Pith. sign in

REVIEW 1 cited by

Cycle-Balanced Representation Learning For Counterfactual Inference

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 2110.15484 v1 pith:6UO2CCZR submitted 2021-10-29 cs.LG cs.AI

classification cs.LGcs.AI
keywords counterfactualrepresentationdatainferencelearningcbrecycle-balancedgroups
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

With the widespread accumulation of observational data, researchers obtain a new direction to learn counterfactual effects in many domains (e.g., health care and computational advertising) without Randomized Controlled Trials(RCTs). However, observational data suffer from inherent missing counterfactual outcomes, and distribution discrepancy between treatment and control groups due to behaviour preference. Motivated by recent advances of representation learning in the field of domain adaptation, we propose a novel framework based on Cycle-Balanced REpresentation learning for counterfactual inference (CBRE), to solve above problems. Specifically, we realize a robust balanced representation for different groups using adversarial training, and meanwhile construct an information loop, such that preserve original data properties cyclically, which reduces information loss when transforming data into latent representation space.Experimental results on three real-world datasets demonstrate that CBRE matches/outperforms the state-of-the-art methods, and it has a great potential to be applied to counterfactual inference.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Asymmetrical Latent Representation for Individual Treatment Effect Modeling

    cs.LG 2025-01 conditional novelty 6.0 of 10

    ALRITE learns two separate latent spaces, one for predicting treated counterfactuals and one for control counterfactuals, and combines them with an X-learner style weighting to estimate conditional average treatment effects.

Pith tools