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

Autor:	Wang, Ke Alexander, Maddix, Danielle, Wang, Yuyang
Rok vydání:	2021
Předmět:	Computer Science - Machine Learning Mathematics - Dynamical Systems
Druh dokumentu:	Working Paper
Popis:	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. Comment: NeurIPS 2021 Workshop ICBINB Spotlight
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2112.09964 Zobrazit plný text záznamu View this record from Arxiv