Query：
学者姓名：冀俊忠
Refining：
Year
Type
Indexed by
Source
Complex
Former Name
Co-Author
Language
Clean All
Abstract ：
Solving dynamic multiobjective optimization problems (DMOPs) is extremely challenging due to the need to address multiple conflicting objectives that change over time. Transfer prediction- based strategies typically leverage solutions from historical environments to generate an initial population for a new environment. However, these strategies often overlook the similarity between the historical and new environments, which can negatively impact the quality of the initial population. To address this issue, we propose a similar environment transfer strategy. Firstly, we select Pareto-optimal solutions from a randomly generated population in the new environment to form a prior Pareto set (PS). The prior PS is expand by oversampling sparse solutions. Then, we apply the maximum mean discrepancy (MMD) to measure the discrepancy between the prior PS and the PS from each historical environment. The historical environment with the smallest MMD is identified as the similar environment. Finally, we use solutions from this similar environment to establish a kernelized easy transfer learning model, which is employed to predict the quality of random solutions in the new environment. The initial population is formed by combining excellent solutions predicted by the model with the prior PS. Experimental results demonstrate that the proposed strategy significantly outperforms several state-of-the-art strategies.
Keyword ：
Dynamic multiobjective optimization Dynamic multiobjective optimization Transfer learning Transfer learning Prediction-based strategy Prediction-based strategy Maximum mean discrepancy Maximum mean discrepancy
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Ji, Junzhong , Zhang, Xiaoyu , Yang, Cuicui et al. A similar environment transfer strategy for dynamic multiobjective optimization [J]. | INFORMATION SCIENCES , 2025 , 707 . |
| MLA | Ji, Junzhong et al. "A similar environment transfer strategy for dynamic multiobjective optimization" . | INFORMATION SCIENCES 707 (2025) . |
| APA | Ji, Junzhong , Zhang, Xiaoyu , Yang, Cuicui , Li, Xiang , Sui, Guangyuan . A similar environment transfer strategy for dynamic multiobjective optimization . | INFORMATION SCIENCES , 2025 , 707 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Multi-head attention (MA), which allows the model to jointly attend to crucial information from diverse representation subspaces through its heads, has yielded remarkable achievement in image captioning. However, there is no explicit mechanism to ensure MA attends to appropriate positions in diverse subspaces, resulting in overfocused attention for each head and redundancy between heads. In this paper, we propose a novel Intra- and Inter-Head Orthogonal Attention (I(2)OA) to efficiently improve MA in image captioning by introducing a concise orthogonal regularization to heads. Specifically, Intra-Head Orthogonal Attention enhances the attention learning of MA by introducing orthogonal constraint to each head, which decentralizes the object-centric attention to more comprehensive content-aware attention. Inter-Head Orthogonal Attention reduces the heads redundancy by applying orthogonal constraint between heads, which enlarges the diversity of representation subspaces and improves the representation ability for MA. Moreover, the proposed I(2)OA is flexible to combine with various multi-head attention based image captioning methods and improve the performances without increasing model complexity and parameters. Experiments on the MS COCO dataset demonstrate the effectiveness of the proposed model.
Keyword ：
Visualization Visualization Transformers Transformers multi-head attention (MA) multi-head attention (MA) Redundancy Redundancy Accuracy Accuracy orthogonal constraint orthogonal constraint Head Head Decoding Decoding Feature extraction Feature extraction Optimization Optimization Dogs Dogs Correlation Correlation Image captioning Image captioning
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhang, Xiaodan , Jia, Aozhe , Ji, Junzhong et al. Intra- and Inter-Head Orthogonal Attention for Image Captioning [J]. | IEEE TRANSACTIONS ON IMAGE PROCESSING , 2025 , 34 : 594-607 . |
| MLA | Zhang, Xiaodan et al. "Intra- and Inter-Head Orthogonal Attention for Image Captioning" . | IEEE TRANSACTIONS ON IMAGE PROCESSING 34 (2025) : 594-607 . |
| APA | Zhang, Xiaodan , Jia, Aozhe , Ji, Junzhong , Qu, Liangqiong , Ye, Qixiang . Intra- and Inter-Head Orthogonal Attention for Image Captioning . | IEEE TRANSACTIONS ON IMAGE PROCESSING , 2025 , 34 , 594-607 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
