Auto IV: Counterfactual Prediction via Automatic Instrumental Variable Decomposition

Yuan, Junkun; Wu, Anpeng; Kuang, Kun; Li, Bo; Wu, Runze; Wu, Fei; Lin, Lanfen

doi:10.1145/3494568

Cited by 16 publications

(16 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, Hartford et al (2021) employs the closest cluster center of estimation points as an instrumental variable. Yuan et al (2022) generates IV presentations…”

Section: Generationmentioning

confidence: 99%

See 1 more Smart Citation

Distribution-Conditioned Adversarial Variational Autoencoder for Valid Instrumental Variable Generation

Li,

Yao

2024

AAAI

View full text Add to dashboard Cite

Instrumental variables (IVs), widely applied in economics and healthcare, enable consistent counterfactual prediction in the presence of hidden confounding factors, effectively addressing endogeneity issues. The prevailing IV-based counterfactual prediction methods typically rely on the availability of valid IVs (satisfying Relevance, Exclusivity, and Exogeneity), a requirement which often proves elusive in real-world scenarios. Various data-driven techniques are being developed to create valid IVs (or representations of IVs) from a pool of IV candidates. However, most of these techniques still necessitate the inclusion of valid IVs within the set of candidates. This paper proposes a distribution-conditioned adversarial variational autoencoder to tackle this challenge. Specifically: 1) for Relevance and Exclusivity, we deduce the corresponding evidence lower bound following the Bayesian network structure and build the variational autoencoder; accordingly, 2) for Exogeneity , we design an adversarial game to encourage latent factors originating from the marginal distribution, compelling the independence between IVs and other outcome-related factors. Extensive experimental results validate the effectiveness, stability and generality of our proposed model in generating valid IV factors in the absence of valid IV candidates.

show abstract

“…Furthermore, Hartford et al (2021) employs the closest cluster center of estimation points as an instrumental variable. Yuan et al (2022) generates IV presentations…”

Section: Generationmentioning

confidence: 99%

“…Extensive literature (Hartford et al 2021;Yuan et al 2022;Davies et al 2015;Burgess, Dudbridge, and Thompson 2016) has attempted to resolve this problem by generat-…”

Section: Introductionmentioning

confidence: 99%

Distribution-Conditioned Adversarial Variational Autoencoder for Valid Instrumental Variable Generation

Li,

Yao

2024

AAAI

View full text Add to dashboard Cite

show abstract

“…In most real-world applications, there is not a known IV. A few data-driven IV estimators have been developed for discovering a valid IV (Yuan, Wu et al 2022) or a synthesising IV (Burgess and Thompson 2013) or eliminating the influence of invalid IVs by using statistical strategies (Kang et al 2016;Guo, Kang et al 2018;Hartford et al 2021). For instance, the tetrad constraint is utilised by IV.Tetrad (Silva and Shimizu 2017) to validate the validity of a pair of CIVs for estimating causal effects from data in presence of latent confounders.…”

Section: Related Workmentioning

confidence: 99%

Causal Inference with Conditional Instruments Using Deep Generative Models

Cheng

et al. 2023

AAAI

View full text Add to dashboard Cite

The instrumental variable (IV) approach is a widely used way to estimate the causal effects of a treatment on an outcome of interest from observational data with latent confounders. A standard IV is expected to be related to the treatment variable and independent of all other variables in the system. However, it is challenging to search for a standard IV from data directly due to the strict conditions. The conditional IV (CIV) method has been proposed to allow a variable to be an instrument conditioning on a set of variables, allowing a wider choice of possible IVs and enabling broader practical applications of the IV approach. Nevertheless, there is not a data-driven method to discover a CIV and its conditioning set directly from data. To fill this gap, in this paper, we propose to learn the representations of the information of a CIV and its conditioning set from data with latent confounders for average causal effect estimation. By taking advantage of deep generative models, we develop a novel data-driven approach for simultaneously learning the representation of a CIV from measured variables and generating the representation of its conditioning set given measured variables. Extensive experiments on synthetic and real-world datasets show that our method outperforms the existing IV methods.

show abstract

“…Xu et al [36] provide an alternating training regime for 2SLS and attain good end-to-end performance in high dimensional image data and off-policy reinforcement learning tasks. Yuan et al [40] utilize mutual information to learn IV representation and confounder representation, which are used as inputs for two-stage regression with neural networks structure. In recommendation, causal learning has been used for tackling problem of the biases (e.g., position bias, popularity bias, selection bias etc.)…”

Section: Related Workmentioning

confidence: 99%

A Model-Agnostic Causal Learning Framework for Recommendation using Search Data

Si,

Han,

Zhang

et al. 2022

Preprint

View full text Add to dashboard Cite

Machine-learning based recommender systems(RSs) has become an effective means to help people automatically discover their interests. Existing models often represent the rich information for recommendation, such as items, users, and contexts, as embedding vectors and leverage them to predict users' feedback. In the view of causal analysis, the associations between these embedding vectors and users' feedback are a mixture of the causal part that describes why an item is preferred by a user, and the non-causal part that merely reflects the statistical dependencies between users and items, for example, the exposure mechanism, public opinions, display position, etc. However, existing RSs mostly ignored the striking differences between the causal parts and non-causal parts when using these embedding vectors. In this paper, we propose a model-agnostic framework named IV4Rec that can effectively decompose the embedding vectors into these two parts, hence enhancing recommendation results. Specifically, we jointly consider users' behaviors in search scenarios and recommendation scenarios. Adopting the concepts in causal analysis, we embed users' search behaviors as instrumental variables (IVs), to help decompose original embedding vectors in recommendation, i.e., treatments. IV4Rec then combines the two parts through deep neural networks and uses the combined results for recommendation. IV4Rec is modelagnostic and can be applied to a number of existing RSs such as DIN and NRHUB. Experimental results on both public and proprietary industrial datasets demonstrate that IV4Rec consistently enhances RSs and outperforms a framework that jointly considers search and recommendation. CCS CONCEPTS• Information systems → Recommender systems.

show abstract

Auto IV: Counterfactual Prediction via Automatic Instrumental Variable Decomposition

Cited by 16 publications

References 38 publications

Distribution-Conditioned Adversarial Variational Autoencoder for Valid Instrumental Variable Generation

Distribution-Conditioned Adversarial Variational Autoencoder for Valid Instrumental Variable Generation

Causal Inference with Conditional Instruments Using Deep Generative Models

A Model-Agnostic Causal Learning Framework for Recommendation using Search Data

Contact Info

Product

Resources

About