Causal Inference for Recommender Systems

Wang, Yixin; Liang, Dawen; Charlin, Laurent; Blei, David M.

doi:10.1145/3383313.3412225

Cited by 106 publications

(78 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The deconfounder: there have been notable efforts afoot to create a variable called a deconfounder [37, 107] that can substitute for substantive knowledge of the causal structure relative to the exposure and the out-come. It would be interesting to combine the best from both simulated and empirical components.…”

Section: Discussionmentioning

confidence: 99%

Using computable knowledge mined from the literature to elucidate confounders for EHR-based pharmacovigilance

Malec

Bernstam

Wei

et al. 2020

Preprint

View full text Add to dashboard Cite

Introduction: Confounding bias threatens the reliability of observational studies and poses a significant scientific challenge. This paper introduces a framework for identifying confounding factors by exploiting literature-derived computable knowledge. In previous work, we have shown that semantic constraint search over computable knowledge extracted from the literature can be useful for reducing confounding bias in statistical models of EHR-derived observational clinical data. We hypothesize that adjustment sets of literature-derived confounders could also improve causal inference. Methods: We introduce two methods (semantic vectors and string-based confounder search) that query the literature for potential confounders and use this information to build models from EHR-derived data to more accurately estimate causal effects. These methods search SemMedDB for indications TREATED BY the drug that is also known to CAUSE the adverse event. For evaluation, we attempt to rediscover associations in a publicly available reference dataset containing expected pairwise relationships between drugs and adverse events from empirical data derived from a corpus of 2.2M EHR-derived clinical notes. For our knowledge-base, we use SemMedDB, a database of computable knowledge mined from the biomedical literature. Using standard adjustment and causal inference procedures on dichotomous drug exposures, confounders, and adverse event outcomes, varying numbers of literature-derived confounders are combined with EHR data to predict and estimate causal effects in light of the literature-derived confounders. We then compare the performance of the new methods with naive ($\chi^2$, reporting odds ratio) measures of association. Results and Conclusions: Logistic regression with ten vector space-derived confounders achieved the most improvement with AUROC of 0.628 (95\% CI: [0.556,0.720]), compared with baseline $\chi^2$ 0.507 (95\% CI: [0.431,0.583]). Bias reduction was improved more often in modeling methods using more rather than less information, and using semantic vector rather than string-based search. We found computable knowledge useful for improving automated causal inference, and identified opportunities for further improvement, including a role for adjudicating literature-derived confounders by subject matter experts.

show abstract

Section: Discussionmentioning

confidence: 99%

Using computable knowledge mined from the literature to elucidate confounders for EHR-based pharmacovigilance

Malec

Bernstam

Wei

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Li et al [14] noticed that users' sensitive features may lead to unfair recommendations and thus developed causal graphs to deconfound the influence of sensitive features in recommendation; Wang et al [30] identified that user clicks may be influenced by item popularity and proposed a deconfounding method to alleviate the amplification of popularity bias. Many other research works are conducted to address different types of confounders, including but not limited to item popularity [2,7,13,35,[41][42][43], item exposure [1,9,27,33,34,38], user selection [16,19,28,30,31], and ranking positions [3,4,10,18,21,36].…”

Section: Related Workmentioning

confidence: 99%

“…• DCF [34]: The deconfounded recommendation model, which uses an exposure model to construct a substitute confounder and then conditions on the substitute confounder for modeling. • DCCF_ND: This is a no-deconfounding (ND) variant of our model.…”

Section: Baselinesmentioning

confidence: 99%

Deconfounded Causal Collaborative Filtering

Xu¹,

Tan²,

Heinecke³

et al. 2021

Preprint

View full text Add to dashboard Cite

Recommender systems may be confounded by various types of confounding factors (also called confounders) that may lead to inaccurate recommendations and sacrificed recommendation performance. Current approaches to solving the problem usually design each specific model for each specific confounder. However, realworld systems may include a huge number of confounders and thus designing each specific model for each specific confounder is unrealistic. More importantly, except for those "explicit confounders" that researchers can manually identify and process such as item's position in the ranking list, there are also many "latent confounders" that are beyond the imagination of researchers. For example, users' rating on a song may depend on their current mood or the current weather, and users' preference on ice creams may depend on the air temperature. Such latent confounders may be unobservable in the recorded training data. To solve the problem, we propose a deconfounded causal collaborative filtering model. We first frame user behaviors with unobserved confounders into a causal graph, and then we design a front-door adjustment model carefully fused with machine learning to deconfound the influence of unobserved confounders. The proposed model is able to handle both global confounders and personalized confounders. Experiments on real-world datasets show that our method is able to deconfound unobserved confounders to achieve better recommendation performance.

show abstract

“…That is, the entries are missing not at random (MNAR). To address the above challenges, there has been exciting recent progress on matrix completion with MNAR data, including Schnabel et al (2016); Ma and Chen (2019); Zhu et al (2019); Sportisse et al (2020a,b); Wang et al (2020); Yang et al (2021); Bhattacharya and Chatterjee (2021). Through numerous empirical studies, these works have shown that algorithms that account for MNAR data outperform conventional algorithms that are designed for MCAR data.…”

Section: Introductionmentioning

confidence: 99%

Causal Matrix Completion

Agarwal,

Dahleh,

Shah

et al. 2021

Preprint

View full text Add to dashboard Cite

Matrix completion is the study of recovering an underlying matrix from a sparse subset of noisy observations. Traditionally, it is assumed that the entries of the matrix are "missing completely at random" (MCAR), i.e., each entry is revealed at random, independent of everything else, with uniform probability. This is likely unrealistic due to the presence of "latent confounders", i.e., unobserved factors that determine both the entries of the underlying matrix and the missingness pattern in the observed matrix. For example, in the context of movie recommender systems-a canonical application for matrix completion-a user who vehemently dislikes horror films is unlikely to ever watch horror films. In general, these confounders yield "missing not at random" (MNAR) data, which can severely impact any inference procedure that does not correct for this bias.We develop a formal causal model for matrix completion through the language of potential outcomes, and provide novel identification arguments for a variety of causal estimands of interest. We design a procedure, which we call "synthetic nearest neighbors" (SNN), to estimate these causal estimands. We prove finite-sample consistency and asymptotic normality of our estimator. Our analysis also leads to new theoretical results for the matrix completion literature. In particular, we establish entry-wise, i.e., max-norm, finite-sample consistency and asymptotic normality results for matrix completion with MNAR data. As a special case, this also provides entry-wise bounds for matrix completion with MCAR data. Across simulated and real data, we demonstrate the efficacy of our proposed estimator.

show abstract

Causal Inference for Recommender Systems

Cited by 106 publications

References 15 publications

Using computable knowledge mined from the literature to elucidate confounders for EHR-based pharmacovigilance

Using computable knowledge mined from the literature to elucidate confounders for EHR-based pharmacovigilance

Deconfounded Causal Collaborative Filtering

Causal Matrix Completion

Contact Info

Product

Resources

About