In recent years, the discovery of brain effective connectivity (EC) networks through computational analysis of functional magnetic resonance imaging (fMRI) data has gained prominence in neuroscience and neuroimaging. However, owing to the influence of diverse factors during data collection and processing, fMRI data typically exhibit high noise and limited sample characteristics, consequently leading to the suboptimal performance of current methods. In this paper, we propose a novel brain effective connectivity discovery method based on meta-reinforcement learning, called MetaRLEC. The method mainly consists of three modules: actor, critic, and meta-critic. MetaRLEC first employs an encoder-decoder framework: The encoder utilizing a transformer converts noisy fMRI data into a state embedding, and the decoder employing bidirectional LSTM discovers brain region dependencies from the state and generates actions (EC networks). Then, a critic network evaluates these actions, incentivizing the actor to learn higher-reward actions amidst the high-noise setting. Finally, a meta-critic framework facilitates online learning of historical state-action pairs, integrating an action-value neural network and supplementary training losses to enhance the model's adaptability to small-sample fMRI data. We conduct comprehensive experiments on both simulated and real-world data to demonstrate the efficacy of our proposed method.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhang, Zuozhen , Ji, Junzhong , Liu, Jinduo . MetaRLEC: Meta-Reinforcement Learning for Discovery of Brain Effective Connectivity [J]. | THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 9 , 2024 : 10261-10269 . |
| MLA | Zhang, Zuozhen et al. "MetaRLEC: Meta-Reinforcement Learning for Discovery of Brain Effective Connectivity" . | THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 9 (2024) : 10261-10269 . |
| APA | Zhang, Zuozhen , Ji, Junzhong , Liu, Jinduo . MetaRLEC: Meta-Reinforcement Learning for Discovery of Brain Effective Connectivity . | THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 9 , 2024 , 10261-10269 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Using deep models to classify brain functional networks (BFNs) for the auxiliary diagnosis and treatment of brain diseases has become increasingly popular. However, the unexplainability of deep models has seriously hindered their applications in computer-aided diagnosis. In addition, current explanation methods mostly focus on natural images, which cannot be directly used to explain the deep model for BFN classification. In this paper, we propose a novel concept-level causal explanation method for BFN classification called CLCEM. First, CLCEM employs the causal learning method to extract concepts that are meaningful to humans from BFNs. Second, it aggregates the same concepts to obtain the contribution of each concept to the model output. Finally, CLCEM adds the contribution of each concept to make a diagnosis. The experimental results show that our CLCEM can not only accurately identify brain regions related to specific brain diseases but also make decisions based on the concepts of these brain regions, which enables humans to understand the decision-making process without performance degradation.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Liu, Jinduo , Wang, Feipeng , Ji, Junzhong . Concept-Level Causal Explanation Method for Brain Function Network Classification [J]. | PROCEEDINGS OF THE THIRTY-THIRD INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2024 , 2024 : 3087-3096 . |
| MLA | Liu, Jinduo et al. "Concept-Level Causal Explanation Method for Brain Function Network Classification" . | PROCEEDINGS OF THE THIRTY-THIRD INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2024 (2024) : 3087-3096 . |
| APA | Liu, Jinduo , Wang, Feipeng , Ji, Junzhong . Concept-Level Causal Explanation Method for Brain Function Network Classification . | PROCEEDINGS OF THE THIRTY-THIRD INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2024 , 2024 , 3087-3096 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
近年来,基于深度学习的脑功能连接分类方法成为脑科学中的研究热点。为了进一步获得具有判别性的大脑连接特征,进而提升脑功能连接的分类准确率,本文提出了一种基于对比学习的卷积神经网络脑功能连接分类方法。对比学习是一种特殊的自监督学习框架,通过在特征空间中对正样本与负样本进行对比,充分挖掘不同样本间的差异性。首先,提出一种融合多视角信息的对比学习框架,采用实例-实例的对比学习挖掘样本间的差异性,并利用实例-原型的对比学习挖掘样本与样本簇之间的差异性。其次,将多视角对比学习与目标分类任务联合训练,增强所学特征的判别性,提升卷积神经网络的分类性能。本文使用ABIDE-I数据集进行实验,结果表明,所提方法能够使脑功能连接的分类效果得到有效提升,并且能够对重要的功能连接与脑区进行准确识别。
Keyword ：
对比学习 对比学习 脑功能连接分类 脑功能连接分类 卷积神经网络 卷积神经网络
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 何庆钊 , 于乐 , 冀俊忠 et al. 基于对比学习的卷积神经网络脑功能连接分类方法 [C] //2023中国自动化大会 . 2023 . |
| MLA | 何庆钊 et al. "基于对比学习的卷积神经网络脑功能连接分类方法" 2023中国自动化大会 . (2023) . |
| APA | 何庆钊 , 于乐 , 冀俊忠 , 雷名龙 . 基于对比学习的卷积神经网络脑功能连接分类方法 2023中国自动化大会 . (2023) . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Deep forest is a new multi-layer ensemble model, where the high time costs and storage requirements inhibit its large-scale application. However, current deep forest pruning methods used to alleviate these drawbacks do not consider its cascade coupling characteristics. Therefore, we propose a tri-objective optimization-based cascade ensemble pruning (TOOCEP) algorithm for it. Concretely, we first present a tri-objective optimization-based single-layer pruning (TOOSLP) method to prune its single-layer by simultaneously optimizing three objectives, namely accuracy, independent diversity, and coupled diversity. Particularly, the coupled diversity is designed for deep forest to deal with the coupling relationships between its adjacent layers. Then, we perform TOOSLP in a cascade framework to prune the deep forest layer-by-layer. Experimental results on 15 UCI datasets show that TOOCEP outperforms several state-ofthe-art methods in accuracy and pruned rate, which significantly reduces the storage space and accelerate the prediction speed of deep forest. & COPY; 2023 Elsevier Ltd. All rights reserved.
