Iterative Feature Space Optimization through Incremental Adaptive Evaluation

TL;DR

This paper introduces EASE, a generalized adaptive evaluator that efficiently optimizes feature spaces by decoupling information, focusing on challenging samples, and incrementally updating evaluations, leading to improved performance across diverse datasets.

Contribution

The paper proposes a novel framework with a feature-sample subspace generator and a contextual attention evaluator for more effective and generalizable feature space optimization.

Findings

Outperforms existing methods on 14 real-world datasets

Effectively reduces evaluation bias and overfitting

Enhances efficiency through incremental evaluation updates

Abstract

Iterative feature space optimization involves systematically evaluating and adjusting the feature space to improve downstream task performance. However, existing works suffer from three key limitations:1) overlooking differences among data samples leads to evaluation bias; 2) tailoring feature spaces to specific machine learning models results in overfitting and poor generalization; 3) requiring the evaluator to be retrained from scratch during each optimization iteration significantly reduces the overall efficiency of the optimization process. To bridge these gaps, we propose a gEneralized Adaptive feature Space Evaluator (EASE) to efficiently produce optimal and generalized feature spaces. This framework consists of two key components: Feature-Sample Subspace Generator and Contextual Attention Evaluator. The first component aims to decouple the information distribution within the feature space to mitigate evaluation bias. To achieve this, we first identify features most relevant to prediction tasks and samples most challenging for evaluation based on feedback from the subsequent evaluator. This decoupling strategy makes the evaluator consistently target the most challenging aspects of the feature space. The second component intends to incrementally capture evolving patterns of the feature space for efficient evaluation. We propose a weighted-sharing multi-head attention mechanism to encode key characteristics of the feature space into an embedding vector for evaluation. Moreover, the evaluator is updated incrementally, retaining prior evaluation knowledge while incorporating new insights, as consecutive feature spaces during the optimization process share partial information. Extensive experiments on fourteen real-world datasets demonstrate the effectiveness of the proposed framework. Our code and data are publicly available.