On the interventional consistency of autoencoders
Autoencoders have played a crucial role in the field of representation learning since its inception, proving to be a flexible learning scheme able to accommodate various notions of optimality of the representation. The now established idea of disentanglement and the recently popular perspective of causality in representation learning identify modularity and robustness to be essential characteristics of the optimal representation. In this work, we show that the current conceptual tools available to assess the quality of the representation against these criteria (e.g. latent traversals or disentanglement metrics) are inadequate. In this regard, we introduce the notion of \emph{interventional consistency} of a representation and argue that it is a desirable property of any disentangled representation. We develop a general training scheme for autoencoders that takes into account interventional consistency in the optimality condition. We present empirical evidence toward the validity of the approach on three different autoencoders, namely standard autoencoders (AE), variational autoencoders (VAE) and structural autoencoders (SAE). Another key finding in this work is that differentiating between information and structure in the latent space of autoencoders can increase the modularity and interpretability of the resulting representation.
Code (0)
등록된 구현이 없습니다.
Tasks
DisentanglementRepresentation LearningSimilar Papers 제목 키워드 기반
VACA: Design of Variational Graph Autoencoders for Interventional and Counterfactual Queries
In this paper, we introduce VACA, a novel class of variational graph autoencoders for causal inference in the absence of hidden confounders, when only observational data and the causal graph are available. Without making…
Causal InferencecounterfactualFairnessPermutation-based Causal Inference Algorithms with Interventions
Learning directed acyclic graphs using both observational and interventional data is now a fundamentally important problem due to recent technological developments in genomics that generate such single-cell gene expressi…
Causal InferenceVariational Causal Autoencoder for Interventional and Counterfactual Queries
We propose the Variational Causal Autoencoder (VCAUSE), a novel class of variational graph autoencoders for causal inference in the absence of hidden confounders, when only observational data and the causal graph are ava…
Causal InferencecounterfactualFairnessLinear Causal Discovery with Interventional Constraints
Incorporating causal knowledge and mechanisms is essential for refining causal models and improving downstream tasks such as designing new treatments. In this paper, we introduce a novel concept in causal discovery, term…
A Long Short-term Memory Based Recurrent Neural Network for Interventional MRI Reconstruction
Interventional magnetic resonance imaging (i-MRI) for surgical guidance could help visualize the interventional process such as deep brain stimulation (DBS), improving the surgery performance and patient outcome. Differe…
MRI Reconstruction