1 code implementation • 30 Apr 2024 • Haoxuan Li, Chunyuan Zheng, Sihao Ding, Peng Wu, Zhi Geng, Fuli Feng, Xiangnan He
On this basis, we propose a novel ideal loss that can be used to deal with selection bias in the presence of neighborhood effect.
1 code implementation • 30 Apr 2024 • Haoxuan Li, Chunyuan Zheng, Yanghao Xiao, Peng Wu, Zhi Geng, Xu Chen, Peng Cui
Inspired by these gaps, we propose to approximate the balancing functions in reproducing kernel Hilbert space and demonstrate that, based on the universal property and representer theorem of kernel functions, the causal balancing constraints can be better satisfied.
no code implementations • 9 Aug 2023 • Shanshan Huang, Haoxuan Li, Qingsong Li, Chunyuan Zheng, Li Liu
Multimedia recommendation involves personalized ranking tasks, where multimedia content is usually represented using a generic encoder.
1 code implementation • 3 Aug 2023 • Haoxuan Li, Taojun Hu, Zetong Xiong, Chunyuan Zheng, Fuli Feng, Xiangnan He, Xiao-Hua Zhou
Adverse drug reaction (ADR) prediction plays a crucial role in both health care and drug discovery for reducing patient mortality and enhancing drug safety.
no code implementations • 17 Apr 2023 • Haoxuan Li, Yanghao Xiao, Chunyuan Zheng, Peng Wu
Recommender systems are seen as an effective tool to address information overload, but it is widely known that the presence of various biases makes direct training on large-scale observational data result in sub-optimal prediction performance.
no code implementations • 10 May 2022 • Haoxuan Li, Chunyuan Zheng, Peng Wu
However, in this paper, we show that DR methods are unstable and have unbounded bias, variance, and generalization bounds to extremely small propensities.
no code implementations • 19 Mar 2022 • Haoxuan Li, Yan Lyu, Chunyuan Zheng, Peng Wu
Bias is a common problem inherent in recommender systems, which is entangled with users' preferences and poses a great challenge to unbiased learning.