In recent years, spatio-temporal (ST) deep models have become increasingly powerful. We build larger models, learn richer representations, and achieve strong performance across many tasks. At the same time, as these models are expected to be more interpretable and more reliable for supporting …

In our NeurIPS 2023 paper “Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatment”, we introduce CaST, a causal framework designed to tackle two key challenges in spatio-temporal graph forecasting: temporal distribution shifts and dynamic spatial causation. We are truly grateful …

Note: This blog is written based on my own understanding of concepts discussed in Weak Theory, Weak Modernism, Thinking Sideways: A Plea for “Weak Theory" and Weak Theory—A Report on the Contemporary. This blog is more like a self learning note summarizing key concepts and the original …

[The Github repo can be found here!]

This is a curated collection of papers on the intersection of causality (including causal inference and causal discovery), spatio-temporal data (including spatio-temporal graph/series data, grid data, and trajectory data), and machine learning. For clarity, …