Low-rank graphs induce latents that form causal abstractions, with identifiability results and a practical objective enabling unsupervised learning of high-level SCMs from low-level measurements.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2representative citing papers
citing papers explorer
-
Unsupervised Causal Abstractions Discovery
Low-rank graphs induce latents that form causal abstractions, with identifiability results and a practical objective enabling unsupervised learning of high-level SCMs from low-level measurements.
- Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data