Author name cluster

Hong Cheng

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

18 papers

2 author rows

EAAI Journal 2025 Journal Article

Adaptive Coordinated Motion Planning for lower limb exoskeleton robots with a robotic walker

Chaobin Zou
Yi Ren
Rui Huang
Xinhao Zhang
Jingting Zhang
Zhinan Peng
Hong Cheng

Repetitive gait training is helpful for patients with gait disabilities and can be effectively facilitated by lower limb exoskeleton robots (LLEs). At the early stages of rehabilitation, the deployment of a mobile robotic walker to complement exoskeleton-assisted gait training is indispensable, particularly for patients with diminished muscle strength. It is a critical issue to coordinated control the exoskeleton robot and the robotic walker to achieve a natural walking posture due to the variations of gait patterns with different walking speeds. In this paper, a novel Adaptive Coordinated Motion Planning (ACMP) approach is proposed to tackle the coordinated control problem of the LLEs with a robotic walker, which comprises of three parts: the gait patterns generation for LLEs, the optimization for adaption to the desired walking speed, and the coordinated control for both the exoskeleton robot and the robotic walker. The main contribution of this paper is twofold: a new knee-stretched gait patterns generation approach with the given foot locations; based on the reduced order dynamics model for the human–exoskeleton system, an optimization problem is constructed to generate reference joint angles for the human–exoskeleton–walker system and adapt to different walking speeds. Experimental validation was conducted on the CoppeliaSim simulation platform. Results demonstrate that the proposed approach achieves coordinated motion control across a wide speed range (0–0. 8 m/s), with the mean displacement tracking error of the center of mass constrained within 0. 01 m. This ensures accurate locomotion tracking of the LLEs while maintaining natural walking postures. Compared to non-adaptive baselines, the proposed method achieves a tracking accuracy improvement of over 92%, highlighting its effectiveness in dynamic human–robot coordination tasks.

Details DOI

IJCAI Conference 2025 Conference Paper

Efficient Constraint-based Window Causal Graph Discovery in Time Series with Multiple Time Lags

Yewei Xia
Yixin Ren
Hong Cheng
Hao Zhang
Jihong Guan
Minchuan Xu
Shuigeng Zhou

We address the identification of direct causes in time series with multiple time lags, and propose a constraint-based window causal graph discovery method. A key advantage of our method is that the number of required conditional independence (CI) tests scales quadratically with the number of sub-series. The method first uses CI tests to find the minimum trek lag between two arbitrary sub-series, followed by designing an efficient CI testing strategy to identify the direct causes between them. We show that the method is both sound and complete under some graph constraints. We compare the proposed method with typical baselines on various datasets. Experimental results show that our method outperforms all the counterparts in both accuracy and running speed.

PDF Details DOI

IROS Conference 2025 Conference Paper

Engaging Mind and Body: An Immersive BCI Paradigm with Motion-Panoramic Virtual Reality

Lianchi Zhang
Mengxi Lei
Jingting Zhang
Zonghai Huang
Rui Huang
Hong Cheng

Brain-computer interface (BCI) is an important technology in developing the closed-loop brain training system for cognitive functional rehabilitation. Most of existing BCI paradigms have not ensured desired immersiveness of mind and body, thereby limiting participants’ engagement in training tasks. In this paper, we propose a sensory-immersive BCI paradigm for decision-making with a novel motion-panoramic virtual-reality system, aiming for deep involvement of both mind and body in brain functional training. This paradigm integrates visual, auditory and motion multi-sensory stimulation by using the Gait Real-time Analysis Interactive Lab system to implement the modified ultimatum game for decision making. The designed paradigm is validated through three experimental studies, including the event-related potentials analysis, power spectral density analysis and the brain network analysis. They demonstrate that the designed paradigm can achieve better performance in motor-cognitive interaction and multi-sensory coordination, by effectively enhancing brain activation in visual, auditory, and motor processing regions, which can result in more effective activation of decision-making areas like the prefrontal cortex. Compared to the existing paradigm, our paradigm can increase the number of high-intensity functional connections in the brain regions of participants by 62. 8% (from 86 to 140), and the number of effective functional connections increased by 90. 5% (from 252 to 480).

