
Chao WangXidian University · School of Artificial Intelligence
Chao Wang
Doctor of Engineering
About
27
Publications
3,082
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
259
Citations
Introduction
My current research interests include evolutionary computation, multi-task learning and optimization, complex networks, fuzzy cognitive maps, and anomaly detection.
Publications
Publications (27)
Evolutionary algorithms (EAs) maintain populations through evolutionary operators to discover diverse solutions for complex tasks while gathering valuable knowledge, such as historical population data and fitness evaluations. However, traditional EAs face challenges in dynamically adapting to expanding knowledge bases, hindering the efficient explo...
Graph neural architecture search (GNAS) can customize high-performance graph neural network architectures for specific graph tasks or datasets. However, existing GNAS methods begin searching for architectures from a zero-knowledge state, ignoring the prior knowledge that may improve the search efficiency. The available knowledge base (e.g. NAS-Benc...
Solving the complex challenges of sophisticated terrain and multi-scale targets in remote sensing (RS) images requires a synergistic combination of Transformer and convolutional neural network (CNN). However, crafting effective CNN architectures remains a major challenge. To address these difficulties, this study introduces the knowledge guided evo...
Existing efforts are dedicated to designing many topologies and graph-aware strategies for the graph Transformer, which greatly improve the model’s representation capabilities. However, manually determining the suitable Transformer architecture for a specific graph dataset or task requires extensive expert knowledge and laborious trials. This artic...
Nature, with its numerous surprising rules, serves as a rich source of creativity for the development of artificial intelligence, inspiring researchers to create several nature-inspired intelligent computing paradigms based on natural mechanisms. Over the past decades, these paradigms have revealed effective and flexible solutions to practical and...
Existing efforts are dedicated to designing many topologies and graph-aware strategies for the graph Transformer, which greatly improve the model's representation capabilities. However, manually determining the suitable Transformer architecture for a specific graph dataset or task requires extensive expert knowledge and laborious trials. This paper...
The construction of machine learning models involves many bi-level multi-objective optimization problems (BL-MOPs), where upper level (UL) candidate solutions must be evaluated via training weights of a model in the lower level (LL). Due to the Pareto optimality of sub-problems and the complex dependency across UL solutions and LL weights, an UL so...
Influence maximization is a crucial issue for mining the deep information of social networks, which aims to select a seed set from the network to maximize the number of influenced nodes. To evaluate the influence spread of a seed set efficiently, existing studies have proposed transformations with lower computational costs to replace the expensive...
The construction of machine learning models involves many bi-level multiobjective optimization problems (BL-MOPs), where upper-level (UL) candidate solutions must be evaluated via training weights of a model in the lower level (LL). Due to the Pareto optimality of subproblems and the complex dependency across UL solutions and LL weights, a UL solut...
Deep representation learning has improved automatic remote sensing change detection (RSCD) in recent years. Existing methods emphasize primarily convolutional neural networks (CNNs) or transformer-based networks. However, most of them neither effectively combine CNNs and transformers nor use prior geometric information to refine regions. In this ar...
Learning to optimize the area under the receiver operating characteristics curve (AUC) performance for imbalanced data has attracted much attention in recent years. Although there have been several methods of AUC optimization, scaling up AUC optimization is still an open issue due to its pairwise learning style. Maximizing AUC in the large-scale da...
Influence maximization is a crucial issue for mining the deep information of social networks, which aims to select a seed set from the network to maximize the number of influenced nodes. To evaluate the influence spread of a seed set efficiently, existing efforts have proposed proxy models (transformations) with lower computational costs to replace...
Currently, the problem of uncovering complex network structure and dynamics from time series is prominent in many fields. Despite the recent progress in this area, reconstructing large-scale networks from limited data remains a tough problem. Existing works treat connections of nodes as continuous values, leaving a challenge of setting a proper cut...
Currently, the problem of uncovering complex network structure and dynamics from time series is prominent in many fields. Despite the recent progress in this area, reconstructing large-scale networks from limited data remains a tough problem. Existing works treat connections of nodes as continuous values, leaving a challenge of setting a proper cut...
Learning to optimize the area under the receiver operating characteristics curve (AUC) performance for imbalanced data has attracted much attention in recent years. Although there have been several methods of AUC optimization, scaling up AUC optimization is still an open issue due to its pairwise learning style. Maximizing AUC in the large-scale da...
This paper focuses on inferring network structure and community structure from the dynamics of the nonlinear and complex dynamical systems, which is prominent in many fields. Many methods have been proposed to solely address these two problems, but none of them consider explicit shareable knowledge across these two tasks. Inspired by the fact that...
Learning to optimize the area under the receiver operating characteristics curve (AUC) performance for imbalanced data has attracted much attention in recent years. Although there have been several methods of AUC optimization, scaling up AUC optimization is still an open issue due to its pairwise learning style. Maximizing AUC in the large-scale da...
Currently, the problem of uncovering complex network structure and dynamics from time series is prominent in many fields. Despite the recent progress in this area, reconstructing
large-scale networks from limited data remains a tough problem. Existing works treat connections of nodes as continuous values, leaving a challenge of setting a proper cut...
Currently, the problem of uncovering complex network structure and dynamics from time series is prominent in many fields. Despite the recent progress in this area, reconstructing large-scale networks from limited data remains a tough problem. Existing works treat connections of nodes as continuous values, leaving a challenge of setting a proper cut...
Due to the multilayer nature of real-world systems, the problem of inferring multilayer network structures from nonlinear and complex dynamical systems is prominent in many fields, including engineering, biological, physical, and computer sciences. Many network reconstruction methods have been proposed to address this problem, but none of them cons...
Fuzzy cognitive maps (FCMs) are a powerful tool for simulating and analyzing complex systems. Many efficient methods based on evolutionary algorithms have been proposed to learn small-scale FCMs. However, large number of function evaluations of those methods make them difficult to cope with large-scale FCM learning problems. To overcome this issue,...
Influence maximization is the problem of finding a small subset of seed nodes to maximize the spread of influence in a social network and is an NP-hard problem. In this paper, Pareto optimization is employed for influence maximization (POIM) where the task of finding a set of influential nodes is reformulated as a bi-objective problem. It has been...
Evolutionary multi-task optimization (EMTO) has recently attracted widespread attention in the evolutionary computation community, which solves two or more tasks simultaneously to improve the convergence characteristics of tasks when individually optimized. Effective knowledge between tasks is transferred by taking advantage of the parallelism of p...
Many complex dynamic systems in the real world need to be described by multilayer networks. How to reveal the reconstruction of the multilayer nonlinear dynamic network structure from the observed streaming data is one of the core issues of dynamic system research. Although people have proposed many methods to reconstruct multilayer nonlinear dynam...
Influence maximization is the problem of finding a small subset of seed nodes to maximize the spread of influence in a social network and is an NP-hard problem. In this paper, we propose Pareto optimization for influence maximization (POIM) where the task of finding a set of influential nodes is re-formulated as a bi-objective problem. Pareto optim...