基于模型行为特征的动态集成，提升预测精度并降低资源开销
BPE: Behavioral Profiling Ensemble
- 为每个模型构建行为画像，按其响应偏离画像程度决定权重
- 在42个真实数据集上优于当前最佳动态集成方法，准确率更高
- 无需依赖参考集，适合追求高效高精度集成的实践者
在机器学习领域，集成学习是提升预测性能的关键策略。传统静态集成方法通常将每个基学习器整体赋权，忽略了模型在不同实例空间区域中表现能力的差异。动态集成选择（DES）虽能缓解此问题，但多数方法仍依赖模型间的差异进行融合，忽视了模型自身特性，且常需大量参考集估计性能。本文提出行为画像集成（BPE）框架，引入以模型为中心的集成范式。BPE为每个模型构建内在行为画像 $\mathcal{P}_k$，通过测试实例的响应与画像的偏差来确定加权策略，本研究中 $\mathcal{P}_k$ 采用熵相关的统计量（如均值与方差）。在42个真实数据集上的大量实验表明，基于BPE的算法超越现有先进DES基线，在提升预测准确率的同时，显著降低计算与存储开销。
原文摘要 · Abstract (English)
In the field of machine learning, ensemble learning is widely recognized as a pivotal strategy for pushing the boundaries of predictive performance. Traditional static ensemble methods typically assign weights by treating each base learner as a whole, thereby overlooking that individual models exhibit varying competence across different regions of the instance space. Dynamic Ensemble Selection (DES) was introduced to address this limitation. However, both static and dynamic approaches predominantly rely on inter-model differences as the basis for integration; this inter-model perspective neglects models' intrinsic characteristics and often requires heavy reliance on reference sets for competence estimation. We propose the Behavioral Profiling Ensemble (BPE) framework, which introduces a model-centric integration paradigm. Unlike traditional methods, BPE constructs an intrinsic behavioral profile $\mathcal{P}_k$ for each model and derives aggregation weights from the deviation between a model's response to a test instance and its established profile; in this work, we instantiate $\mathcal{P}_k$ with entropy-based summary statistics (e.g., mean and variance). Extensive experiments on 42 real-world datasets show that BPE-derived algorithms outperform state-of-the-art DES baselines, increasing predictive accuracy while reducing computational and storage overhead.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。