GOPHER: Categorical probabilistic forecasting with graph structure via local continuous-time dynamics

12/18/2021
by   Ke Alexander Wang, et al.
8

We consider the problem of probabilistic forecasting over categories with graph structure, where the dynamics at a vertex depends on its local connectivity structure. We present GOPHER, a method that combines the inductive bias of graph neural networks with neural ODEs to capture the intrinsic local continuous-time dynamics of our probabilistic forecasts. We study the benefits of these two inductive biases by comparing against baseline models that help disentangle the benefits of each. We find that capturing the graph structure is crucial for accurate in-domain probabilistic predictions and more sample efficient models. Surprisingly, our experiments demonstrate that the continuous time evolution inductive bias brings little to no benefit despite reflecting the true probability dynamics.

READ FULL TEXT
research
12/26/2022

Modeling Nonlinear Dynamics in Continuous Time with Inductive Biases on Decay Rates and/or Frequencies

We propose a neural network-based model for nonlinear dynamics in contin...
research
12/17/2019

Deep Iterative and Adaptive Learning for Graph Neural Networks

In this paper, we propose an end-to-end graph learning framework, namely...
research
10/16/2020

Generalizable Machine Learning in Neuroscience using Graph Neural Networks

Although a number of studies have explored deep learning in neuroscience...
research
10/10/2022

Mining Causality from Continuous-time Dynamics Models: An Application to Tsunami Forecasting

Continuous-time dynamics models, such as neural ordinary differential eq...
research
08/06/2020

Learning Insulin-Glucose Dynamics in the Wild

We develop a new model of insulin-glucose dynamics for forecasting blood...
research
02/08/2023

Taming Local Effects in Graph-based Spatiotemporal Forecasting

Spatiotemporal graph neural networks have shown to be effective in time ...
research
06/15/2019

Efficient predicate invention using shared "NeMuS"

Amao is a cognitive agent framework that tackles the invention of predic...

Please sign up or login with your details

Forgot password? Click here to reset