Pith. sign in

REVIEW 2 cited by

Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systems

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2206.06169 v2 pith:ABUW7DVS submitted 2022-06-13 cs.LG cs.AIstat.ML

Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systems

classification cs.LG cs.AIstat.ML
keywords causaleffectsinstantaneoustemporalvariablesicitrislearningobservations
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Causal representation learning is the task of identifying the underlying causal variables and their relations from high-dimensional observations, such as images. Recent work has shown that one can reconstruct the causal variables from temporal sequences of observations under the assumption that there are no instantaneous causal relations between them. In practical applications, however, our measurement or frame rate might be slower than many of the causal effects. This effectively creates "instantaneous" effects and invalidates previous identifiability results. To address this issue, we propose iCITRIS, a causal representation learning method that allows for instantaneous effects in intervened temporal sequences when intervention targets can be observed, e.g., as actions of an agent. iCITRIS identifies the potentially multidimensional causal variables from temporal observations, while simultaneously using a differentiable causal discovery method to learn their causal graph. In experiments on three datasets of interactive systems, iCITRIS accurately identifies the causal variables and their causal graph.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. What Makes a Representation Good for Single-Cell Perturbation Prediction?

    cs.LG 2026-05 unverdicted novelty 6.0

    PerturbedVAE disentangles perturbation-specific signals from invariant gene expression structure to recover causal representations and improve out-of-distribution prediction in single-cell perturbation modeling.

  2. Learning Latent Dynamical Causal Processes for Single-Cell Perturbation Prediction

    cs.LG 2026-05 unverdicted novelty 5.0

    Proposes CITE-VAE, a latent dynamical causal VAE with identifiability analysis for single-cell perturbation prediction, claiming better OOD generalization on CRISPR data.