Author name cluster

Guan Wang

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.

17 papers

2 author rows

EAAI Journal 2026 Journal Article

A novel fractional order partial grey prediction model with conformable fractional derivative and its application to energy prediction

Qiong Wang
Lin Lin
Guan Wang
Wei Chen
Guoping Zhan

Precise regional energy output prediction is key to optimizing the energy structure, promoting clean energy, lessening fossil fuel reliance, and providing an important reference for formulating energy policies and achieving sustainable development. This paper constructs a fractional order partial grey model incorporating a control matrix by combining a partial differential equation, which predicts energy production. First, the new model effectively reduces the random fluctuations in the data by introducing a fractional order accumulation operator, and enhances the ability to handle nonlinear data by leveraging conformable fractional derivatives. At the same time, a control matrix containing exponential and trigonometric functions is used to dynamically adjust parameters, allowing the model to better adapt to various oscillatory data, thereby improving its generalizability. Additionally, the model’s more accurate time response function is obtained through the characteristic curve method, and the optimal parameters of the model are determined using the particle swarm optimization algorithm. Finally, this paper evaluates the effectiveness of the new model from different angles using seven evaluation indicators by simulating and predicting the output of raw coal, gasoline, coalbed methane, and natural gas in nine provinces across China. The results show that the performance of the new model is superior to that of the comparison models, demonstrating its efficacy in forecasting energy production. Ultimately, this novel model is employed to project and assess crude oil production in Jiangsu Province, offering theoretical insights and technical assistance for energy management, economic planning, and environmental conservation.

Details DOI

EAAI Journal 2026 Journal Article

A novel grey model based on fractional derivative and self-adaptive reverse accumulation and its application in energy forecasting

Qiong Wang
Zhihong Chen
Guan Wang
Wei Chen

In response to the global energy crisis and climate change, developing prediction models with high data adaptability is crucial for sustainable development. To address the challenges of general models’ inadequate adaptation to non-smooth, nonlinear energy data and the lack of data memory effects, therefore, a novel grey prediction model based on Caputo fractional derivative is established, effectively enhancing the adaptability of the model by incorporating both the Caputo fractional derivative and a fractional self-adaptive reverse accumulation operator, enabling dynamic memory and the adaptive adjustment of data weight. Additionally, adding a nonlinear correction term and optimizing the background value in the model enhances the performance to fit nonlinear data and further increases prediction accuracy. In this paper, the Laplace transform is employed to derive the analytical solution of the model, while the particle swarm optimization algorithm is utilized to optimize the parameters, ensuring the model achieves optimal performance. To verify the model’s validity, empirical analysis with various energy production and consumption data shows that the model significantly outperforms comparison models, presenting the excellent applicability of data in different types. Finally, the new model is applied to forecast the development trends of the average daily consumption of energy, natural gas, and electricity. The prediction results not only provide practical value for the application in energy forecasting but also offer a reliable theoretical basis and data support for relevant decision-making.

Details DOI

EAAI Journal 2026 Journal Article

Transfer learning-driven adaptive physics-informed neural networks acceleration method for aerodynamic identification

Ming Yan
Kai Liu
Shuaibin An
Guan Wang
Zeyu Jin
Jianwen Zang

Aiming at the problem of model uncertainty and strict space-time constraints in the landing process of carrier-based aircraft, this paper proposes a transfer learning-driven adaptive physics-informed neural networks acceleration method for aerodynamic identification to achieve collaborative optimization of online aerodynamic identification efficiency and accuracy. Firstly, the physics-informed neural networks model is constructed offline to increase the physical meaning of data-driven. Secondly, an adaptive activation function with trainable parameters is introduced to dynamically adjust the network feature-mapping ability. Finally, the online strategy of transfer learning is used to freeze part of the network layers of the offline pre-training model. The iteration time of online identification is compressed to meet the limited space-time requirements of the landing process. The simulation results show that the method proposed in this paper can improve the efficiency of online identification while ensuring the accuracy of identification. It provides an efficient and feasible solution for the aerodynamic identification task of carrier-based aircraft landing.

