4 papers
Disentangled Double Machine Learning for Accurate Causal Effect Estimation
Guodu Xiang, Kui Yu, Yujie Wang +3
Confounding bias is a key challenge in causal effect estimation from observational data. Double Machine Learning (DML) addresses this issue by estimating treatment and outcome nuis…
PITE: Multi-Prototype Alignment for Individual Treatment Effect Estimation
Fuyuan Cao, Jiaxuan Zhang, Xiaoli Li
Estimating Individual Treatment Effects (ITE) from observational data is challenging due to confounding bias. Most studies tackle this bias by balancing distributions globally, but…
Few-Shot Identity Adaptation for 3D Talking Heads via Global Gaussian Field
Hong Nie, Fuyuan Cao, Lu Chen +3
Reconstruction and rendering-based talking head synthesis methods achieve high-quality results with strong identity preservation but are limited by their dependence on identity-spe…
Towards Effective Graph Rationalization via Boosting Environment Diversity
Yujie Wang, Kui Yu, Yuhong Zhang +2
Graph Neural Networks (GNNs) perform effectively when training and testing graphs are drawn from the same distribution, but struggle to generalize well in the face of distribution…