DPR: An Algorithm Mitigate Bias Accumulation in Recommendation feedback loops

no code implementations • 10 Nov 2023 • Hangtong Xu, Yuanbo Xu, Yongjian Yang, Fuzhen Zhuang, Hui Xiong

We demonstrate theoretically that our approach mitigates the negative effects of feedback loops and unknown exposure mechanisms.

Recommendation Systems

Causal Structure Representation Learning of Confounders in Latent Space for Recommendation

no code implementations • 2 Nov 2023 • Hangtong Xu, Yuanbo Xu, Yongjian Yang

Specifically, we consider the influence of confounders, disentangle them from user preferences in the latent space, and employ causal graphs to model their interdependencies without specific labels.

Recommendation Systems Representation Learning +1

Separating and Learning Latent Confounders to Enhancing User Preferences Modeling

no code implementations • 2 Nov 2023 • Hangtong Xu, Yuanbo Xu, Yongjian Yang

Recommender models aim to capture user preferences from historical feedback and then predict user-specific feedback on candidate items.

counterfactual Recommendation Systems