that the global optimum is often missed. In this paper, we present a three-step semi-greedy heuristic method that directly forms a population of candidate solutions to obtain better results. In the first step, we design the heuristic function. The second step involves the random selection of a feature from the current best k features at each iteration. This is the major difference from conventional greedy heuristics. In the third step, we obtain p candidate solutions and select the best one. Through a series of experiments on four datasets, we compare our algorithm with a classic greedy heuristic approach and an information gain-based k-weighted greedy heuristic method. The results show that the new approach is more likely to obtain optimal solutions.

Fuzzy information granulation towards interpretable sentiment analysis

“…In real applications, the granular computing theory has been popularly used for advancing other research areas, such as computational intelligence (Dubois and Prade 2016;Kreinovich 2016;Yao 2005b;Livi and Sadeghian 2016), artificial intelligence (Wilke and Portmann 2016;Yao 2005b;Skowron et al 2016), and machine learning (Min and Xu 2016;Peters and Weber 2016;Liu and Cocea 2017b;Antonelli et al 2016). In addition, ensemble learning is an area that has a strong link with granular computing.…”

Effective Evolutionary Multilabel Feature Selection under a Budget Constraint

“…This problem is known as budgeted feature selection [13] or feature selection with test cost constraints [8,14,15]. However, most studies have been conducted from the perspective of traditional single-label learning.…”

Multi-attribute decision-making based on the SPIFGIA operators

“…MADM problems and granular computing have got more attentions from the literatures (Beliakov et al 2011;Beliakov et al 2010;Wei and Zhao 2012;Chen 2014;Bedregal et al 2014;Livi and Sadeghian 2015;Pedrycz and Chen 2015;Chen and Chang 2015;Rodríguez et al 2012Rodríguez et al , 2013Rodríguez et al , 2014He et al 2015;Chen et al 2016;Apolloni et al 2016;Antonelli et al 2016;Ciucci 2016;Lingras et al 2016;Loia et al 2016;Maciel et al 2016;Min and Xu 2016;Peters and Weber 2016;Skowron et al 2016;Wilke and Portmann 2016;Xu and Wang 2016;Yao 2016). Considering the different backgrounds of experts, Xu and Wang (2016) gave an overview on managing multigranularity linguistic term sets for MADM problems.…”