Classification with Costly Features as a Sequential Decision-Making Problem

Abstract

This work focuses on a specific classification problem, where the information about a sample is not readily available, but has to be acquired for a cost, and there is a per-sample budget. Inspired by real-world use-cases, we analyze average and hard variations of a directly specified budget. We postulate the problem in its explicit formulation and then convert it into an equivalent MDP, that can be solved with deep reinforcement learning. Also, we evaluate a real-world inspired setting with sparse training dataset with missing features. The presented method performs robustly well in all settings across several distinct datasets, outperforming other prior-art algorithms. The method is flexible, as showcased with all mentioned modifications and can be improved with any domain independent advancement in RL.

References in corpus (14)

• Continuous control with deep reinforcement learning
• Dueling Network Architectures for Deep Reinforcement Learning
• Asynchronous Methods for Deep Reinforcement Learning
• Safe and Efficient Off-Policy Reinforcement Learning
• Cost-Sensitive Tree of Classifiers
• Efficient Learning with Partially Observed Attributes
• Risk-Constrained Reinforcement Learning with Percentile Risk Criteria
• The Greedy Miser: Learning under Test-time Budgets
• Fast classification using sparse decision DAGs
• Efficient Learning by Directed Acyclic Graph For Resource Constrained Prediction
• Adaptive Classification for Prediction Under a Budget
• Datum-Wise Classification: A Sequential Approach to Sparsity
• Opportunistic Learning: Budgeted Cost-Sensitive Learning from Data Streams
• Integrating Learning from Examples into the Search for Diagnostic Policies

Cited by in corpus (5)

• Why People Skip Music? On Predicting Music Skips using Deep Reinforcement Learning
• Classification with Costly Features in Hierarchical Deep Sets
• Confounding Feature Acquisition for Causal Effect Estimation
• Evolutionary Optimization of High-Coverage Budgeted Classifiers
• Mapping the Internet: Modelling Entity Interactions in Complex Heterogeneous Networks