Practical Equivariances via Relational Conditional Neural Processes
Aalto University · University of Southern Denmark - SDU · University of Helsinki · Aalto University & Finnish Center for Artificial Intelligence · Vrije Universiteit Amsterdam · Aalto University and University of Manchester
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
Conditional Neural Processes (CNPs) are a class of metalearning models popular for combining the runtime efficiency of amortized inference with reliable uncertainty quantification. Many relevant machine learning tasks, such as in spatio-temporal modeling, Bayesian Optimization and continuous control, inherently contain equivariances – for example to translation – which the model can exploit for maximal performance. However, prior attempts to include equivariances in CNPs do not scale effectively beyond two input dimensions. In this work, we propose Relational Conditional Neural Processes (RCNPs), an effective approach to incorporate equivariances into any neural process model. Our proposed method extends the applicability and impact of equivariant neural processes to higher dimensions. We empirically demonstrate the competitive performance of RCNPs on a large array of tasks naturally containing equivariances.