Author name cluster

Cheng Wu

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.

15 papers

1 author row

AAAI Conference 2025 Conference Paper

Learning Multiple User Distributions for Recommendation via Guided Conditional Diffusion

Cheng Wu
Liang Su
Chaokun Wang
Shaoyun Shi
Ziqian Zhang
Ziyang Liu
Wang Peng
Wenjin Wu

Recommender systems are increasingly prevalent to provide personalized suggestions and enhance user satisfaction. Typical recommendation models encode users and items as embeddings, and generate recommendations by assessing the similarity between these embeddings. Despite their effectiveness, these embedding-based models struggle with modeling user uncertainty and capturing diverse user interests using a single fixed user embedding. Recent studies have begun to explore a user-distribution paradigm to learn distributions for users. However, this approach employs a single distribution per user, which fails to effectively delineate semantic boundaries, resulting in sub-optimal recommendations. To this end, we propose GCDR, a Guided Conditional Diffusion Recommender model, to learn multiple distributions for each user in this paper. Specifically, GCDR addresses two major challenges: 1) learning disentangled distributions, and 2) learning personalized distributions. GCDR captures inter-user and intra-user distribution properties through conditional and guided diffusion, respectively. It maintains user-specific embeddings to encode long-term interests for conditional diffusion, while for guided diffusion, it incorporates short-term interests encoded from recent interactions with category preferences. To align the diffusion model with the recommendation task, we train GCDR with three loss functions, included the user loss, the recommendation loss and the diffusion loss. Extensive experiments on four real-world datasets show that GCDR is able to learn effective user distributions and is superior to thirteen state-of-the-art baseline methods.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Negative Feedback Really Matters: Signed Dual-Channel Graph Contrastive Learning Framework for Recommendation

Leqi Zheng
Chaokun Wang
Zixin Song
Cheng Wu
Shannan Yan
Jiajun Zhang
Ziyang Liu

Traditional recommender systems have relied heavily on positive feedback for learning user preferences, while the abundance of negative feedback in real-world scenarios remains underutilized. To address this limitation, recent years have witnessed increasing attention on leveraging negative feedback in recommender systems to enhance recommendation performance. However, existing methods face three major challenges: limited model compatibility, ineffective information exchange, and computational inefficiency. To overcome these challenges, we propose a model-agnostic Signed Dual-Channel Graph Contrastive Learning (SDCGCL) framework that can be seamlessly integrated with existing graph contrastive learning methods. The framework features three key components: (1) a Dual-Channel Graph Embedding that separately processes positive and negative graphs, (2) a Cross-Channel Distribution Calibration mechanism to maintain structural consistency, and (3) an Adaptive Prediction Strategy that effectively combines signals from both channels. Building upon this framework, we further propose a Dual-channel Feedback Fusion (DualFuse) model and develop a two-stage optimization strategy to ensure efficient training. Extensive experiments on four public datasets demonstrate that our approach consistently outperforms state-of-the-art baselines by substantial margins while exhibiting minimal computational complexity. Our source code and data are released at \url{https: //github. com/LQgdwind/nips25-sdcgcl}.

PDF Details

YNIMG Journal 2024 Journal Article

Cortical activation and brain network efficiency during dual tasks: An fNIRS study

Qian Ding
Zitong Ou
Shantong Yao
Cheng Wu
Jing Chen
Junhui Shen
Yue Lan
Guangqing Xu

OBJECTIVE: Dual task (DT) is a commonly used paradigm indicative of executive functions. Brain activities during DT walking is usually measured by portable functional near infrared spectroscopy (fNIRS). Previous studies focused on cortical activation in prefrontal cortex and overlooked other brain regions such as sensorimotor cortices. This study is aimed at investigating the modulations of cortical activation and brain network efficiency in multiple brain regions from single to dual tasks with different complexities and their relationships with DT performance. METHODS: Forty-two healthy adults [12 males; mean age: 27.7 (SD=6.5) years] participated in this study. Participants performed behavioral tasks with portable fNIRS simultaneous recording. There were three parts of behavioral tasks: cognitive tasks while standing (serial subtraction of 3's and 7's), walking alone and DT (walk while subtraction, including serial subtraction of 3's and 7's). Cognitive cost, walking cost and cost sum (i.e., sum of cognitive and walking costs) were calculated for DT. Cortical activation, local and global network efficiency were calculated for each task. RESULTS: The cognitive cost was greater and the walking cost was less during DT with subtraction 3's compared with 7's (P's = 0.032 and 0.019, respectively). Cortical activation and network efficiency were differentially modulated among single and dual tasks (P's < 0.05). Prefrontal activation during DT was positively correlated with DT costs, while network efficiency was negatively correlated with DT costs (P's < 0.05). CONCLUSIONS: Our results revealed prefrontal over-activation and reduced network efficiency in individuals with poor DT performance. Our findings suggest that reduced network efficiency could be a possible mechanism contributing to poor DT performance, which is accompanied by compensatory prefrontal over-activation.