Keyword ：
Deep forest Deep forest Ensemble pruning Ensemble pruning Ensemble learning Ensemble learning Coupled diversity Coupled diversity Multi-objective optimization Multi-objective optimization
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Ji, Junzhong , Li, Junwei . Tri-objective optimization-based cascade ensemble pruning for deep forest [J]. | PATTERN RECOGNITION , 2023 , 143 . |
| MLA | Ji, Junzhong et al. "Tri-objective optimization-based cascade ensemble pruning for deep forest" . | PATTERN RECOGNITION 143 (2023) . |
| APA | Ji, Junzhong , Li, Junwei . Tri-objective optimization-based cascade ensemble pruning for deep forest . | PATTERN RECOGNITION , 2023 , 143 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Using machine learning methods to estimate brain effective connectivity networks from functional magnetic resonance imaging (fMRI) data has garnered significant attention in the fields of neuroinformatics and bioinformatics. However, existing methods usually require retraining the model for each subject, which ignores the knowledge shared across subjects. In this paper, we propose a novel framework for estimating effective connectivity based on an amortization transformer, named AT-EC. In detail, AT-EC first employs an amortization transformer to model the dynamics of fMRI time series and infer brain effective connectivity across different subjects, which can train an amortized model that leverages the shared knowledge from different subjects. Then, an assisted learning mechanism based on functional connectivity is designed to assist the estimation of the brain effective connectivity network. Experimental results on both simulated and real-world data demonstrate the efficacy of our method.
Keyword ：
brain effective connectivity brain effective connectivity transformer transformer functional magnetic resonance imaging functional magnetic resonance imaging amortization learning amortization learning
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhang, Zuozhen , Zhang, Ziqi , Ji, Junzhong et al. Amortization Transformer for Brain Effective Connectivity Estimation from fMRI Data [J]. | BRAIN SCIENCES , 2023 , 13 (7) . |
| MLA | Zhang, Zuozhen et al. "Amortization Transformer for Brain Effective Connectivity Estimation from fMRI Data" . | BRAIN SCIENCES 13 . 7 (2023) . |
| APA | Zhang, Zuozhen , Zhang, Ziqi , Ji, Junzhong , Liu, Jinduo . Amortization Transformer for Brain Effective Connectivity Estimation from fMRI Data . | BRAIN SCIENCES , 2023 , 13 (7) . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
A wealth of causal relationships exists in biological systems, both causal brain networks and causal protein signaling networks are very classical causal biological networks (CBNs). Learning CBNs from biological signal data reliably is a critical problem today. However, most of the existing methods are not excellent enough in terms of accuracy and time performance, and tend to fall into local optima because they do not take full advantage of global information. In this paper, we propose a parallel ant colony optimization algorithm to learn causal biological networks from biological signal data, called PACO. Specifically, PACO first maps the construction of CBNs to ants, then searches for CBNs in parallel by simulating multiple groups of ants foraging, and finally obtains the optimal CBN through pheromone fusion and CBNs fusion between different ant colonies. Extensive experimental results on simulation data sets as well as two real-world data sets, the fMRI signal data set and the Single-cell data set, show that PACO can accurately and efficiently learn CBNs from biological signal data.
