3 citations · 13 across the 34 of their papers we have counts for
13 papers · 1 filter
Unifying Invariant and Variant Features for Graph Out-of-Distribution via Probability of Necessity and Sufficiency
Xuexin Chen, Ruichu Cai, Kaitao Zheng +4
Graph Out-of-Distribution (OOD), requiring that models trained on biased data generalize to the unseen test data, has considerable real-world applications. One of the most mainstre…
Learning Discrete Latent Variable Structures with Tensor Rank Conditions
Zhengming Chen, Ruichu Cai, Feng Xie +5
Unobserved discrete data are ubiquitous in many scientific disciplines, and how to learn the causal structure of these latent variables is crucial for uncovering data patterns. Mos…
SGSL: Incorporating Segment to Syntactic Enhanced Graph Structure Learning for Aspect-based Sentiment Analysis
Bingfeng Chen, Qihan Ouyang, Yongqi Luo +3
Previous graph-based approaches in Aspect based Sentiment Analysis(ABSA) have demonstrated impressive performance by utilizing graph neural networks and attention mechanisms to lea…
Estimating Long-term Heterogeneous Dose-response Curve: Generalization Bound Leveraging Optimal Transport Weights
Zeqin Yang, Weilin Chen, Ruichu Cai +7
Long-term treatment effect estimation is a significant but challenging problem in many applications. Existing methods rely on ideal assumptions, such as no unobserved confounders o…
From Orthogonality to Dependency: Learning Disentangled Representation for Multi-Modal Time-Series Sensing Signals
Ruichu Cai, Zhifang Jiang, Zijian Li +6
Existing methods for multi-modal time series representation learning aim to disentangle the modality-shared and modality-specific latent variables. Although achieving notable perfo…
On the Identification of Temporally Causal Representation with Instantaneous Dependence
Zijian Li, Yifan Shen, Kaitao Zheng +5
Temporally causal representation learning aims to identify the latent causal process from time series observations, but most methods require the assumption that the latent causal p…
Doubly Robust Causal Effect Estimation under Networked Interference via Targeted Learning
Weilin Chen, Ruichu Cai, Zeqin Yang +4
Causal effect estimation under networked interference is an important but challenging problem. Available parametric methods are limited in their model space, while previous semipar…
Causal Discovery from Poisson Branching Structural Causal Model Using High-Order Cumulant with Path Analysis
Jie Qiao, Yu Xiang, Zhengming Chen +2
Count data naturally arise in many fields, such as finance, neuroscience, and epidemiology, and discovering causal structure among count data is a crucial task in various scientifi…
Debiased Model-based Interactive Recommendation
Zijian Li, Ruichu Cai, Haiqin Huang +4
Existing model-based interactive recommendation systems are trained by querying a world model to capture the user preference, but learning the world model from historical logged da…
Unifying Invariance and Spuriousity for Graph Out-of-Distribution via Probability of Necessity and Sufficiency
Xuexin Chen, Ruichu Cai, Kaitao Zheng +4
Graph Out-of-Distribution (OOD), requiring that models trained on biased data generalize to the unseen test data, has a massive of real-world applications. One of the most mainstre…
Nonstationary Time Series Forecasting via Unknown Distribution Adaptation
Zijian Li, Ruichu Cai, Zhenhui Yang +6
As environments evolve, temporal distribution shifts can degrade time series forecasting performance. A straightforward solution is to adapt to nonstationary changes while preservi…
Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanation
Xuexin Chen, Ruichu Cai, Zhengting Huang +5
We investigate the problem of explainability for machine learning models, focusing on Feature Attribution Methods (FAMs) that evaluate feature importance through perturbation tests…
Where and How to Attack? A Causality-Inspired Recipe for Generating Counterfactual Adversarial Examples
Ruichu Cai, Yuxuan Zhu, Jie Qiao +3
Deep neural networks (DNNs) have been demonstrated to be vulnerable to well-crafted \emph{adversarial examples}, which are generated through either well-conceived -n…