Interpolation for scattered data is a classical problem in numerical analysis, with a long history of theoretical and practical contributions. Recent advances have utilized deep neural networks to construct interpolators, exhibiting excellent and generalizable performance. However, they still fall short in two aspects: \textbf{1) inadequate representation learning}, resulting from separate embeddings of observed and target points in popular encoder-decoder frameworks and \textbf{2) limited generalization power}, caused by overlooking prior interpolation knowledge shared across different domains. To overcome these limitations, we present a \textbf{N}umerical \textbf{I}nterpolation approach using \textbf{E}ncoder \textbf{R}epresentation of \textbf{T}ransformers (called \textbf{NIERT}). On one hand, NIERT utilizes an encoder-only framework rather than the encoder-decoder structure. This way, NIERT can embed observed and target points into a unified encoder representation space, thus effectively exploiting the correlations among them and obtaining more precise representations. On the other hand, we propose to pre-train NIERT on large-scale synthetic mathematical functions to acquire prior interpolation knowledge, and transfer it to multiple interpolation domains with consistent performance gain. On both synthetic and real-world datasets, NIERT outperforms the existing approaches by a large margin, i.e., 4.3$\sim$14.3$\times$ lower MAE on TFRD subsets, and 1.7/1.8/8.7$\times$ lower MSE on Mathit/PhysioNet/PTV datasets. The source code of NIERT is available at https://github.com/DingShizhe/NIERT.
翻译:分散数据的内插是一个典型的数值分析问题,其理论和实践贡献的历史悠久。最近的进展利用了深层神经网络来构建内插器,表现出优异和可概括的性能。然而,它们仍然在两个方面落后:\ textbf{{1 1 代表性学习不足},原因是在流行的编码解码框架和 & textbf{2) 中分别嵌入了观测点和目标点。一方面,NIERT利用了一个仅显示内插框架,而不是在不同的领域共享的内插知识。为了克服这些限制,我们展示了一个深层神经网络网络用来构建内插点,用\ textbf{E} coder\ textbf{1 不充分的代表性学习。然而,NIERT可以将所观察的和目标点嵌入一个统一的内置值$ textbrb{tal/decodealdealation 空间的内嵌入,从而有效地利用了内部货币数据库和内部货币数据库的不断转换。</s>