Rejection via Learning Density Ratios

📅 2024-05-29
🏛️ Neural Information Processing Systems
📈 Citations: 2
Influential: 1
📄 PDF

career value

219K/year
🤖 AI Summary
This work addresses the problem that classification models are forced to predict even under high uncertainty. We propose a rejection mechanism based on density ratio estimation (DRE), modeling rejection as estimating the ratio between the true data distribution and an idealized target distribution. Our method optimizes a risk function regularized by α-divergence—departing for the first time from conventional loss-augmentation paradigms. It endows rejection decisions with well-defined probabilistic semantics and distribution-level interpretability, and naturally accommodates pre-trained models. Empirically, it significantly improves both rejection accuracy and classification reliability on both clean and noisy datasets. Key contributions are: (1) the first formalization of rejection learning as a DRE problem; (2) the introduction of φ-divergence regularization—specifically the α-divergence family—to achieve distributionally robust optimization; and (3) a theoretically rigorous yet practical framework for interpretable rejection.

Technology Category

Application Category

📝 Abstract
Classification with rejection emerges as a learning paradigm which allows models to abstain from making predictions. The predominant approach is to alter the supervised learning pipeline by augmenting typical loss functions, letting model rejection incur a lower loss than an incorrect prediction. Instead, we propose a different distributional perspective, where we seek to find an idealized data distribution which maximizes a pretrained model's performance. This can be formalized via the optimization of a loss's risk with a $varphi$-divergence regularization term. Through this idealized distribution, a rejection decision can be made by utilizing the density ratio between this distribution and the data distribution. We focus on the setting where our $varphi$-divergences are specified by the family of $alpha$-divergence. Our framework is tested empirically over clean and noisy datasets.
Problem

Research questions and friction points this paper is trying to address.

Develops a method for classification with rejection using density ratios
Proposes an idealized data distribution to enhance model performance
Utilizes $alpha$-divergence for regularization and rejection decisions
Innovation

Methods, ideas, or system contributions that make the work stand out.

Uses density ratios for rejection decisions
Optimizes loss risk with divergence regularization
Applies α-divergence family for distribution comparison
🔎 Similar Papers
No similar papers found.