AdaKernel learns adaptive kernel scale parameters inside GNNs for spatiotemporal data while preserving geometric structure, with experiments showing gains on kriging, imputation and forecasting tasks.
Multivariate time series forecasting with latent graph inference
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
LTS-CG infers latent temporal sparse coordination graphs from historical observations to enable efficient, uncertainty-aware agent coordination in MARL with complexity linear in the number of agents.
citing papers explorer
-
AdaKernel: Learning Adaptive Kernel Parameters for Spatiotemporal Graph Neural Networks
AdaKernel learns adaptive kernel scale parameters inside GNNs for spatiotemporal data while preserving geometric structure, with experiments showing gains on kriging, imputation and forecasting tasks.
-
Inferring Latent Temporal Sparse Coordination Graph for Multi-Agent Reinforcement Learning
LTS-CG infers latent temporal sparse coordination graphs from historical observations to enable efficient, uncertainty-aware agent coordination in MARL with complexity linear in the number of agents.