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.
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.
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.
no code implementations • 16 Aug 2023 • Jialei Chen, Yuanbo Xu, Pengyang Wang, Yongjian Yang
Existing statistical methods model the MNAR mechanism by different decomposition of the joint distribution of the complete data and the missing mask.
1 code implementation • 24 May 2023 • Yiheng Jiang, Yuanbo Xu, Yongjian Yang, Funing Yang, Pengyang Wang, Hui Xiong
In this paper, we present a MLP-like architecture for sequential recommendation, namely TriMLP, with a novel Triangular Mixer for cross-token communications.
no code implementations • 19 May 2022 • Yuanbo Xu, En Wang, Yongjian Yang, Yi Chang
On the other hand, ME models directly employ inner products as a default loss function metric that cannot project users and items into a proper latent space, which is a methodological disadvantage.
no code implementations • 19 May 2022 • Yuanbo Xu, Yongjian Yang, En Wang, Fuzhen Zhuang, Hui Xiong
2) the PMU detection model should take both ratings and reviews into consideration, which makes PMU detection a multi-modal problem.
1 code implementation • 28 Apr 2022 • Mingrui Ma, Lei Song, Yuanbo Xu, Guixia Liu
Medical image registration is a fundamental and critical task in medical image analysis.
no code implementations • 27 Apr 2022 • Yuanbo Xu, Yongjian Yang, En Wang
Classical accuracy-oriented Recommender Systems (RSs) typically face the cold-start problem and the filter-bubble problem when users suffer the familiar, repeated, and even predictable recommendations, making them boring and unsatisfied.