Poster
in
Workshop: AI for Science: Progress and Promises
Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Prediction
Wenlin Chen · Austin Tripp · José Miguel Hernández-Lobato
Keywords: [ Bilevel Optimization ] [ Drug Discovery ] [ deep kernel learning ] [ molecules ] [ chemistry ] [ Meta-Learning ] [ Gaussian Processes ]
We propose Adaptive Deep Kernel Fitting with Implicit Function Theorem (ADKF-IFT), a novel framework for learning deep kernels by interpolating between meta-learning and conventional deep kernel learning. Our approach employs a bilevel optimization objective where we meta-learn generally useful feature representations across tasks, in the sense that task-specific Gaussian process models estimated on top of such features achieve the lowest possible predictive loss on average. We solve the resulting nested optimization problem using the implicit function theorem (IFT). We show that our ADKF-IFT framework contains Deep Kernel Learning (DKL) and Deep Kernel Transfer (DKT) as special cases. Although ADKF-IFT is a completely general method, we argue that it is especially well-suited for drug discovery problems and demonstrate that it significantly outperforms previous SOTA methods on a variety of real-world few-shot molecular property prediction tasks and out-of-domain molecular property prediction and optimization tasks.