Details DOI

EAAI Journal 2025 Journal Article

A novel time-delay multivariable grey model and its application in predicting oil production

Huiming Duan
Guan Wang
YuXin Song
Hongli Chen

An accurate prediction of oil production can provide a scientific basis for planning the production of the Qinghai oilfield and help in rationally arranging resources. To address the time-delay of related factors in the oil production system and how this problem affects oil production, this paper classifies the different degrees of time-delay of related factors and establishes a time-delay multivariable grey model with multiple parameters. This model not only reflects the characteristics of a Logistic model with strong historical recurrence ability and high prediction accuracy in the short and medium terms but also compensates for the defects of existing grey models that do not consider the time-delay of related factors; this is a new idea for grey modelling. Moreover, the parameter estimation of the new model is obtained via the least squares technique, the time response of the new model is obtained via a mathematical method, and the modelling steps of the new model are also obtained. Finally, the new model is applied to the prediction of production of the Qinghai oilfield in China, the effectiveness of the model is analysed according to two different correlation sequences, and six types of the same modelling objects are tested. Results of two types of twelve experiments each show that the total mean absolute percentage error is less than 5%, the lowest is 1. 2580%, and the highest is only 4. 0087%. This shows that the new model has a good effect and results of six technical indicators show that the new model is better than the other five multivariable grey models.

Details DOI

AAAI Conference 2025 Conference Paper

Are Expressive Models Truly Necessary for Offline RL?

Guan Wang
Haoyi Niu
Jianxiong Li
Li Jiang
Jianming Hu
Xianyuan Zhan

Among various branches of offline reinforcement learning (RL) methods, goal-conditioned supervised learning (GCSL) has gained increasing popularity as it formulates the offline RL problem as a sequential modeling task, therefore bypassing the notoriously difficult credit assignment challenge of value learning in conventional RL paradigm. Sequential modeling, however, requires capturing accurate dynamics across long horizons in trajectory data to ensure reasonable policy performance. To meet this requirement, leveraging large, expressive models has become a popular choice in recent literature, which, however, comes at the cost of significantly increased computation and inference latency. Contradictory yet promising, we reveal that lightweight models as simple as shallow 2-layer MLPs, can also enjoy accurate dynamics consistency and significantly reduced sequential modeling errors against large expressive models by adopting a simple recursive planning scheme: recursively planning coarse-grained future sub-goals based on current and target information, and then executes the action with a goal-conditioned policy learned from data relabeled with these sub-goal ground truths. We term our method as Recursive Skip-Step Planning (RSP). Simple yet effective, RSP enjoys great efficiency improvements thanks to its lightweight structure, and substantially outperforms existing methods, reaching new SOTA performances on the D4RL benchmark, especially in multi-stage long-horizon tasks.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

DrivAerStar: An Industrial-Grade CFD Dataset for Vehicle Aerodynamic Optimization

Jiyan Qiu
Lyulin Kuang
Guan Wang
Yichen Xu
Leiyao Cui
Shaotong Fu
Yixin Zhu
Rita Zhang

Vehicle aerodynamics optimization has become critical for automotive electrification, where drag reduction directly determines electric vehicle range and energy efficiency. Traditional approaches face an intractable trade-off: computationally expensive Computational Fluid Dynamics (CFD) simulations requiring weeks per design iteration, or simplified models that sacrifice production-grade accuracy. While machine learning offers transformative potential, existing datasets exhibit fundamental limitations -- inadequate mesh resolution, missing vehicle components, and validation errors exceeding 5% -- preventing deployment in industrial workflows. We present DrivAerStar, comprising 12, 000 industrial-grade automotive CFD simulations generated using STAR-CCM+${}^{\textregistered}$ software. The dataset systematically explores three vehicle configurations through 20 Computer Aided Design (CAD) parameters via Free Form Deformation (FFD) algorithms, including complete engine compartments and cooling systems with realistic internal airflow. DrivAerStar achieves wind tunnel validation accuracy below 1. 04% -- a five-fold improvement over existing datasets -- through refined mesh strategies with strict wall $y^+$ control. Benchmarks demonstrate that models trained on this data achieve production-ready accuracy while reducing computational costs from weeks to minutes. This represents the first dataset bridging academic machine learning research and industrial CFD practice, establishing a new standard for data-driven aerodynamic optimization in automotive development. Beyond automotive applications, DrivAerStar demonstrates a paradigm for integrating high-fidelity physics simulations with Artificial Intelligence (AI) across engineering disciplines where computational constraints currently limit innovation.