Details DOI

IJCAI Conference 2024 Conference Paper

Graph Contrastive Learning with Reinforcement Augmentation

Ziyang Liu
Chaokun Wang
Cheng Wu

Graph contrastive learning (GCL), designing contrastive objectives to learn embeddings from augmented graphs, has become a prevailing method for extracting embeddings from graphs in an unsupervised manner. As an important procedure in GCL, graph data augmentation (GDA) directly affects the model performance on downstream tasks. Currently, the GCL methods typically treat GDA as independent events, neglecting its continuity. In this paper, we regard the GDA in GCL as a Markov decision process and propose a novel graph reinforcement augmentation framework for GCL. Based on this framework, we design a Graph Advantage Actor-Critic (GA2C) model. We conduct extensive experiments to evaluate GA2C on unsupervised learning, transfer learning, and semi-supervised learning. The experimental results demonstrate the performance superiority of GA2C over the state-of-the-art GCL models. Furthermore, we verify that GA2C is more efficient than the other GCL methods with learnable GDA and provide two examples of chemical molecular graphs from ZINC-2M to demonstrate that GA2C generates meaningful augmented views, where the edge weights reflect the importance of chemical bonds in the molecule.

PDF Details DOI

AAAI Conference 2024 Short Paper

Scene Flow Prior Based Point Cloud Completion with Masked Transformer (Student Abstract)

Junzhe Ding
Yufei Que
Jin Zhang
Cheng Wu

It is necessary to explore an effective point cloud completion mechanism that is of great significance for real-world tasks such as autonomous driving, robotics applications, and multi-target tracking. In this paper, we propose a point cloud completion method using a self-supervised transformer model based on the contextual constraints of scene flow. Our method uses the multi-frame point cloud context relationship as a guide to generate a series of token proposals, this priori condition ensures the stability of the point cloud completion. The experimental results show that the method proposed in this paper achieves high accuracy and good stability.

PDF Details DOI

AIIM Journal 2022 Journal Article

A multi-scale keypoint estimation network with self-supervision for spinal curvature assessment of idiopathic scoliosis from the imperfect dataset

Tianyu Liu
Yu Wang
Yukang Yang
Ming Sun
Wenhui Fan
Cody Bunger
Cheng Wu

Idiopathic scoliosis (IS) is a common lifetime disease, which exhibits an obvious deformity of spinal curvature to seriously affect heart and lung function. Accurate radiographic assessment of spinal curvature is vitally important for the clinical diagnosis and treatment planning of idiopathic scoliosis. Deep learning algorithms have been widely adopted to the medical image analysis with the remarkable advancement in computer vision. The automated methods can improve the efficiency of clinical diagnosis to relieve the burden of doctors, which have advantage in dealing with the tedious and repetitive tasks. However, existing methods usually require sufficiently large training datasets with strict annotation, which are costly and laborious especially for medical images. Moreover, the medical images of serious IS always contain the blurry and occlusive parts, which would make the accurate and robust estimation of the spinal curvature more difficult. In this paper, a dot annotation approach is presented to train the spinal curvature assessment model, rather than using strict annotation of IS X-ray images. We develop a multi-scale keypoint estimation network to reduce the requirement for large training datasets, in which the Squeeze-and-Excitation (SE) blocks are incorporated to improve the representational capacity of the model. Then, a self-supervision module is designed to alleviate the blurry and occlusive problem, and we use the two-view radiographic assessments of IS to generate a 3D spinal curvature. Finally, extensive experiments are conducted on a collected clinical dataset, in which we obtain 81. 5 AP and the average E d between the predicted keypoints and the ground truths is 0. 43, making an improvement over the mainstream approaches.

Details DOI

AIIM Journal 2019 Journal Article

A hybrid machine learning approach to cerebral stroke prediction based on imbalanced medical dataset

Tianyu Liu
Wenhui Fan
Cheng Wu

Background and Objective Cerebral stroke has become a significant global public health issue in recent years. The ideal solution to this concern is to prevent in advance by controlling related metabolic factors. However, it is difficult for medical staff to decide whether special precautions are needed for a potential patient only based on the monitoring of physiological indicators unless they are obviously abnormal. This paper will develop a hybrid machine learning approach to predict cerebral stroke for clinical diagnosis based on the physiological data with incompleteness and class imbalance. Methods Two steps are involved in the whole process. Firstly, random forest regression is adopted to impute missing values before classification. Secondly, an automated hyperparameter optimization(AutoHPO) based on deep neural network(DNN) is applied to stroke prediction on an imbalanced dataset. Results The medical dataset contains 43, 400 records of potential patients which includes 783 occurrences of stroke. The false negative rate from our prediction approach is only 19. 1%, which has reduced by an average of 51. 5% in comparison to other traditional approaches. The false positive rate, accuracy and sensitivity predicted by the proposed approach are respectively 33. 1, 71. 6, and 67. 4%. Conclusion The approach proposed in this paper has effectively reduced the false negative rate with a relatively high overall accuracy, which means a successful decrease in the misdiagnosis rate for stroke prediction. The results are more reliable and valid as the reference in stroke prognosis, and also can be acquired conveniently at a low cost.

