LGJun 18, 2023

Weakly Supervised Regression with Interval Targets

arXiv:2306.10458v18 citationsh-index: 25
Originality Incremental advance
AI Analysis

This work addresses a specific weakly supervised regression problem, offering a consistent solution for scenarios where only interval targets are available.

The paper tackles weakly supervised regression with interval targets by proposing a statistically consistent limiting method, achieving improved performance across various datasets.

This paper investigates an interesting weakly supervised regression setting called regression with interval targets (RIT). Although some of the previous methods on relevant regression settings can be adapted to RIT, they are not statistically consistent, and thus their empirical performance is not guaranteed. In this paper, we provide a thorough study on RIT. First, we proposed a novel statistical model to describe the data generation process for RIT and demonstrate its validity. Second, we analyze a simple selection method for RIT, which selects a particular value in the interval as the target value to train the model. Third, we propose a statistically consistent limiting method for RIT to train the model by limiting the predictions to the interval. We further derive an estimation error bound for our limiting method. Finally, extensive experiments on various datasets demonstrate the effectiveness of our proposed method.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes