124 citations · 181 across the 29 of their papers we have counts for
22 papers · 1 filter
CDFM: Towards a General-Purpose Causal Discovery Foundation Model
Jie Qiao, Ruichu Cai, Zijian Li +6
Causal discovery, the process of recovering underlying causal structures from observational data, is a fundamental pursuit across scientific disciplines. Over the past decades, num…
Rethinking Zero-Shot Time Series Classification: From Task-specific Classifiers to In-Context Inference
Juntao Fang, Shifeng Xie, Shengbin Nie +7
The zero-shot evaluation of time series foundation models (TSFMs) for classification typically uses a frozen encoder followed by a task-specific classifier. However, this practice…
Temporal Latent Variable Structural Causal Model for Causal Discovery under External Interferences
Ruichu Cai, Xiaokai Huang, Wei Chen +2
Inferring causal relationships from observed data is an important task, yet it becomes challenging when the data is subject to various external interferences. Most of these interfe…
Long-Term Individual Causal Effect Estimation via Identifiable Latent Representation Learning
Ruichu Cai, Junjie Wan, Weilin Chen +4
Estimating long-term causal effects by combining long-term observational and short-term experimental data is a crucial but challenging problem in many real-world scenarios. In exis…
Interpretable High-order Knowledge Graph Neural Network for Predicting Synthetic Lethality in Human Cancers
Xuexin Chen, Ruichu Cai, Zhengting Huang +3
Synthetic lethality (SL) is a promising gene interaction for cancer therapy. Recent SL prediction methods integrate knowledge graphs (KGs) into graph neural networks (GNNs) and emp…
Time Series Domain Adaptation via Latent Invariant Causal Mechanism
Ruichu Cai, Junxian Huang, Zhenhui Yang +4
Time series domain adaptation aims to transfer the complex temporal dependence from the labeled source domain to the unlabeled target domain. Recent advances leverage the stable ca…
Disentangling Long-Short Term State Under Unknown Interventions for Online Time Series Forecasting
Ruichu Cai, Haiqin Huang, Zhifang Jiang +5
Current methods for time series forecasting struggle in the online scenario, since it is difficult to preserve long-term dependency while adapting short-term changes when data are…
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…
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…
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…
Identifying Semantic Component for Robust Molecular Property Prediction
Zijian Li, Zunhong Xu, Ruichu Cai +5
Although graph neural networks have achieved great success in the task of molecular property prediction in recent years, their generalization ability under out-of-distribution (OOD…
Subspace Identification for Multi-Source Domain Adaptation
Zijian Li, Ruichu Cai, Guangyi Chen +3
Multi-source domain adaptation (MSDA) methods aim to transfer knowledge from multiple labeled source domains to an unlabeled target domain. Although current methods achieve target…
TNPAR: Topological Neural Poisson Auto-Regressive Model for Learning Granger Causal Structure from Event Sequences
Yuequn Liu, Ruichu Cai, Wei Chen +5
Learning Granger causality from event sequences is a challenging but essential task across various applications. Most existing methods rely on the assumption that event sequences a…
Time-Series Domain Adaptation via Sparse Associative Structure Alignment: Learning Invariance and Variance
Zijian Li, Ruichu Cai, Jiawei Chen +4
Domain adaptation on time-series data is often encountered in the industry but received limited attention in academia. Most of the existing domain adaptation methods for time-serie…
REST: Debiased Social Recommendation via Reconstructing Exposure Strategies
Ruichu Cai, Fengzhu Wu, Zijian Li +4
The recommendation system, relying on historical observational data to model the complex relationships among the users and items, has achieved great success in real-world applicati…
Motif Graph Neural Network
Xuexin Chen, Ruichu Cai, Yuan Fang +3
Graphs can model complicated interactions between entities, which naturally emerge in many important applications. These applications can often be cast into standard graph learning…
Aggregating From Multiple Target-Shifted Sources
Changjian Shui, Zijian Li, Jiaqi Li +3
Multi-source domain adaptation aims at leveraging the knowledge from multiple tasks for predicting a related target domain. Hence, a crucial aspect is to properly combine different…
Graph Domain Adaptation: A Generative View
Ruichu Cai, Fengzhu Wu, Zijian Li +3
Recent years have witnessed tremendous interest in deep learning on graph-structured data. Due to the high cost of collecting labeled graph-structured data, domain adaptation is im…
Time Series Domain Adaptation via Sparse Associative Structure Alignment
Ruichu Cai, Jiawei Chen, Zijian Li +6
Domain adaptation on time series data is an important but challenging task. Most of the existing works in this area are based on the learning of the domain-invariant representation…
Disentanglement Challenge: From Regularization to Reconstruction
Jie Qiao, Zijian Li, Boyan Xu +2
The challenge of learning disentangled representation has recently attracted much attention and boils down to a competition using a new real world disentanglement dataset (Gondal e…