Causal representation learning from network data
By: Jifan Zhang, Michelle M. Li, Elena Zheleva
Potential Business Impact:
Finds hidden causes in complex systems.
Causal disentanglement from soft interventions is identifiable under the assumptions of linear interventional faithfulness and availability of both observational and interventional data. Previous research has looked into this problem from the perspective of i.i.d. data. Here, we develop a framework, GraCE-VAE, for non-i.i.d. settings, in which structured context in the form of network data is available. GraCE-VAE integrates discrepancy-based variational autoencoders with graph neural networks to jointly recover the true latent causal graph and intervention effects. We show that the theoretical results of identifiability from i.i.d. data hold in our setup. We also empirically evaluate GraCE-VAE against state-of-the-art baselines on three genetic perturbation datasets to demonstrate the impact of leveraging structured context for causal disentanglement.
Similar Papers
Causally Fair Node Classification on Non-IID Graph Data
Machine Learning (CS)
Makes computer predictions fairer for everyone.
VAE-based Feature Disentanglement for Data Augmentation and Compression in Generalized GNSS Interference Classification
Machine Learning (CS)
Makes GPS signals work better by shrinking data.
Causal Intervention Framework for Variational Auto Encoder Mechanistic Interpretability
Machine Learning (CS)
Explains how AI creates images and sounds.