Details

NeurIPS Conference 2025 Conference Paper

Non-stationary Equivariant Graph Neural Networks for Physical Dynamics Simulation

Chaohao Yuan
Maoji Wen
Ercan KURUOGLU
Yang Liu
Jia Li
Tingyang Xu
Deli Zhao
Hong Cheng

To enhance the generalization ability of graph neural networks (GNNs) in learning and simulation physical dynamics, a series of equivariant GNNs have been developed to incorporate the symmetric inductive bias. However, the existing methods do not take into account the non-stationarity nature of physical dynamics, where the joint distribution changes over time. Moreover, previous approaches for modeling non-stationary time series typically involve normalizing the data, which disrupts the symmetric assumption inherent in physical dynamics. To model the non-stationary physical dynamics while preserving the symmetric inductive bias, we introduce a Non-Stationary Equivariant Graph Neural Network (NS-EGNN) to capture the non-stationarity in physical dynamics while preserving the symmetric property of the model. Specifically, NS-EGNN employs Fourier Transform on segments of physical dynamics to extract time-varying frequency information from the trajectories. It then uses the first and second-order differences to mitigate non-stationarity, followed by pooling for future predictions. Through capturing varying frequency characteristics and alleviate the linear and quadric trend in the raw physical dynamics, NS-EGNN better models the temporal dependencies in the physical dynamics. NS-EGNN has been applied on various types of physical dynamics, including molecular, motion and protein dynamics. In various scenario, NS-EGNN consistently surpasses the performance of existing state-of-the-art algorithms, underscoring its effectiveness. The implementation of NS-EGNN is available at https: //github. com/MaojiWEN/NS-EGNN.

PDF Details

IJCAI Conference 2024 Conference Paper

A Survey of Graph Meets Large Language Model: Progress and Future Directions

Yuhan Li
Zhixun Li
Peisong Wang
Jia Li
Xiangguo Sun
Hong Cheng
Jeffrey Xu Yu

Graph plays a significant role in representing and analyzing complex relationships in real-world applications such as citation networks, social networks, and biological data. Recently, Large Language Models (LLMs), which have achieved tremendous success in various domains, have also been leveraged in graph-related tasks to surpass traditional Graph Neural Networks (GNNs) based methods and yield state-of-the-art performance. In this survey, we first present a comprehensive review and analysis of existing methods that integrate LLMs with graphs. First of all, we propose a new taxonomy, which organizes existing methods into three categories based on the role (i. e. , enhancer, predictor, and alignment component) played by LLMs in graph-related tasks. Then we systematically survey the representative methods along the three categories of the taxonomy. Finally, we discuss the remaining limitations of existing studies and highlight promising avenues for future research. The relevant papers are summarized and will be consistently updated at: https: //github. com/yhLeeee/Awesome-LLMs-in-Graph-tasks.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

All in One: Multi-task Prompting for Graph Neural Networks (Extended Abstract)

Xiangguo Sun
Hong Cheng
Jia Li
Bo Liu
Jihong Guan

This paper is an extended abstract of our original work published in KDD23, where we won the best research paper award. The paper introduces a novel approach to bridging the gap between pre-trained graph models and the diverse tasks they’re applied to, inspired by the success of prompt learning in NLP. Recognizing the challenge of aligning pre-trained models with varied graph tasks (node level, edge level, and graph level), which can lead to negative transfer and poor performance, we propose a multi-task prompting method for graphs. This method involves unifying graph and language prompt formats, enabling NLP’s prompting strategies to be adapted for graph tasks. By analyzing the task space of graph applications, we reformulate problems to fit graph-level tasks and apply meta-learning to improve prompt initialization for multiple tasks. Experiments show our method’s effectiveness in enhancing model performance across different graph tasks. Beyond the original work, in this extended abstract, we further discuss the graph prompt from a bigger picture and provide some of the latest work toward this area.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Can Graph Learning Improve Planning in LLM-based Agents?

