GP-ConvCNP: Better Generalization for Convolutional Conditional Neural Processes on Time Series Data
Neural Processes (NPs) are a family of conditional generative models that are able to model a distribution over functions, in a way that allows them to perform predictions at test time conditioned on a number of context points. A recent addition to this family, Convolutional Conditional Neural Processes (ConvCNP), have shown remarkable improvement in performance over prior art, but we find that they sometimes struggle to generalize when applied to time series data. In particular, they are not robust to distribution shifts and fail to extrapolate observed patterns into the future. By incorporating a Gaussian Process into the model, we are able to remedy this and at the same time improve performance within distribution. As an added benefit, the Gaussian Process reintroduces the possibility to sample from the model, a key feature of other members in the NP family.
Code (1)
Tasks
Time SeriesTime Series AnalysisMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Spectral Convolutional Conditional Neural Processes
Conditional Neural Processes (CNPs) constitute a family of probabilistic models that harness the flexibility of neural networks to parameterize stochastic processes. Their capability to furnish well-calibrated prediction…
Inductive BiasMeta-LearningConvolutional Conditional Neural Processes
We introduce the Convolutional Conditional Neural Process (ConvCNP), a new member of the Neural Process family that models translation equivariance in the data. Translation equivariance is an important inductive bias for…
Inductive BiasTime SeriesTime Series AnalysisTranslation+1Convolutional conditional neural processes for local climate downscaling
A new model is presented for multisite statistical downscaling of temperature and precipitation using convolutional conditional neural processes (convCNPs). ConvCNPs are a recently developed class of models that allow de…
Gaussian ProcessesWhere to Measure: Epistemic Uncertainty-Based Sensor Placement with ConvCNPs
Accurate sensor placement is critical for modeling spatio-temporal systems such as environmental and climate processes. Neural Processes (NPs), particularly Convolutional Conditional Neural Processes (ConvCNPs), provide …
Sim2Real for Environmental Neural Processes
Machine learning (ML)-based weather models have recently undergone rapid improvements. These models are typically trained on gridded reanalysis data from numerical data assimilation systems. However, reanalysis data come…