Adaptive Classification for Prediction Under a Budget

Abstract

We propose a novel adaptive approximation approach for test-time resource-constrained prediction. Given an input instance at test-time, a gating function identifies a prediction model for the input among a collection of models. Our objective is to minimize overall average cost without sacrificing accuracy. We learn gating and prediction models on fully labeled training data by means of a bottom-up strategy. Our novel bottom-up method first trains a high-accuracy complex model. Then a low-complexity gating and prediction model are subsequently learned to adaptively approximate the high-accuracy model in regions where low-cost models are capable of making highly accurate predictions. We pose an empirical loss minimization problem with cost constraints to jointly train gating and prediction models. On a number of benchmark datasets our method outperforms state-of-the-art achieving higher accuracy for the same cost.

arXiv admin note: substantial text overlap with arXiv:1704.07505

Cited by in corpus (13)

• Classification with Costly Features as a Sequential Decision-Making Problem
• Opportunistic Learning: Budgeted Cost-Sensitive Learning from Data Streams
• Cost-Sensitive Diagnosis and Learning Leveraging Public Health Data
• AppealNet: An Efficient and Highly-Accurate Edge/Cloud Collaborative Architecture for DNN Inference
• Costly Features Classification using Monte Carlo Tree Search
• Effective Medical Test Suggestions Using Deep Reinforcement Learning
• Interpretable Companions for Black-Box Models
• Online Selective Classification with Limited Feedback
• Selective Classification via One-Sided Prediction
• Cost-Sensitive Feature-Value Acquisition Using Feature Relevance
• Adaptive Covariate Acquisition for Minimizing Total Cost of Classification
• Cost-Aware Fine-Grained Recognition for IoTs Based on Sequential Fixations
• Robust Text Classifier on Test-Time Budgets