MLP-KAN统一表示与函数学习，自动适配任务需求
MLP-KAN: Unifying Deep Representation and Function Learning
- 用MoE融合MLP与KAN，动态选择适合的建模方式
- 在4个数据集上表现优于传统方法，兼顾表示与函数学习
- 适合需要自动模型选择的多领域应用
近年来，表示学习与函数学习在人工智能多个领域展现出巨大潜力。然而，如何有效融合两种范式仍面临挑战，尤其在用户需根据数据特征手动选择模型时。为此，我们提出MLP-KAN，一种统一方法，旨在消除手动模型选择的必要性。通过在混合专家（MoE）架构中集成用于表示学习的多层感知机（MLPs）与用于函数学习的柯尔莫哥洛夫-阿诺德网络（KANs），MLP-KAN可动态适应任务特性，实现最优性能。该方法嵌入基于Transformer的框架，在四个广泛使用的跨领域数据集上取得显著成果。大量实验验证了其卓越的通用性，在深度表示学习和函数学习任务中均表现优异。这些结果表明MLP-KAN有潜力简化模型选择流程，为多种应用场景提供全面且自适应的解决方案。代码与权重已开源。
原文摘要 · Abstract (English)
Recent advancements in both representation learning and function learning have demonstrated substantial promise across diverse domains of artificial intelligence. However, the effective integration of these paradigms poses a significant challenge, particularly in cases where users must manually decide whether to apply a representation learning or function learning model based on dataset characteristics. To address this issue, we introduce MLP-KAN, a unified method designed to eliminate the need for manual model selection. By integrating Multi-Layer Perceptrons (MLPs) for representation learning and Kolmogorov-Arnold Networks (KANs) for function learning within a Mixture-of-Experts (MoE) architecture, MLP-KAN dynamically adapts to the specific characteristics of the task at hand, ensuring optimal performance. Embedded within a transformer-based framework, our work achieves remarkable results on four widely-used datasets across diverse domains. Extensive experimental evaluation demonstrates its superior versatility, delivering competitive performance across both deep representation and function learning tasks. These findings highlight the potential of MLP-KAN to simplify the model selection process, offering a comprehensive, adaptable solution across various domains. Our code and weights are available at \url{https://github.com/DLYuanGod/MLP-KAN}.
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。