PDF Details

IJCAI Conference 2025 Conference Paper

GBGC: Efficient and Adaptive Graph Coarsening via Granular-ball Computing

Shuyin Xia
Guan Wang
Gaojie Xu
Sen Zhao
Guoyin Wang

The objective of graph coarsening is to generate smaller, more manageable graphs while preserving key information of the original graph. Previous work were mainly based on the perspective of spectrum-preserving, using some predefined coarsening rules to make the eigenvalues of the Laplacian matrix of the original graph and the coarsened graph match as much as possible. However, they largely overlooked the fact that the original graph is composed of subregions at different levels of granularity, where highly connected and similar nodes should be more inclined to be aggregated together as nodes in the coarsened graph. By combining the multi-granularity characteristics of the graph structure, we can generate coarsened graph at the optimal granularity. To this end, inspired by the application of granular-ball computing in multi-granularity, we propose a new multi-granularity, efficient, and adaptive coarsening method via granular-ball (GBGC), which significantly improves the coarsening results and efficiency. Specifically, GBGC introduces an adaptive granular-ball graph refinement mechanism, which adaptively splits the original graph from coarse to fine into granular-balls of different sizes and optimal granularity, and constructs the coarsened graph using these granular-balls as supernodes. In addition, compared with other state-of-the-art graph coarsening methods, the processing speed of this method can be increased by tens to hundreds of times and has lower time complexity. The accuracy of GBGC is almost always higher than that of the original graph due to the good robustness and generalization of the granular-ball computing, so it has the potential to become a standard graph data preprocessing method.

PDF Details DOI

JBHI Journal 2025 Journal Article

Large Model Driven Multi-Granularity Medical Image Analysis: A Fuzzy Logic-Guided Framework

Guan Wang
Mingyu Xu
Chao Li
Xingsi Xue
Bo Yi
Jing Yang

The analysis of medical images requires sophisticated computational approaches that can handle the inherent complexity and uncertainty present in pathological structures. This paper presents a large model driven framework that integrates fuzzy logic principles with transformer-based architectures to enable multi-granularity medical image analysis. The proposed approach, termed ULVM-MG, employs a sophisticated feature extraction strategy that simultaneously processes pathological images at coarse, medium, and fine granularity levels, mirroring the systematic examination methodology employed by experienced pathologists. In particular, a fuzzy-guided cross-attention mechanism directs the transformer's attention toward diagnostically significant regions while preserving essential contextual information. regions while preserving essential contextual information. Comprehensive evaluation on histopathological datasets demonstrates superior performance compared to state-of-the-art transformer-based approaches. ULVM-MG achieves 98. 76% and 97. 34% accuracy on LC25000 and NCT datasets, respectively, outperforming the best baseline by 1. 61% and 2. 17%. The framework excels particularly in distinguishing morphologically similar tissue types and benign versus malignant classification tasks. Ablation studies confirm the critical contributions of multi-granularity processing and fuzzy uncertainty modeling, with statistical analysis revealing significant performance improvements across all evaluation metrics.

Details DOI

EAAI Journal 2024 Journal Article

A novel time-lagged logistic grey model and its application in forecasting energy production volume

Hui Li
Guan Wang
Huiming Duan

Scientific and accurate prediction of energy production is important for exploring energy alternative paths, adjusting energy structure and industrial layout in a targeted manner, and promoting strategic energy transformation. In this paper, a time-lagged logistic grey forecasting model with harvesting term is established by combining the Logistic model, which has the ability of historical recurrence and short- and medium-term forecasting ability, and the grey forecasting model, which has the characteristics of strong adaptability and small computational effort. The least squares method is used to estimate the parameters of the new model, and the mathematical method is used to calculate the time response equation of the new model, and the modeling steps and flow chart of the new model are obtained. Finally, the oil production data of a province in China is used as the validity analysis of the model, and the new model is compared with two classical grey prediction models, three optimized grey prediction models, and one other prediction model. Through the comparison of seven indicators, the results show that the new model is significantly better than other models. Based on the validity analysis results, the new model is applied to the energy production forecast of three typical provinces in China. The horizontal and vertical comparison shows that the model can effectively predict the three kinds of energy production, and can provide technical support for the strategy and measures to adjust the energy security structure and promote the healthy and sustainable development of the energy industry.

Details DOI

AAAI Conference 2024 Conference Paper

CDPNet: Cross-Modal Dual Phases Network for Point Cloud Completion

Zhenjiang Du
Jiale Dou
Zhitao Liu
Jiwei Wei
Guan Wang
Ning Xie
Yang Yang

Point cloud completion aims at completing shapes from their partial. Most existing methods utilized shape’s priors information for point cloud completion, such as inputting the partial and getting the complete one through an encoder-decoder deep learning structure. However, it is very often to easily cause the loss of information in the generation process because of the invisibility of missing areas. Unlike most existing methods directly inferring the missing points using shape priors, we address it as a cross-modality task. We propose a new Cross-modal Dual Phases Network (CDPNet) for shape completion. Our key idea is that the global information of the shape is obtained from the extra single-view image, and the partial point clouds provide the geometric information. After that, the multi-modal features jointly guide the specific structural information. To learn the geometric details of the shape, we chose to use patches to preserve the local geometric feature. In this way, we can generate shapes with enough geometric details. Experimental results show that our method achieves state-of-the-art performance on point cloud completion.