Xixi Wu
Yifei Shen
Caihua Shan
Kaitao Song
Siwei Wang
Bohang Zhang
Jiarui Feng
Hong Cheng

Task planning in language agents is emerging as an important research topic alongside the development of large language models (LLMs). It aims to break down complex user requests in natural language into solvable sub-tasks, thereby fulfilling the original requests. In this context, the sub-tasks can be naturally viewed as a graph, where the nodes represent the sub-tasks, and the edges denote the dependencies among them. Consequently, task planning is a decision-making problem that involves selecting a connected path or subgraph within the corresponding graph and invoking it. In this paper, we explore graph learning-based methods for task planning, a direction that is orthogonal to the prevalent focus on prompt design. Our interest in graph learning stems from a theoretical discovery: the biases of attention and auto-regressive loss impede LLMs' ability to effectively navigate decision-making on graphs, which is adeptly addressed by graph neural networks (GNNs). This theoretical insight led us to integrate GNNs with LLMs to enhance overall performance. Extensive experiments demonstrate that GNN-based methods surpass existing solutions even without training, and minimal training can further enhance their performance. The performance gain increases with a larger task graph size.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

ProG: A Graph Prompt Learning Benchmark

Chenyi Zi
Haihong Zhao
Xiangguo Sun
Yiqing Lin
Hong Cheng
Jia Li

Artificial general intelligence on graphs has shown significant advancements across various applications, yet the traditional `Pre-train & Fine-tune' paradigm faces inefficiencies and negative transfer issues, particularly in complex and few-shot settings. Graph prompt learning emerges as a promising alternative, leveraging lightweight prompts to manipulate data and fill the task gap by reformulating downstream tasks to the pretext. However, several critical challenges still remain: how to unify diverse graph prompt models, how to evaluate the quality of graph prompts, and to improve their usability for practical comparisons and selection. In response to these challenges, we introduce the first comprehensive benchmark for graph prompt learning. Our benchmark integrates SIX pre-training methods and FIVE state-of-the-art graph prompt techniques, evaluated across FIFTEEN diverse datasets to assess performance, flexibility, and efficiency. We also present 'ProG', an easy-to-use open-source library that streamlines the execution of various graph prompt models, facilitating objective evaluations. Additionally, we propose a unified framework that categorizes existing graph prompt methods into two main approaches: prompts as graphs and prompts as tokens. This framework enhances the applicability and comparison of graph prompt techniques. The code is available at: https: //github. com/sheldonresearch/ProG.

PDF Details DOI

EAAI Journal 2024 Journal Article

Spatio-temporal features for fast early warning of unplanned self-extubation in ICU

Yang Chen
Ling Wang
Guorong Wang
Shuang Yang
Yingying Wang
MingFang Xiang
Xuan Zhang
Hui Chen

Patients’ behaviors in the Intensive Care Units (ICU) have garnered research attention, particularly regarding the impact of Unplanned Extubation (UEX). However, there is currently no existing report on methods for early warning of UEX action in RGB video. Applying traditional human action recognition algorithms to UEX in the complex ICU environment proves challenging. To address the above issue, we propose a novel feature for early warning of UEX action in patients using RGB videos. Firstly, we employ the YOLOv3 detection method to extract the region of interest (ROI), which corresponds to the region where the patient is located. Subsequently, we develop a spatio-temporal (ST) feature for human action tracking by using the L-K optical flow algorithm. This ST feature encompasses optical flow corner number, trajectory distance, and wavelet transform features. Finally, we utilize support vector machine (SVM) for patient action classification and early warning. Experimental results on the ICU monitoring dataset demonstrate the superior performance of the proposed feature in UEX prediction.

Details DOI

NeurIPS Conference 2021 Conference Paper

Deconvolutional Networks on Graph Data

Jia Li
Jiajin Li
Yang Liu
Jianwei Yu
Yueting Li
Hong Cheng

In this paper, we consider an inverse problem in graph learning domain -- "given the graph representations smoothed by Graph Convolutional Network (GCN), how can we reconstruct the input graph signal? " We propose Graph Deconvolutional Network (GDN) and motivate the design of GDN via a combination of inverse filters in spectral domain and de-noising layers in wavelet domain, as the inverse operation results in a high frequency amplifier and may amplify the noise. We demonstrate the effectiveness of the proposed method on several tasks including graph feature imputation and graph structure generation.

PDF Details

NeurIPS Conference 2020 Conference Paper

Dirichlet Graph Variational Autoencoder

Jia Li
Jianwei Yu
Jiajin Li
Honglei Zhang
Kangfei Zhao
Yu Rong
Hong Cheng
Junzhou Huang

Graph Neural Networks (GNN) and Variational Autoencoders (VAEs) have been widely used in modeling and generating graphs with latent factors. However there is no clear explanation of what these latent factors are and why they perform well. In this work, we present Dirichlet Graph Variational Autoencoder (DGVAE) with graph cluster memberships as latent factors. Our study connects VAEs based graph generation and balanced graph cut, and provides a new way to understand and improve the internal mechanism of VAEs based graph generation. Specifically, we first interpret the reconstruction term of DGVAE as balanced graph cut in a principled way. Furthermore, motivated by the low pass characteristics in balanced graph cut, we propose a new variant of GNN named Heatts to encode the input graph into cluster memberships. Heatts utilizes the Taylor series for fast computation of Heat kernels and has better low pass characteristics than Graph Convolutional Networks (GCN). Through experiments on graph generation and graph clustering, we demonstrate the effectiveness of our proposed framework.

PDF Details

AAAI Conference 2020 Conference Paper

Hybrid Graph Neural Networks for Crowd Counting

Ao Luo
Fan Yang
Xin Li
Dong Nie
Zhicheng Jiao
Shangchen Zhou
Hong Cheng

Crowd counting is an important yet challenging task due to the large scale and density variation. Recent investigations have shown that distilling rich relations among multi-scale features and exploiting useful information from the auxiliary task, i. e. , localization, are vital for this task. Nevertheless, how to comprehensively leverage these relations within a uni- ﬁed network architecture is still a challenging problem. In this paper, we present a novel network structure called Hybrid Graph Neural Network (HyGnn) which targets to relieve the problem by interweaving the multi-scale features for crowd density as well as its auxiliary task (localization) together and performing joint reasoning over a graph. Speciﬁcally, HyGnn integrates a hybrid graph to jointly represent the task-speciﬁc feature maps of diﬀerent scales as nodes, and two types of relations as edges: (i) multi-scale relations capturing the feature dependencies across scales and (ii) mutual beneﬁcial relations building bridges for the cooperation between counting and localization. Thus, through message passing, HyGnn can capture and distill richer relations between nodes to obtain more powerful representations, providing robust and accurate results. Our HyGnn performs signiﬁcantly well on four challenging datasets: ShanghaiTech Part A, ShanghaiTech Part B, UCF CC 50 and UCF QNRF, outperforming the state-ofthe-art algorithms by a large margin.

PDF Details

AAAI Conference 2018 Conference Paper

Multi-Scale Bidirectional FCN for Object Skeleton Extraction

Fan Yang
Xin Li
Hong Cheng
Yuxiao Guo
Leiting Chen
Jianping Li

Object skeleton detection is a challenging problem with wide application. Recently, deep Convolutional Neural Networks (CNNs) have substantially improved the performance of the state-of-the-art in this task. However, most of the existing CNN-Based methods are based on a skip-layer structure where low-level and high-level features are combined and learned so as to gather multi-level contextual information. As shallow features are too messy and lack semantic knowledge, they may cause errors and inaccuracy. Therefore, we propose a novel network architecture, Multi-Scale Bidirectional Fully Convolutional Network (MSB-FCN), to better capture and consolidate multi-scale high-level context information for object skeleton detection. Our network uses only deep features to build multi-scale feature representations, and employs a bidirectional structure to collect contextual knowledge. Hence the proposed MSB-FCN has the ability to learn the semantic-level information from different sub-regions. Furthermore, we introduce dense connections into the bidirectional structure of our MSB-FCN to ensure that the learning process at each scale can directly encode information from all other scales. Extensive experiments on various commonly used benchmarks demonstrate that the proposed MSB- FCN has achieved signiﬁcant improvements over the state-ofthe-art algorithms.

PDF Details

NeurIPS Conference 2017 Conference Paper

Accelerated First-order Methods for Geodesically Convex Optimization on Riemannian Manifolds

Yuanyuan Liu
Fanhua Shang
James Cheng
Hong Cheng
Licheng Jiao

In this paper, we propose an accelerated first-order method for geodesically convex optimization, which is the generalization of the standard Nesterov's accelerated method from Euclidean space to nonlinear Riemannian space. We first derive two equations and obtain two nonlinear operators for geodesically convex optimization instead of the linear extrapolation step in Euclidean space. In particular, we analyze the global convergence properties of our accelerated method for geodesically strongly-convex problems, which show that our method improves the convergence rate from O((1-\mu/L)^{k}) to O((1-\sqrt{\mu/L})^{k}). Moreover, our method also improves the global convergence rate on geodesically general convex problems from O(1/k) to O(1/k^{2}). Finally, we give a specific iterative scheme for matrix Karcher mean problems, and validate our theoretical results with experiments.

