提出自校准注意力机制，提升高维数据建模能力。
SCALAR: Self-Calibrating Adaptive Latent Attention Representation Learning
- 分组自适应注意力机制，分别处理不同特征组
- 在多数据集上显著优于现有最先进方法
- 适合处理具有复杂交互的高维异构数据
高维异构数据中复杂的特征交互给传统预测建模带来挑战。尽管投影到潜在结构（PLS）仍是常用方法，但难以捕捉复杂非线性关系，尤其在高维相关结构的多变量系统中表现不佳。同时，多尺度下的协同交互使局部处理难以捕获跨组依赖。静态特征权重也限制了对上下文变化的适应性，忽略样本特定的相关性。为此，我们提出一种新方法，通过创新架构提升预测性能。该架构引入基于自适应核的注意力机制，先分别处理不同特征组，再进行融合，既能捕捉局部模式，又保持全局关系。实验结果表明，在多个数据集上性能显著优于当前最先进方法。
原文摘要 · Abstract (English)
High-dimensional, heterogeneous data with complex feature interactions pose significant challenges for traditional predictive modeling approaches. While Projection to Latent Structures (PLS) remains a popular technique, it struggles to model complex non-linear relationships, especially in multivariate systems with high-dimensional correlation structures. This challenge is further compounded by simultaneous interactions across multiple scales, where local processing fails to capture crossgroup dependencies. Additionally, static feature weighting limits adaptability to contextual variations, as it ignores sample-specific relevance. To address these limitations, we propose a novel method that enhances predictive performance through novel architectural innovations. Our architecture introduces an adaptive kernel-based attention mechanism that processes distinct feature groups separately before integration, enabling capture of local patterns while preserving global relationships. Experimental results show substantial improvements in performance metrics, compared to the state-of-the-art methods across diverse datasets.
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。