Feature Matching Intervention: Leveraging Observational Data for Causal Representation Learning
This addresses a major bottleneck in causal discovery for researchers and practitioners relying on observational data, offering a novel method to improve causal representation learning.
The paper tackles the challenge of distinguishing causal from spurious features in observational data by proposing Feature Matching Intervention (FMI), which mimics perfect interventions through a matching procedure, resulting in strong out-of-distribution generalizability and superior performance in identifying causal features.
A major challenge in causal discovery from observational data is the absence of perfect interventions, making it difficult to distinguish causal features from spurious ones. We propose an innovative approach, Feature Matching Intervention (FMI), which uses a matching procedure to mimic perfect interventions. We define causal latent graphs, extending structural causal models to latent feature space, providing a framework that connects FMI with causal graph learning. Our feature matching procedure emulates perfect interventions within these causal latent graphs. Theoretical results demonstrate that FMI exhibits strong out-of-distribution (OOD) generalizability. Experiments further highlight FMI's superior performance in effectively identifying causal features solely from observational data.