mlsanityData to 14 Oct 2026

Conditionally Identifiable Latent-Environment Modeling for Out-of-Distribution Recommendation

arXiv 2608.03647 ↗First posted 4 Aug 2026cs.IR cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Out-of-distribution (OOD) recommendation is vulnerable to preference shifts induced by a latent environment. Existing methods can infer latent states from logged interactions, yet the statistical meaning of the latent environment and its effect on preference remain underdetermined. We formulate this task as conditionally identifiable risk-aware recommendation (CI-RR) and propose Conditionally Identifiable Latent-Environment Recommendation (CILER). CILER uses a user-conditioned exponential family to model the latent environment and a feature-indexed polynomial to specify how it changes preference. It predicts by marginalizing item probabilities over the inferred environment distribution. Under sufficient variation, correct specification, and decoder regularity, CILER identifies the environment-sensitive representation up to the stated equivalence class. We further bound excess deployment log-risk by environment-inference error. Controlled studies test the observable consequences of sufficient variation and model specification. Experiments on three datasets show that CILER improves all twelve OOD ranking metrics under feature, temporal, and geographical shifts within shared support.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 31 of its 51 references that are in the map. First posted on arXiv 4 Aug 2026.

Builds on

31 of 51 references.

References · 31

  1. 2019Invariant Risk Minimizationcited by 1,854
  2. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 941
  3. 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 752
  4. 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 503
  5. 2018Variational Autoencoders for Collaborative Filteringcited by 310
  6. 2020Environment Inference for Invariant Learningcited by 306
  7. 2018Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learningcited by 282
  8. 2021Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalizationcited by 220
  9. 2021Does Invariant Risk Minimization Capture Invariance?cited by 116
  10. 2019Learning Disentangled Representations for Recommendationcited by 110
  11. 2023Nonparametric Identifiability of Causal Representations from Unknown Interventionscited by 106
  12. 2023Learning Linear Causal Representations from Interventions under General Nonlinear Mixingcited by 92
19 more
  1. 2023Identifiability Guarantees for Causal Disentanglement from Soft Interventionscited by 84
  2. 2022CIRS: Bursting Filter Bubbles by Counterfactual Interactive Recommender Systemcited by 38
  3. 2022Identifying Weight-Variant Latent Causal Modelscited by 34
  4. 2024Score-based Causal Representation Learning: Linear and General Transformationscited by 27
  5. 2024Time-Series Forecasting for Out-of-Distribution Generalization Using Invariant Learningcited by 27
  6. 2023Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalizationcited by 26
  7. 2023Invariant Collaborative Filtering to Popularity Distribution Shiftcited by 23
  8. 2023Identifiable Latent Polynomial Causal Models Through the Lens of Changecited by 23
  9. 2022CausPref: Causal Preference Learning for Out-of-Distribution Recommendationcited by 17
  10. 2024Distributionally Robust Graph-based Recommendation Systemcited by 17
  11. 2024Dual Test-time Training for Out-of-distribution Recommender Systemcited by 16
  12. 2023Robust Collaborative Filtering to Popularity Distribution Shiftcited by 12
  13. 2024Graph Representation Learning via Causal Diffusion for Out-of-Distribution Recommendationcited by 11
  14. 2022The Missing Invariance Principle Found -- the Reciprocal Twin of Invariant Risk Minimizationcited by 8
  15. 2023Causal Disentangled Recommendation Against User Preference Shiftscited by 8
  16. 2026Causal Representation Learning from General Environments under Nonparametric Mixingcited by 5
  17. 2022Decorr: Environment Partitioning for Invariant Learning and OOD Generalizationcited by 3
  18. 2023Reformulating CTR Prediction: Learning Invariant Feature Interactions for Recommendationcited by 2
  19. 2024Invariant debiasing learning for recommendation via biased imputationcited by 2

Built on by

Not cited yet.