GP-ConvCNP: Better Generalization for Convolutional Conditional Neural Processes on Time Series Data
This work addresses generalization issues in time series modeling for researchers and practitioners, representing an incremental improvement over existing ConvCNP methods.
The paper tackled the problem of poor generalization in Convolutional Conditional Neural Processes (ConvCNP) on time series data, particularly under distribution shifts and extrapolation, by incorporating a Gaussian Process, which improved performance within distribution and restored sampling capability.
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.