Sequential Neural Processes

Abstract

Neural Processes combine the strengths of neural networks and Gaussian processes to achieve both flexible learning and fast prediction in stochastic processes. However, a large class of problems comprises underlying temporal dependency structures in a sequence of stochastic processes that Neural Processes (NP) do not explicitly consider. In this paper, we propose Sequential Neural Processes (SNP) which incorporates a temporal state-transition model of stochastic processes and thus extends its modeling capabilities to dynamic stochastic processes. In applying SNP to dynamic 3D scene modeling, we introduce the Temporal Generative Query Networks. To our knowledge, this is the first 4D model that can deal with the temporal dynamics of 3D scenes. In experiments, we evaluate the proposed methods in dynamic (non-stationary) regression and 4D scene inference and rendering.

NeurIPS 2019 Spotlight. First two authors contributed equally

Cited by in corpus (14)

• Normalizing Flow-based Neural Process for Few-Shot Knowledge Graph Completion
• Graph Sequential Neural ODE Process for Link Prediction on Dynamic and Sparse Graphs
• Modeling Continuous Stochastic Processes with Dynamic Normalizing Flows
• Recurrent Neural Processes
• Bootstrapping Neural Processes
• Multi-fidelity Hierarchical Neural Processes
• Real-time Adaptation for Condition Monitoring Signal Prediction using Label-aware Neural Processes
• Message Passing Neural Processes
• Few-Shot Learning Patterns in Financial Time-Series for Trend-Following Strategies
• Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Future
• Global Convolutional Neural Processes
• Evidential Turing Processes
• Continual Learning of Multi-modal Dynamics with External Memory
• GP-ConvCNP: Better Generalization for Convolutional Conditional Neural Processes on Time Series Data