no code implementations • 25 Mar 2024 • Jie Qiao, Yu Xiang, Zhengming Chen, Ruichu Cai, Zhifeng Hao
Fortunately, in this work, we found that the causal order from $X$ to its child $Y$ is identifiable if $X$ is a root vertex and has at least two directed paths to $Y$, or the ancestor of $X$ with the most directed path to $X$ has a directed path to $Y$ without passing $X$.
no code implementations • 7 Feb 2024 • Ruichu Cai, Siyang Huang, Jie Qiao, Wei Chen, Yan Zeng, Keli Zhang, Fuchun Sun, Yang Yu, Zhifeng Hao
As a key component to intuitive cognition and reasoning solutions in human intelligence, causal knowledge provides great potential for reinforcement learning (RL) agents' interpretability towards decision-making by helping reduce the searching space.
no code implementations • 21 Dec 2023 • Ruichu Cai, Yuxuan Zhu, Jie Qiao, Zefeng Liang, Furui Liu, Zhifeng Hao
By considering the underappreciated causal generating process, first, we pinpoint the source of the vulnerability of DNNs via the lens of causality, then give theoretical results to answer \emph{where to attack}.
no code implementations • 19 Dec 2023 • Jie Qiao, Zhengming Chen, Jianhua Yu, Ruichu Cai, Zhifeng Hao
With this observation, we aim to investigate the identification problem of learning causal structure from missing data under an additive noise model with different missingness mechanisms, where the `no self-masking missingness' assumption can be eliminated appropriately.
no code implementations • 25 Jun 2023 • Yuequn Liu, Ruichu Cai, Wei Chen, Jie Qiao, Yuguang Yan, Zijian Li, Keli Zhang, Zhifeng Hao
assumption is often violated due to the inherent dependencies among the event sequences.
1 code implementation • 10 May 2023 • Jie Qiao, Ruichu Cai, Siyu Wu, Yu Xiang, Keli Zhang, Zhifeng Hao
Learning causal structure among event types from discrete-time event sequences is a particularly important but challenging task.
no code implementations • 14 Dec 2022 • Ruichu Cai, Yuxuan Zhu, Xuexin Chen, Yuan Fang, Min Wu, Jie Qiao, Zhifeng Hao
To address the non-identifiability of PNS, we resort to a lower bound of PNS that can be optimized via counterfactual estimation, and propose a framework of Necessary and Sufficient Explanation for GNN (NSEG) via optimizing that lower bound.
1 code implementation • 13 Jan 2022 • Ruichu Cai, Fengzhu Wu, Zijian Li, Jie Qiao, Wei Chen, Yuexing Hao, Hao Gu
By explicitly Reconstructing Exposure STrategies (REST in short), we formalize the recommendation problem as the counterfactual reasoning and propose the debiased social recommendation method.
1 code implementation • 5 Jun 2021 • Weilin Chen, Jie Qiao, Ruichu Cai, Zhifeng Hao
Causal discovery from observational data is an important but challenging task in many scientific fields.
no code implementations • 23 May 2021 • Ruichu Cai, Siyu Wu, Jie Qiao, Zhifeng Hao, Keli Zhang, Xi Zhang
We further propose a causal structure learning method on THP in a likelihood framework.
1 code implementation • 22 Dec 2020 • Ruichu Cai, Zijian Li, Pengfei Wei, Jie Qiao, Kun Zhang, Zhifeng Hao
Different from previous efforts on the entangled feature space, we aim to extract the domain invariant semantic information in the latent disentangled semantic representation (DSR) of the data.
no code implementations • 28 Jun 2020 • Chunlong Luo, Tianqi Yu, Yufan Luo, Manqing Wang, Fuhai Yu, Yinhao Li, Chan Tian, Jie Qiao, Li Xiao
Previous methods only classify manually segmented single chromosome, which is far from clinical practice.
no code implementations • 30 Nov 2019 • Jie Qiao, Zijian Li, Boyan Xu, Ruichu Cai, Kun Zhang
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 et al., 2019).
no code implementations • 12 Oct 2019 • Li Xiao, Chunlong Luo, Tianqi Yu, Yufan Luo, Manqing Wang, Fuhai Yu, Yinhao Li, Chan Tian, Jie Qiao
Chromosome enumeration is an essential but tedious procedure in karyotyping analysis.
2 code implementations • 23 May 2019 • Ruichu Cai, Jie Qiao, Kun Zhang, Zhenjie Zhang, Zhifeng Hao
In this work, we propose a cascade nonlinear additive noise model to represent such causal influences--each direct causal relation follows the nonlinear additive noise model but we observe only the initial cause and final effect.
no code implementations • NeurIPS 2018 • Ruichu Cai, Jie Qiao, Kun Zhang, Zhenjie Zhang, Zhifeng Hao
In this paper we make an attempt to find a way to solve this problem by assuming a two-stage causal process: the first stage maps the cause to a hidden variable of a lower cardinality, and the second stage generates the effect from the hidden representation.