Deep Causal Reasoning for Recommendations
- URL: http://arxiv.org/abs/2201.02088v1
- Date: Thu, 6 Jan 2022 15:00:01 GMT
- Title: Deep Causal Reasoning for Recommendations
- Authors: Yaochen Zhu, Jing Yi, Jiayi Xie and Zhenzhong Chen
- Abstract summary: A new trend in recommender system research is to negate the influence of confounders from a causal perspective.
We model the recommendation as a multi-cause multi-outcome (MCMO) inference problem.
We show that MCMO modeling may lead to high variance due to scarce observations associated with the high-dimensional causal space.
- Score: 47.83224399498504
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Traditional recommender systems aim to estimate a user's rating to an item
based on observed ratings from the population. As with all observational
studies, hidden confounders, which are factors that affect both item exposures
and user ratings, lead to a systematic bias in the estimation. Consequently, a
new trend in recommender system research is to negate the influence of
confounders from a causal perspective. Observing that confounders in
recommendations are usually shared among items and are therefore multi-cause
confounders, we model the recommendation as a multi-cause multi-outcome (MCMO)
inference problem. Specifically, to remedy confounding bias, we estimate
user-specific latent variables that render the item exposures independent
Bernoulli trials. The generative distribution is parameterized by a DNN with
factorized logistic likelihood and the intractable posteriors are estimated by
variational inference. Controlling these factors as substitute confounders,
under mild assumptions, can eliminate the bias incurred by multi-cause
confounders. Furthermore, we show that MCMO modeling may lead to high variance
due to scarce observations associated with the high-dimensional causal space.
Fortunately, we theoretically demonstrate that introducing user features as
pre-treatment variables can substantially improve sample efficiency and
alleviate overfitting. Empirical studies on simulated and real-world datasets
show that the proposed deep causal recommender shows more robustness to
unobserved confounders than state-of-the-art causal recommenders. Codes and
datasets are released at https://github.com/yaochenzhu/deep-deconf.
Related papers
- Estimating Treatment Effects under Recommender Interference: A Structured Neural Networks Approach [13.208141830901845]
We show that the standard difference-in-means estimator can lead to biased estimates due to recommender interference.
We propose a "recommender choice model" that describes which item gets exposed from a pool containing both treated and control items.
We show that the proposed estimator yields results comparable to the benchmark, whereas the standard difference-in-means estimator can exhibit significant bias and even produce reversed signs.
arXiv Detail & Related papers (2024-06-20T14:53:26Z) - Causal Distillation for Alleviating Performance Heterogeneity in Recommender Systems [142.3424649008479]
We show the uneven distribution of historical interactions and the biased training of recommender models.
The key to debiased training lies in eliminating the effect of confounders that influence both the user's historical behaviors and the next behavior.
We propose a causal multi-teacher distillation framework (CausalD) to address unobserved confounders.
arXiv Detail & Related papers (2024-05-31T05:31:00Z) - Source Echo Chamber: Exploring the Escalation of Source Bias in User, Data, and Recommender System Feedback Loop [65.23044868332693]
We investigate the impact of source bias on the realm of recommender systems.
We show the prevalence of source bias and reveal a potential digital echo chamber with source bias amplification.
We introduce a black-box debiasing method that maintains model impartiality towards both HGC and AIGC.
arXiv Detail & Related papers (2024-05-28T09:34:50Z) - Exploring Popularity Bias in Session-based Recommendation [0.6798775532273751]
We extend the analysis to session-based setup and adapted propensity calculation to the unique characteristics of session-based recommendation tasks.
We study the distributions of propensity and different stratification techniques on different datasets and find that propensity-related traits are actually dataset-specific.
arXiv Detail & Related papers (2023-12-13T02:48:35Z) - Causal Structure Representation Learning of Confounders in Latent Space
for Recommendation [6.839357057621987]
Inferring user preferences from the historical feedback of users is a valuable problem in recommender systems.
We consider the influence of confounders, disentangle them from user preferences in the latent space, and employ causal graphs to model their interdependencies.
arXiv Detail & Related papers (2023-11-02T08:46:07Z) - Causal Disentangled Variational Auto-Encoder for Preference
Understanding in Recommendation [50.93536377097659]
This paper introduces the Causal Disentangled Variational Auto-Encoder (CaD-VAE), a novel approach for learning causal disentangled representations from interaction data in recommender systems.
The approach utilizes structural causal models to generate causal representations that describe the causal relationship between latent factors.
arXiv Detail & Related papers (2023-04-17T00:10:56Z) - Rethinking Missing Data: Aleatoric Uncertainty-Aware Recommendation [59.500347564280204]
We propose a new Aleatoric Uncertainty-aware Recommendation (AUR) framework.
AUR consists of a new uncertainty estimator along with a normal recommender model.
As the chance of mislabeling reflects the potential of a pair, AUR makes recommendations according to the uncertainty.
arXiv Detail & Related papers (2022-09-22T04:32:51Z) - Debiased Recommendation with Neural Stratification [19.841871819722016]
We propose to cluster the users for computing more accurate IPS via increasing the exposure densities.
We conduct extensive experiments based on real-world datasets to demonstrate the effectiveness of the proposed method.
arXiv Detail & Related papers (2022-08-15T15:45:35Z) - Cross Pairwise Ranking for Unbiased Item Recommendation [57.71258289870123]
We develop a new learning paradigm named Cross Pairwise Ranking (CPR)
CPR achieves unbiased recommendation without knowing the exposure mechanism.
We prove in theory that this way offsets the influence of user/item propensity on the learning.
arXiv Detail & Related papers (2022-04-26T09:20:27Z) - Be Causal: De-biasing Social Network Confounding in Recommendation [7.589060156056251]
In recommendation systems, the existence of the missing-not-at-random (MNAR) problem results in the selection bias issue.
Most of the existing approaches use models or re-weighting strategy on observed ratings to mimic the missing-at-random setting.
We propose an unbiased and robust method called DENC inspired by confounder analysis in causal inference.
arXiv Detail & Related papers (2021-05-17T12:38:59Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.