Details DOI

NeurIPS Conference 2019 Conference Paper

Implicit Semantic Data Augmentation for Deep Networks

Yulin Wang
Xuran Pan
Shiji Song
Hong Zhang
Gao Huang
Cheng Wu

In this paper, we propose a novel implicit semantic data augmentation (ISDA) approach to complement traditional augmentation techniques like flipping, translation or rotation. Our work is motivated by the intriguing property that deep networks are surprisingly good at linearizing features, such that certain directions in the deep feature space correspond to meaningful semantic transformations, e. g. , adding sunglasses or changing backgrounds. As a consequence, translating training samples along many semantic directions in the feature space can effectively augment the dataset to improve generalization. To implement this idea effectively and efficiently, we first perform an online estimate of the covariance matrix of deep features for each class, which captures the intra-class semantic variations. Then random vectors are drawn from a zero-mean normal distribution with the estimated covariance to augment the training data in that class. Importantly, instead of augmenting the samples explicitly, we can directly minimize an upper bound of the expected cross-entropy (CE) loss on the augmented training set, leading to a highly efficient algorithm. In fact, we show that the proposed ISDA amounts to minimizing a novel robust CE loss, which adds negligible extra computational cost to a normal training procedure. Although being simple, ISDA consistently improves the generalization performance of popular deep models (ResNets and DenseNets) on a variety of datasets, e. g. , CIFAR-10, CIFAR-100 and ImageNet. Code for reproducing our results are available at https: //github. com/blackfeather-wang/ISDA-for-Deep-Networks.

PDF Details

NeurIPS Conference 2019 Conference Paper

Regularized Anderson Acceleration for Off-Policy Deep Reinforcement Learning

Wenjie Shi
Shiji Song
Hui Wu
Ya-Chu Hsu
Cheng Wu
Gao Huang

Model-free deep reinforcement learning (RL) algorithms have been widely used for a range of complex control tasks. However, slow convergence and sample inefficiency remain challenging problems in RL, especially when handling continuous and high-dimensional state spaces. To tackle this problem, we propose a general acceleration method for model-free, off-policy deep RL algorithms by drawing the idea underlying regularized Anderson acceleration (RAA), which is an effective approach to accelerating the solving of fixed point problems with perturbations. Specifically, we first explain how policy iteration can be applied directly with Anderson acceleration. Then we extend RAA to the case of deep RL by introducing a regularization term to control the impact of perturbation induced by function approximation errors. We further propose two strategies, i. e. , progressive update and adaptive restart, to enhance the performance. The effectiveness of our method is evaluated on a variety of benchmark tasks, including Atari 2600 and MuJoCo. Experimental results show that our approach substantially improves both the learning speed and final performance of state-of-the-art deep RL algorithms.

PDF Details

AAAI Conference 2019 Short Paper

Robust Principal Component Analysis-Based Infrared Small Target Detection

Qiwei Chen
Cheng Wu
Yiming Wang

A method based on Robust Principle Component Analysis (RPCA) technique is proposed to detect small targets in infrared images. Using the low rank characteristic of background and the sparse characteristic of target, the observed image is regarded as the sum of a low-rank background matrix and a sparse outlier matrix, and then the decomposition is solved by the RPCA. The infrared small target is extracted from the single-frame image or multi-frame sequence. In order to get more efficient algorithm, the iteration process in the augmented Lagrange multiplier method is improved. The simulation results show that the method can detect out the small target precisely and efficiently.

PDF Details

IJCAI Conference 2019 Conference Paper

Soft Policy Gradient Method for Maximum Entropy Deep Reinforcement Learning

Wenjie Shi
Shiji Song
Cheng Wu

Maximum entropy deep reinforcement learning (RL) methods have been demonstrated on a range of challenging continuous tasks. However, existing methods either suffer from severe instability when training on large off-policy data or cannot scale to tasks with very high state and action dimensionality such as 3D humanoid locomotion. Besides, the optimality of desired Boltzmann policy set for non-optimal soft value function is not persuasive enough. In this paper, we first derive soft policy gradient based on entropy regularized expected reward objective for RL with continuous actions. Then, we present an off-policy actor-critic, model-free maximum entropy deep RL algorithm called deep soft policy gradient (DSPG) by combining soft policy gradient with soft Bellman equation. To ensure stable learning while eliminating the need of two separate critics for soft value functions, we leverage double sampling approach to making the soft Bellman equation tractable. The experimental results demonstrate that our method outperforms in performance over off-policy prior methods.

