IM-Context: In-Context Learning for Imbalanced Regression Tasks

TL;DR

This paper introduces in-context learning as a novel approach to improve regression models in highly imbalanced data regions, avoiding overfitting associated with traditional weight update methods.

Contribution

It proposes using in-context learning for imbalanced regression, emphasizing localized context and demonstrating superior performance over existing methods.

Findings

In-context learning outperforms traditional methods in imbalanced regression tasks.

Localized context reduces bias in high-imbalance regions.

Empirical results show significant improvements across real-world datasets.

Abstract

Regression models often fail to generalize effectively in regions characterized by highly imbalanced label distributions. Previous methods for deep imbalanced regression rely on gradient-based weight updates, which tend to overfit in underrepresented regions. This paper proposes a paradigm shift towards in-context learning as an effective alternative to conventional in-weight learning methods, particularly for addressing imbalanced regression. In-context learning refers to the ability of a model to condition itself, given a prompt sequence composed of in-context samples (input-label pairs) alongside a new query input to generate predictions, without requiring any parameter updates. In this paper, we study the impact of the prompt sequence on the model performance from both theoretical and empirical perspectives. We emphasize the importance of localized context in reducing bias within regions of high imbalance. Empirical evaluations across a variety of real-world datasets demonstrate that in-context learning substantially outperforms existing in-weight learning methods in scenarios with high levels of imbalance.