PDF Details

IJCAI Conference 2015 Conference Paper

Robust Kernel Dictionary Learning Using a Whole Sequence Convergent Algorithm

Huaping Liu
Jie Qin
Hong Cheng
Fuchun Sun

Kernel sparse coding is an effective strategy to capture the non-linear structure of data samples. However, how to learn a robust kernel dictionary remains an open problem. In this paper, we propose a new optimization model to learn the robust kernel dictionary while isolating outliers in the training samples. This model is essentially based on the decomposition of the reconstruction error into small dense noises and large sparse outliers. The outlier error term is formulated as the product of the sample matrix in the feature space and a diagonal coefficient matrix. This facilitates the kernelized dictionary learning. To solve the non-convex optimization problem, we develop a whole sequence convergent algorithm which guarantees the obtained solution sequence is a Cauchy sequence. The experimental results show that the proposed robust kernel dictionary learning method provides significant performance improvement.

PDF Details

NeurIPS Conference 2014 Conference Paper

Generalized Higher-Order Orthogonal Iteration for Tensor Decomposition and Completion

Yuanyuan Liu
Fanhua Shang
Wei Fan
James Cheng
Hong Cheng

Low-rank tensor estimation has been frequently applied in many real-world problems. Despite successful applications, existing Schatten 1-norm minimization (SNM) methods may become very slow or even not applicable for large-scale problems. To address this difficulty, we therefore propose an efficient and scalable core tensor Schatten 1-norm minimization method for simultaneous tensor decomposition and completion, with a much lower computational complexity. We first induce the equivalence relation of Schatten 1-norm of a low-rank tensor and its core tensor. Then the Schatten 1-norm of the core tensor is used to replace that of the whole tensor, which leads to a much smaller-scale matrix SNM problem. Finally, an efficient algorithm with a rank-increasing scheme is developed to solve the proposed problem with a convergence guarantee. Extensive experimental results show that our method is usually more accurate than the state-of-the-art methods, and is orders of magnitude faster.

PDF Details

IS Journal 2004 Journal Article

Toward intelligent driver-assistance and safety warning system

Nan-Ning Zheng
Shuming Tang
Hong Cheng
Qing Li
G. Lai
F.-W. Wang

A major problem associated with the rapid growth in automotive production is an increase in traffic congestion and accidents, especially in big cities of China. To solve the problem, the government has been increasing funds for improving the traffic infrastructure, enforcing traffic laws, and educating drivers about traffic regulations. In addition, research institutes have launched R&D projects in driver assistance and safety warning systems. In particular, in 1999, the Chinese Academy of Sciences' Intelligent Control and Systems Engineering Center started the Intelligent Vehicle Platforms project. The project aims to promote the use of intelligent technology for safe, efficient, and smart vehicles and to prototype vehicular electronic and sensory products and systems for the Chinese automotive industry. One of the project's key objectives is to develop a vehicular application-specific operating system (vASOS). The National Science Foundation of China and the CAS Knowledge Innovation Program support the project. Supported by the Vehicular Embedded Computing Platform project, the Xi'an Jiaotong University (XJTU-"Jiao Tong" means transportation in Chinese) Institute of Artificial Intelligence and Robotics and the CAS have collaborated to develop intelligent driver-assistance and safety warning systems for passenger vehicles, particularly GPS-and vision-based systems.

Details DOI

ICAPS Conference 2003 Conference Paper

Planning for Marketing Campaigns

Qiang Yang 0001
Hong Cheng

In business marketing, corporations and institutions are interested in executing a sequence of marketing actions to affect a group of customers. For example, a financial institution may derive marketing strategies for turning their reluctant customers into active ones and a telecommunications company may plan actions to stop their valuable customers from leaving. These marketing plans are aimed at converting groups of customers from an undesirable class to a desirable one. In this paper, we formulate this group marketing-plan generation problem as a planning problem. We design a novel search algorithm to find a cost-effective and highly probable plan for switching a group of customers from their initial states to some more desirable final states. We explore the tradeoff among time, space and quality of computation in this planning framework. We demonstrate the effectiveness of the methods through empirical results.

Details