175 citations · 1.2k across the 65 of their papers we have counts for
68 papers
Beyond the Shadows of Plato's Cave: Evaluating False Memory in Autonomous Agents via Counterfactual Reasoning
Quan M. Tran, Zhuo Huang, Zhen Fang +3
Autonomous agents increasingly rely on memory to generalize beyond their training environments. However, agents are bounded by what they have seen and believed, and leveraging such…
Discovering and Reasoning of Causality in the Hidden World with Large Language Models
Chenxi Liu, Yongqiang Chen, Tongliang Liu +4
Revealing hidden causal variables alongside the underlying causal mechanisms is essential to the development of science. Despite the progress in the past decades, existing practice…
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…
Diversity-enhancing Generative Network for Few-shot Hypothesis Adaptation
Ruijiang Dong, Feng Liu, Haoang Chi +5
Generating unlabeled data has been recently shown to help address the few-shot hypothesis adaptation (FHA) problem, where we aim to train a classifier for the target domain with a…
Learning World Models with Identifiable Factorization
Yu-Ren Liu, Biwei Huang, Zhengmao Zhu +4
Extracting a stable and compact representation of the environment is crucial for efficient reinforcement learning in high-dimensional, noisy, and non-stationary environments. Diffe…
Adaptive Edge-to-Edge Interaction Learning for Point Cloud Analysis
Shanshan Zhao, Mingming Gong, Xi Li +1
Recent years have witnessed the great success of deep learning on various point cloud analysis tasks, e.g., classification and semantic segmentation. Since point cloud data is spar…
Strength-Adaptive Adversarial Training
Chaojian Yu, Dawei Zhou, Li Shen +5
Adversarial training (AT) is proved to reliably improve network's robustness against adversarial data. However, current AT with a pre-specified perturbation budget has limitations…
Identifiability and Asymptotics in Learning Homogeneous Linear ODE Systems from Discrete Observations
Yuanyuan Wang, Wei Huang, Mingming Gong +4
Ordinary Differential Equations (ODEs) have recently gained a lot of attention in machine learning. However, the theoretical aspects, e.g., identifiability and asymptotic propertie…
On the Sparse DAG Structure Learning Based on Adaptive Lasso
Danru Xu, Erdun Gao, Wei Huang +3
Learning the underlying Bayesian Networks (BNs), represented by directed acyclic graphs (DAGs), of the concerned events from purely-observational data is a crucial part of evidenti…
Truncated Matrix Power Iteration for Differentiable DAG Learning
Zhen Zhang, Ignavier Ng, Dong Gong +5
Recovering underlying Directed Acyclic Graph (DAG) structures from observational data is highly challenging due to the combinatorial nature of the DAG-constrained optimization prob…
Latent Covariate Shift: Unlocking Partial Identifiability for Multi-Source Domain Adaptation
Yuhang Liu, Zhen Zhang, Dong Gong +5
Multi-source domain adaptation (MSDA) addresses the challenge of learning a label prediction function for an unlabeled target domain by leveraging both the labeled data from multip…
Identifying Weight-Variant Latent Causal Models
Yuhang Liu, Zhen Zhang, Dong Gong +5
The task of causal representation learning aims to uncover latent higher-level causal variables that affect lower-level observations. Identifying the true latent causal variables f…
MetaComp: Learning to Adapt for Online Depth Completion
Yang Chen, Shanshan Zhao, Wei Ji +2
Relying on deep supervised or self-supervised learning, previous methods for depth completion from paired single image and sparse depth data have achieved impressive performance in…
Detecting Deepfake by Creating Spatio-Temporal Regularity Disruption
Jiazhi Guan, Hang Zhou, Mingming Gong +3
Despite encouraging progress in deepfake detection, generalization to unseen forgery types remains a significant challenge due to the limited forgery clues explored during training…
Harnessing Out-Of-Distribution Examples via Augmenting Content and Style
Zhuo Huang, Xiaobo Xia, Li Shen +4
Machine learning models are vulnerable to Out-Of-Distribution (OOD) examples, and such a problem has drawn much attention. However, current methods lack a full understanding of dif…
Style Interleaved Learning for Generalizable Person Re-identification
Wentao Tan, Changxing Ding, Pengfei Wang +2
Domain generalization (DG) for person re-identification (ReID) is a challenging problem, as access to target domain data is not permitted during the training process. Most existing…
Adversarial Consistency for Single Domain Generalization in Medical Image Segmentation
Yanwu Xu, Shaoan Xie, Maxwell Reynolds +3
An organ segmentation method that can generalize to unseen contrasts and scanner settings can significantly reduce the need for retraining of deep learning models. Domain Generaliz…
Understanding Robust Overfitting of Adversarial Training and Beyond
Chaojian Yu, Bo Han, Li Shen +4
Robust overfitting widely exists in adversarial training of deep networks. The exact underlying reasons for this are still not completely understood. Here, we explore the causes of…
A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learning
Jixian Guo, Mingming Gong, Dacheng Tao
The generalization of model-based reinforcement learning (MBRL) methods to environments with unseen transition dynamics is an important yet challenging problem. Existing methods tr…
Counterfactual Fairness with Partially Known Causal Graph
Aoqi Zuo, Susan Wei, Tongliang Liu +3
Fair machine learning aims to avoid treating individuals or sub-populations unfavourably based on \textit{sensitive attributes}, such as gender and race. Those methods in fair mach…
MissDAG: Causal Discovery in the Presence of Missing Data with Continuous Additive Noise Models
Erdun Gao, Ignavier Ng, Mingming Gong +5
State-of-the-art causal discovery methods usually assume that the observational data is complete. However, the missing data problem is pervasive in many practical scenarios such as…
Few-Shot Font Generation by Learning Fine-Grained Local Styles
Licheng Tang, Yiyang Cai, Jiaming Liu +7
Few-shot font generation (FFG), which aims to generate a new font with a few examples, is gaining increasing attention due to the significant reduction in labor cost. A typical FFG…
On Causality in Domain Adaptation and Semi-Supervised Learning: an Information-Theoretic Analysis for Parametric Models
Xuetong Wu, Mingming Gong, Jonathan H. Manton +2
Recent advancements in unsupervised domain adaptation (UDA) and semi-supervised learning (SSL), particularly incorporating causality, have led to significant methodological improve…
MP2: A Momentum Contrast Approach for Recommendation with Pointwise and Pairwise Learning
Menghan Wang, Yuchen Guo, Zhenqi Zhao +4
Binary pointwise labels (aka implicit feedback) are heavily leveraged by deep learning based recommendation algorithms nowadays. In this paper we discuss the limited expressiveness…