Keyword ：
causal protein signaling networks causal protein signaling networks CBNs fusion CBNs fusion causal biological networks causal biological networks parallel ant colony optimization parallel ant colony optimization pheromone fusion pheromone fusion causal brain networks causal brain networks
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhai, Jihao , Ji, Junzhong , Liu, Jinduo . Learning Causal Biological Networks with Parallel Ant Colony Optimization Algorithm [J]. | BIOENGINEERING-BASEL , 2023 , 10 (8) . |
| MLA | Zhai, Jihao et al. "Learning Causal Biological Networks with Parallel Ant Colony Optimization Algorithm" . | BIOENGINEERING-BASEL 10 . 8 (2023) . |
| APA | Zhai, Jihao , Ji, Junzhong , Liu, Jinduo . Learning Causal Biological Networks with Parallel Ant Colony Optimization Algorithm . | BIOENGINEERING-BASEL , 2023 , 10 (8) . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Multiobjective evolutionary algorithms (MOEAs) have received much attention in multiobjective optimization in recent years due to their practicality. With limited computational resources, most existing MOEAs cannot efficiently solve large-scale multiobjective optimization problems (LSMOPs) that widely exist in the real world. This paper innovatively proposes a dual decomposition strategy (DDS) that can be embedded into many existing MOEAs to improve their performance in solving LSMOPs. Firstly, the outer decomposition uses a sliding window to divide large-scale decision variables into overlapped subsets of small-scale ones. A small-scale multiobjective optimization problem (MOP) is generated every time the sliding window slides. Then, once a small-scale MOP is generated, the inner decomposition immediately creates a set of global direction vectors to transform it into a set of single-objective optimization problems (SOPs). At last, all SOPs are optimized by adopting a block coordinate descent strategy, ensuring the solution's integrity and improving the algorithm's performance to some extent. Comparative experiments on benchmark test problems with seven state-of-the-art evolutionary algorithms and a deep learning-based algorithm framework have shown the remarkable efficiency and solution quality of the proposed DDS. Meanwhile, experiments on two real-world problems show that DDS can achieve the best performance beyond at least one order of magnitude with up to 3072 decision variables.
Keyword ：
Decomposition Decomposition Block coordinate descent Block coordinate descent Large-scale multiobjective optimization Large-scale multiobjective optimization Sliding window Sliding window
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Yang, Cuicui , Wang, Peike , Ji, Junzhong . A dual decomposition strategy for large-scale multiobjective evolutionary optimization [J]. | NEURAL COMPUTING & APPLICATIONS , 2022 , 35 (5) : 3767-3788 . |
| MLA | Yang, Cuicui et al. "A dual decomposition strategy for large-scale multiobjective evolutionary optimization" . | NEURAL COMPUTING & APPLICATIONS 35 . 5 (2022) : 3767-3788 . |
| APA | Yang, Cuicui , Wang, Peike , Ji, Junzhong . A dual decomposition strategy for large-scale multiobjective evolutionary optimization . | NEURAL COMPUTING & APPLICATIONS , 2022 , 35 (5) , 3767-3788 . |
| Export to | NoteExpress RIS BibTex |
Abstract ：
Recently, functional brain network analysis via graph neural networks has achieved state-of-the-art results as it can directly extract information from irregular graphs without any approximation. However, current methods remain limited in exploring the high-order structural information of brain networks. To address this issue, we propose a hypergraph attention network for functional brain network classification (FC-HAT). First, we build a dynamic hypergraph generation phase and model each brain network as a hypergraph to preserve the high-order information. The pair-wise and community-wise similarities in functional brain networks are separately captured by k nearest neighbors and k-means. Theoretical analysis shows that the constructed hypergraph exhibits superior spectral properties. Then, we design a hypergraph attention aggregation phase to further extract information in hypergraphs. This includes node and hyperedge attention layers that can separately aggregate features among nodes and hyperedges. Finally, the two phases are jointly optimized in an end-to-end manner, which can dynamically update hypergraphs and node embeddings along with the training process. Experimental results on ABIDE-I and ADHD-200 demonstrate the effectiveness of FC-HAT in cerebral disease classification. Moreover, the abnormal connectivity patterns and brain regions identified by FC-HAT are found to be more likely to become biomarkers associated with cerebral diseases.(c) 2022 Elsevier Inc. All rights reserved.
Keyword ：
Graph Neural Networks Graph Neural Networks Functional Brain Networks Functional Brain Networks Hypergraphs Hypergraphs Attention Mechanism Attention Mechanism
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Ji, Junzhong , Ren, Yating , Lei, Minglong . FC-HAT: Hypergraph attention network for functional brain network classification [J]. | INFORMATION SCIENCES , 2022 , 608 : 1301-1316 . |
| MLA | Ji, Junzhong et al. "FC-HAT: Hypergraph attention network for functional brain network classification" . | INFORMATION SCIENCES 608 (2022) : 1301-1316 . |
| APA | Ji, Junzhong , Ren, Yating , Lei, Minglong . FC-HAT: Hypergraph attention network for functional brain network classification . | INFORMATION SCIENCES , 2022 , 608 , 1301-1316 . |
| Export to | NoteExpress RIS BibTex |
Export
| Results： |
Selected to |
| Format： |
