ADAG pre-trains a linear transformer to map observed data from many related tasks directly to DAG adjacency matrices, enabling fast zero-shot causal discovery on new order-consistent or heterogeneous datasets.
Hyperparameters, including sparsity constraint coefficients and thresholds, are extensively tuned 15 to optimize SHD performance
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Causal Graphs at Scale: A Foundation Model Approach
ADAG pre-trains a linear transformer to map observed data from many related tasks directly to DAG adjacency matrices, enabling fast zero-shot causal discovery on new order-consistent or heterogeneous datasets.