PDF Details DOI

ICLR Conference 2024 Conference Paper

OpenChat: Advancing Open-source Language Models with Mixed-Quality Data

Guan Wang
Sijie Cheng
Xianyuan Zhan
Xiangang Li
Sen Song
Yang Liu 0165

Nowadays, open-source large language models like LLaMA have emerged. Recent developments have incorporated supervised fine-tuning (SFT) and reinforcement learning fine-tuning (RLFT) to align these models with human goals. However, SFT methods treat all training data with mixed quality equally, while RLFT methods require high-quality pairwise or ranking-based preference data. In this study, we present a novel framework, named OpenChat, to advance open-source language models with mixed-quality data. Specifically, we consider the general SFT training data, consisting of a small amount of expert data mixed with a large proportion of sub-optimal data, without any preference labels. We propose the C(onditioned)-RLFT, which regards different data sources as coarse-grained reward labels and learns a class-conditioned policy to leverage complementary data quality information. Interestingly, the optimal policy in C-RLFT can be easily solved through single-stage, RL-free supervised learning, which is lightweight and avoids costly human preference labeling. Through extensive experiments on three standard benchmarks, our openchat-13b fine-tuned with C-RLFT achieves the highest average performance among all 13b open-source language models. Moreover, we use AGIEval to validate the model generalization performance, in which only openchat-13b surpasses the base model. Finally, we conduct a series of analyses to shed light on the effectiveness and robustness of OpenChat. Our code, data, and models are publicly available at https://github.com/imoneoi/openchat and https://huggingface.co/openchat.

Details

EAAI Journal 2024 Journal Article

Semi-supervised soft sensor method for fermentation processes based on physical monotonicity and variational autoencoders

Xinyue Cheng
Zhenhua Yu
Guan Wang
Qingchao Jiang
Zhixing Cao

Data-driven models have shown broad application prospects in soft sensor modeling. However, numerous challenges persist. On the one hand, data-driven soft sensor methods have high requirements on data quality. On the other hand, models relying on limited experimental data often lack physical interpretability. To tackle these challenges, a semi-supervised soft sensor method (PMVAER) for fermentation processes based on physical monotonicity and variational autoencoders (VAEs) is introduced. First, physical monotonicity constraint is incorporated into the loss function of VAEs for regression to ensure that the model's predictions adhere to physical feasibility. Next, considering the disparate sampling frequencies for process and quality variables, this approach is extended to learn from unlabeled data, creating a semi-supervised soft sensor model. The proposed model is validated on simulation and real cases of penicillin fermentation. Comparisons with five other methods verify that the proposed method exhibits exceptional predictive accuracy along with enhanced generalization ability.

Details DOI

NeurIPS Conference 2023 Conference Paper

Evolving Connectivity for Recurrent Spiking Neural Networks

Guan Wang
Yuhao Sun
Sijie Cheng
Sen Song

Recurrent spiking neural networks (RSNNs) hold great potential for advancing artificial general intelligence, as they draw inspiration from the biological nervous system and show promise in modeling complex dynamics. However, the widely-used surrogate gradient-based training methods for RSNNs are inherently inaccurate and unfriendly to neuromorphic hardware. To address these limitations, we propose the evolving connectivity (EC) framework, an inference-only method for training RSNNs. The EC framework reformulates weight-tuning as a search into parameterized connection probability distributions, and employs Natural Evolution Strategies (NES) for optimizing these distributions. Our EC framework circumvents the need for gradients and features hardware-friendly characteristics, including sparse boolean connections and high scalability. We evaluate EC on a series of standard robotic locomotion tasks, where it achieves comparable performance with deep neural networks and outperforms gradient-trained RSNNs, even solving the complex 17-DoF humanoid task. Additionally, the EC framework demonstrates a two to three fold speedup in efficiency compared to directly evolving parameters. By providing a performant and hardware-friendly alternative, the EC framework lays the groundwork for further energy-efficient applications of RSNNs and advances the development of neuromorphic devices. Our code is publicly available at https: //github. com/imoneoi/EvolvingConnectivity.

