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

  title={A Model-Agnostic Causal Learning Framework for Recommendation using Search Data},
  author={Zihua Si and Xue-Fen Han and Xiao Zhang and Jun Xu and Yue Yin and Yang Song and Jirong Wen},
  journal={Proceedings of the ACM Web Conference 2022},
Machine-learning based recommender system(RS) 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… 

Figures and Tables from this paper

Causal Inference in Recommender Systems: A Survey and Future Directions

This survey comprehensively review the existing work of causal inference-based recommendation, based on a taxonomy of what kind of problem causal inference addresses, and presents the fundamental concepts of both recommendation and causal inference as the basis of later content.

Causal Intervention for Fairness in Multi-behavior Recommendation

This work examines causal relationships behind the interaction generation procedure in multi-behavior recommendation and proposes a causal framework to estimate the causal effect, which leverages backdoor adjustment to block the backdoor paths caused by the confounders.



Learning a Joint Search and Recommendation Model from User-Item Interactions

inspired by the neural approaches to collaborative filtering and the language modeling approaches to information retrieval, this model is jointly optimized to predict user-item interactions and reconstruct the item textual descriptions.

Deep Item-based Collaborative Filtering for Top-N Recommendation

This article proposes a more expressive ICF solution by accounting for the nonlinear and higher-order relationships among items, and treats this solution as a deep variant of ICF, thus term it as DeepICF.

Learning Fair Representations for Recommendation: A Graph-based Perspective

  • Le Wu
  • Computer Science
  • 2021
This paper proposes a novel graph based technique for ensuring fairness of any recommendation models, and extensive experimental results clearly show the effectiveness of the proposed model for fair recommendation.

Disentangling User Interest and Conformity for Recommendation with Causal Embedding

DICE is presented, a general framework that learns representations where interest and conformity are structurally disentangled, and various backbone recommendation models could be smoothly integrated, and it is shown that DICE guarantees the robustness and interpretability of recommendation.

USER: A Unified Information Search and Recommendation Model based on Integrated Behavior Sequence

The Unified Information SEarch and Recommendation model (USER), which mines user interests from the integrated sequence and accomplish the two tasks in a unified way and outperforms separate search and recommendation baselines is designed.

Causal embeddings for recommendation

A new domain adaptation algorithm is proposed that learns from logged data containing outcomes from a biased recommendation policy and predicts recommendation outcomes according to random exposure, and is shown to be equivalent to learning to predict recommendation outcomes under a fully random recommendation policy.

Joint Modeling and Optimization of Search and Recommendation

A general framework that simultaneously learns a retrieval model and a recommendation model by optimizing a joint loss function is proposed and preliminary results indicate that the proposed joint modeling substantially outperforms the retrieval and recommendation models trained independently.

Zero-Shot Heterogeneous Transfer Learning from Recommender Systems to Cold-Start Search Retrieval

This paper proposes a new Zero-Shot Heterogeneous Transfer Learning framework that transfers learned knowledge from the recommender system component to improve the search component of a content platform and demonstrates that the proposed approach can achieve high performance on offline search retrieval tasks, and achieved significant improvements on relevance and user interactions over the highly-optimized production system in online experiments.

Causal Inference for Recommender Systems

This work develops an algorithm that leverages classical recommendation models for causal recommendation and demonstrates that the proposed algorithm is more robust to unobserved confounders and improves recommendation.

Causal Intervention for Leveraging Popularity Bias in Recommendation

A new training and inference paradigm for recommendation named Popularity-bias Deconfounding and Adjusting (PDA) is proposed, which removes the confounding popularity bias in model training and adjusts the recommendation score with desired popularity bias via causal intervention.