GP-ConvCNP: Better Generalization for Convolutional Conditional Neural Processes on Time Series Data
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 33 of its 52 references that are in the map. First posted on arXiv 9 Jun 2021.
Builds on
33 of 52 references.
References · 33
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
- 2014Deep Learning Face Attributes in the Wildcited by 3,679
- 2017Deep Setscited by 1,394
- 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
- 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
- 2015Weight Uncertainty in Neural Networkscited by 554
- 2018Generalizing to Unseen Domains via Adversarial Data Augmentationcited by 451
- 2015Deep Kernel Learningcited by 440
- 2018Conditional Neural Processescited by 421
- 2013Gaussian Processes for Big Datacited by 377
21 more
- 2018Neural Processescited by 307
- 2015Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networkscited by 295
- 2019Attentive Neural Processescited by 280
- 2019GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representationscited by 227
- 2014Scalable Variational Gaussian Process Classificationcited by 226
- 2015Kernel Interpolation for Scalable Structured Gaussian Processes (KISS-GP)cited by 175
- 2019Convolutional Conditional Neural Processescited by 139
- 2019Exact Gaussian Processes on a Million Data Pointscited by 118
- 2016Stochastic Variational Deep Kernel Learningcited by 92
- 2019On the Limitations of Representing Functions on Setscited by 89
- 2015Distributed Gaussian Processescited by 84
- 2014Manifold Gaussian Processes for Regressioncited by 79
- 2019Sequential Neural Processescited by 55
- 2019The Functional Neural Processcited by 43
- 2018Product Kernel Interpolation for Scalable Gaussian Processescited by 31
- 2017Variational Inference for Gaussian Process Models with Linear Complexitycited by 21
- 2018Orthogonally Decoupled Variational Gaussian Processescited by 19
- 2014A la Carte - Learning Fast Kernelscited by 18
- 2019Adaptive Deep Kernel Learningcited by 15
- 2019Recurrent Neural Processescited by 10
- 2018Learning models for visual 3D localization with implicit mappingcited by 7
Built on by
Citing papers per year: 2022: 2; 2023: 0; 2024: 1.
3 papers.