PDF Details

AAAI Conference 2019 Short Paper

T-Center: A Novel Discriminative Feature Extraction Approach for Iris Recognition

Yifeng Chen
Cheng Wu
Yiming Wang

For large-scale iris recognition tasks, the determination of classification thresholds remains a challenging task, especially in practical applications where sample space is growing rapidly. Due to the complexity of iris samples, the classification threshold is difficult to determine with the increase of samples. The key issue to solving such threshold determination problems is to obtain iris feature vectors with more obvious discrimination. Therefore, we train deep convolutional neural networks based on a large number of iris samples to extract iris features. More importantly, an optimized center loss function referred to Tight Center (T -Center) Loss is used to solve the problem of insufficient discrimination caused by Softmax loss function. In order to evaluate the effectiveness of our proposed method, we use cosine similarity to estimate the similarity between the features on the published datasets CASIA-IrisV4 and IITD2. 0. Our experiment results demonstrate that the T -Center loss can minimize intra-class variance and maximize inter-class variance, which achieve significant performance on the benchmark experiments.

PDF Details

EAAI Journal 2012 Journal Article

A hybrid local search algorithm for scheduling real-world job shops with batch-wise pending due dates

Rui Zhang
Cheng Wu

This paper aims at solving a real-world job shop scheduling problem with two characteristics, i. e. , the existence of pending due dates and job batches. Due date quotation is an important decision process for contemporary companies that adopt the MTO (make to order) strategy. Although the assignment of due dates is usually performed separately with production scheduling, there exist strong interactions between the two tasks. Therefore, we integrate these two decisions into one optimization model. Meanwhile, each order placed by the customer defines a batch of jobs, for which the same due date should be set. Thus, the completion times of these jobs should be close to one another in order to reduce waiting time and cost. For this purpose, we propose a dispatching rule to synchronize their manufacturing progresses. A two-stage local search algorithm based on the PMBGA (probabilistic model-building genetic algorithm) and parameter perturbation is proposed to solve the integrated scheduling problem and its superiority is revealed by the applications to a real-world mechanical factory.

Details DOI

AAMAS Conference 2010 Conference Paper

Spectrum Management of Cognitive Radio Using Multi-agent Reinforcement Learning

Cheng Wu
Kaushik Chowdhury
Marco Di Felice
Waleed Meleis

Wireless cognitive radio (CR) is a newly emerging paradigmthat attempts to opportunistically transmit in licensed frequencies, without affecting the pre-assigned users of thesebands. To enable this functionality, such a radio must predict its operational parameters, such as transmit power andspectrum. These tasks, collectively called spectrum management, is difficult to achieve in a dynamic distributed environment, in which CR users may only take local decisions, andreact to the environmental changes. In this paper, we introduce a multi-agent reinforcement learning approach basedspectrum management. Our approach uses value functionsto evaluate the desirability of choosing different transmission parameters, and enables efficient assignment of spectrums and transmit powers by maximizing long-term reward. We then investigate various real-world scenarios, andcompare the communication performance using different setsof learning parameters. We also apply Kanerva-based function approximation to improve our approach's ability to handle large cognitive radio networks and evaluate its effect oncommunication performance. We conclude that our reinforcement learning based spectrum management can significantly reduce the interference to the licensed users, whilemaintaining a high probability of successful transmissions ina cognitive radio ad hoc network.

PDF

AAMAS Conference 2008 Conference Paper

Adaptive Kanerva-based Function Approximation for Multi-Agent Systems

Cheng Wu
Waleed Meleis

In this paper, we show how adaptive prototype optimization can be used to improve the performance of function approximation based on Kanerva Coding when solving largescale instances of classic multi-agent problems. We apply our techniques to the predator-prey pursuit problem. We first demonstrate that Kanerva Coding applied within a reinforcement learner does not give good results. We then describe our new adaptive Kanerva-based function approximation algorithm, based on prototype deletion and generation. We show that probabilistic prototype deletion with random prototype generation increases the fraction of test instances that are solved from 45% to 90%, and that prototype splitting increases that fraction to 94%. We also show that optimizing prototypes reduces the number of prototypes, and therefore the number of features, needed to achieve a 90% solution rate by up to 87%. These results demonstrate that our approach can dramatically improve the quality of the results obtained and reduce the number of prototypes required. We conclude that adaptive prototype optimization can greatly improve a Kanerva-based reinforcement learner’s ability to solve large-scale multi-agent problems.

PDF