PDF Details

EAAI Journal 2023 Journal Article

Koopman-operator-based learning control of air-breathing hypersonic vehicles with nonminimum phase properties

Guan Wang
Hongwei Xia

In this article, a prescribed learning controller is developed for nonminimum phase air-breathing hypersonic vehicles (AHVs) in the presence of parametric uncertainties and external disturbances. In comparison with the current state of the art, the most significant feature of our control design lies in introducing the Koopman operator to construct an intelligent output redefinition to overcome the nonminimum phase behavior. To evaluate the current control behavior and enhance the learning ability, an improved continuous-time performance index is developed under the actor–critic learning structure. Furthermore, combined with a nonlinear disturbance observer, prescribed learning control is proposed to design control commands, while compensating for lumped disturbances, including neural approximation errors and external disturbances. Numerical simulations have been performed to highlight the superiority of the proposed learning control.

Details DOI

ICML Conference 2020 Conference Paper

Dynamic Knapsack Optimization Towards Efficient Multi-Channel Sequential Advertising

Xiaotian Hao
Zhaoqing Peng
Yi Ma 0005
Guan Wang
Junqi Jin
Jianye Hao
Shan Chen
Rongquan Bai

In E-commerce, advertising is essential for merchants to reach their target users. The typical objective is to maximize the advertiser’s cumulative revenue over a period of time under a budget constraint. In real applications, an advertisement (ad) usually needs to be exposed to the same user multiple times until the user finally contributes revenue (e. g. , places an order). However, existing advertising systems mainly focus on the immediate revenue with single ad exposures, ignoring the contribution of each exposure to the final conversion, thus usually falls into suboptimal solutions. In this paper, we formulate the sequential advertising strategy optimization as a dynamic knapsack problem. We propose a theoretically guaranteed bilevel optimization framework, which significantly reduces the solution space of the original optimization space while ensuring the solution quality. To improve the exploration efficiency of reinforcement learning, we also devise an effective action space reduction approach. Extensive offline and online experiments show the superior performance of our approaches over state-of-the-art baselines in terms of cumulative revenue.

Details

ICML Conference 2017 Conference Paper

Interactive Learning from Policy-Dependent Human Feedback

James MacGlashan
Mark K. Ho
Robert Tyler Loftin
Bei Peng 0001
Guan Wang
David L. Roberts 0001
Matthew E. Taylor
Michael L. Littman

This paper investigates the problem of interactively learning behaviors communicated by a human teacher using positive and negative feedback. Much previous work on this problem has made the assumption that people provide feedback for decisions that is dependent on the behavior they are teaching and is independent from the learner’s current policy. We present empirical results that show this assumption to be false—whether human trainers give a positive or negative feedback for a decision is influenced by the learner’s current policy. Based on this insight, we introduce Convergent Actor-Critic by Humans (COACH), an algorithm for learning from policy-dependent feedback that converges to a local optimum. Finally, we demonstrate that COACH can successfully learn multiple behaviors on a physical robot.

Details

TIST Journal 2012 Journal Article

Identify Online Store Review Spammers via Social Review Graph

Guan Wang
Sihong Xie
Bing Liu
Philip S. Yu

Online shopping reviews provide valuable information for customers to compare the quality of products, store services, and many other aspects of future purchases. However, spammers are joining this community trying to mislead consumers by writing fake or unfair reviews to confuse the consumers. Previous attempts have used reviewers’ behaviors such as text similarity and rating patterns, to detect spammers. These studies are able to identify certain types of spammers, for instance, those who post many similar reviews about one target. However, in reality, there are other kinds of spammers who can manipulate their behaviors to act just like normal reviewers, and thus cannot be detected by the available techniques. In this article, we propose a novel concept of review graph to capture the relationships among all reviewers, reviews and stores that the reviewers have reviewed as a heterogeneous graph. We explore how interactions between nodes in this graph could reveal the cause of spam and propose an iterative computation model to identify suspicious reviewers. In the review graph, we have three kinds of nodes, namely, reviewer, review, and store. We capture their relationships by introducing three fundamental concepts, the trustiness of reviewers, the honesty of reviews, and the reliability of stores, and identifying their interrelationships: a reviewer is more trustworthy if the person has written more honesty reviews; a store is more reliable if it has more positive reviews from trustworthy reviewers; and a review is more honest if many other honest reviews support it. This is the first time such intricate relationships have been identified for spam detection and captured in a graph model. We further develop an effective computation method based on the proposed graph model. Different from any existing approaches, we do not use an review text information. Our model is thus complementary to existing approaches and able to find more difficult and subtle spamming activities, which are agreed upon by human judges after they evaluate our results.

Details DOI