26 citations · 69 across the 20 of their papers we have counts for
22 papers
CausalWAM: Learning the Causes of Actions in World Action Models
Juntao Cheng, Jinzhou Tang, Fan Feng +2
World action models (WAMs) learn latent variables from observations and use these to both predict the evolution of the scene and to generate actions. The prediction has to be of th…
Towards Identifiable Representations under Misspecified Structure
Yuke Li, Yujia Zheng, Ziyi Chen +2
The presence of noise that depends on the latent variables poses a fundamental challenge to identifiability. Existing results rely on conditional independence among the observation…
Hessian Rank Constraint for Learning Structure of Nonlinear Latent Variable Models
Zijian Li, Ruichu Cai, Feng Xie +7
Uncovering latent variables and their causal relations from observed data is a fundamental yet challenging problem. Existing methods often rely on restrictive assumptions, such as…
Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data
Shikai Qiu, Marc Finzi, Yujia Zheng +2
Compression is fundamental to intelligence. A model that can represent its training data as a short code has discovered regularities that enable generalization. Large neural networ…
Causal Discovery in the Era of Agents
Yujia Zheng, Vishal Verma, Mantej Gill +3
Recent attempts to combine large language models (LLMs) with causal discovery ask models to infer pairwise directions, propose graph structures, or inject language-model outputs as…
On the Identifiability of Sparse ICA without Assuming Non-Gaussianity
Ignavier Ng, Yujia Zheng, Xinshuai Dong +1
Independent component analysis (ICA) is a fundamental statistical tool used to reveal hidden generative processes from observed data. However, traditional ICA approaches struggle w…
Local Causal Discovery with Linear non-Gaussian Cyclic Models
Haoyue Dai, Ignavier Ng, Yujia Zheng +2
Local causal discovery is of great practical significance, as there are often situations where the discovery of the global causal structure is unnecessary, and the interest lies so…
Causal Representation Learning from Multiple Distributions: A General Setting
Kun Zhang, Shaoan Xie, Ignavier Ng +1
In many problems, the measured variables (e.g., image pixels) are just mathematical functions of the latent causal variables (e.g., the underlying concepts or objects). For the pur…
A Versatile Causal Discovery Framework to Allow Causally-Related Hidden Variables
Xinshuai Dong, Biwei Huang, Ignavier Ng +6
Most existing causal discovery methods rely on the assumption of no latent confounders, limiting their applicability in solving real-life problems. In this paper, we introduce a no…
Generalizing Nonlinear ICA Beyond Structural Sparsity
Yujia Zheng, Kun Zhang
Nonlinear independent component analysis (ICA) aims to uncover the true latent sources from their observable nonlinear mixtures. Despite its significance, the identifiability of no…
Causal-learn: Causal Discovery in Python
Yujia Zheng, Biwei Huang, Wei Chen +6
Causal discovery aims at revealing causal relations from observational data, which is a fundamental task in science and engineering. We describe , an open-so…
Partial Identifiability for Domain Adaptation
Lingjing Kong, Shaoan Xie, Weiran Yao +5
Unsupervised domain adaptation is critical to many real-world applications where label information is unavailable in the target domain. In general, without further assumptions, the…
Generalized Precision Matrix for Scalable Estimation of Nonparametric Markov Networks
Yujia Zheng, Ignavier Ng, Yewen Fan +1
A Markov network characterizes the conditional independence structure, or Markov property, among a set of random variables. Existing work focuses on specific families of distributi…
Whole Page Unbiased Learning to Rank
Haitao Mao, Lixin Zou, Yujia Zheng +5
The page presentation biases in the information retrieval system, especially on the click behavior, is a well-known challenge that hinders improving ranking models' performance wit…
On the Identifiability of Nonlinear ICA: Sparsity and Beyond
Yujia Zheng, Ignavier Ng, Kun Zhang
Nonlinear independent component analysis (ICA) aims to recover the underlying independent latent sources from their observable nonlinear mixtures. How to make the nonlinear ICA mod…
Reliable Causal Discovery with Improved Exact Search and Weaker Assumptions
Ignavier Ng, Yujia Zheng, Jiji Zhang +1
Many of the causal discovery methods rely on the faithfulness assumption to guarantee asymptotic correctness. However, the assumption can be approximately violated in many ways, le…
Learning Elastic Embeddings for Customizing On-Device Recommenders
Tong Chen, Hongzhi Yin, Yujia Zheng +3
In today's context, deploying data-driven services like recommendation on edge devices instead of cloud servers becomes increasingly attractive due to privacy and network latency c…
Cold-start Sequential Recommendation via Meta Learner
Yujia Zheng, Siyi Liu, Zekun Li +1
This paper explores meta-learning in sequential recommendation to alleviate the item cold-start problem. Sequential recommendation aims to capture user's dynamic preferences based…
Heterogeneous Graph Collaborative Filtering
Zekun Li, Yujia Zheng, Shu Wu +2
Graph-based collaborative filtering (CF) algorithms have gained increasing attention. Existing work in this literature usually models the user-item interactions as a bipartite grap…
DGTN: Dual-channel Graph Transition Network for Session-based Recommendation
Yujia Zheng, Siyi Liu, Zekun Li +1
The task of session-based recommendation is to predict user actions based on anonymous sessions. Recent research mainly models the target session as a sequence or a graph to captur…
Long-tail Session-based Recommendation
Siyi Liu, Yujia Zheng
Session-based recommendation focuses on the prediction of user actions based on anonymous sessions and is a necessary method in the lack of user historical data. However, none of t…
Balancing Multi-level Interactions for Session-based Recommendation
Yujia Zheng, Siyi Liu, Zailei Zhou
Predicting user actions based on anonymous sessions is a challenge to general recommendation systems because the lack of user profiles heavily limits data-driven models. Recently,…