One-Shot Multi-Label Causal Discovery in High-Dimensional Event Sequences
This enables practical scientific diagnostics at production scale in domains like healthcare, cybersecurity, or vehicle diagnostics, though it appears incremental as it builds on existing Transformer-based methods.
The paper tackles the problem of scaling causal discovery in high-dimensional event sequences with thousands of sparse event types, presenting OSCAR, a one-shot method that recovers interpretable causal structures in minutes on a real-world automotive dataset with 29,100 events and 474 labels, while classical methods fail to scale.
Understanding causality in event sequences with thousands of sparse event types is critical in domains such as healthcare, cybersecurity, or vehicle diagnostics, yet current methods fail to scale. We present OSCAR, a one-shot causal autoregressive method that infers per-sequence Markov Boundaries using two pretrained Transformers as density estimators. This enables efficient, parallel causal discovery without costly global CI testing. On a real-world automotive dataset with 29,100 events and 474 labels, OSCAR recovers interpretable causal structures in minutes, while classical methods fail to scale, enabling practical scientific diagnostics at production scale.