检索结果-内蒙古大学图书馆

Preference Multi-Objective Evolutionary Optimization Based on Angle Decompositio

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Gao, Yubo Yu, Fan Zou, Juan Tang, Huanrong Zheng, Jinhua Key Laboratory of Intelligent Computing and Information Processing Ministry of Education Xiangtan University Xiangtan411105 China School of Computer Science School of Cyberspace Science University of Xiangtan Xiangtan411105 China School of Traffic and Transport Engineering Central South University Changsha410083 China

The optimal solution set of multi-objective optimization problems (MOPs) exists in a Pareto optimal front (PF) consisting of many Pareto non-dominated solutions. Still, the decision maker (DM) may be interested in only some of the solutions in the PF, called the region of interest (ROI). However, the existing strategies to determine the ROI for the DM are only limited to obtaining the preference region close to the preference point, which does not fully realize the essence of the preference multi-objective optimization problems (PMOPs), i.e., the solutions closer to the preference point should be more preferred by the DM. To better investigate the effectiveness of solving PMOPs, this paper proposes a preference multi-objective optimization evolutionary algorithm (PMOEA) based on the angle decomposition between objectives (MOEA/D-DAP) to avoid the challenge of preference information loss in PMOPs with increasing objective space dimension. Meanwhile, the reference vector generation method proposed by the MOEA/D-DAP enables preference solutions that align with the DM's needs to be closer to the preference points. Therefore, the preference solutions that are more in line with the needs of the DM exist closer to the preference points. Experiments on benchmark problems with dual and high dimensional objectives demonstrate the high effectiveness of the proposed MOEA/D-DAP in obtaining the ROI of the PMOPs. © 2023, The Authors. All rights reserved.

关键词： Multiobjective optimization

S2CCT: Self-Supervised Collaborative CNN-Transformer for Few-shot Medical Image Segmentation

学校读者我要写书评

暂无评论

S2CCT: Self-Supervised Collaborative CNN-Transformer for Few...

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Rongzhou Zhou Ziqi Shu Weixing Xie Junfeng Yao Qingqi Hong Center for Digital Media Computing School of Film School of Informatics Xiamen University Xiamen China National Institute for Data Science in Health and Medicine Xiamen University Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Ministry of Culture and Tourism Institute of Artificial Intelligence Xiamen University Xiamen China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Self-supervised pre-training followed by fine-tuning is a potent paradigm for few-shot learning, leveraging extensive unlabeled data with remarkable efficacy. Current self-supervised methods often lean towards Vision Transformers (ViTs) rather than CNN-Transformer hybrid architectures, which generally demonstrate superior performance. However, this reliance on ViTs can lead to poor perception of local features by the model. The challenge lies in designing a suitable proxy task for hybrid architectures like CNN-Transformers, which have significant structural differences. Additionally, the current organization of CNN-Transformer hybrid backbones is often sequential, hindering collaboration during pre-training and the acquisition of robust representations. To address these issues, we propose Self-Supervised Collaborative CNN-Transformer (S 2 CCT) for few-shot medical image segmentation. This framework introduces three innovative designs: (1) a composite proxy task based on image masking and image super-resolution tailored for CNN-Transformer hybrid architectures, enabling the backbone to acquire robust representations during pre-training that can be transferred to downstream tasks; (2) a parallel CNN-Transformer architecture that better attends to multi-scale features in images, making it more suitable for dense prediction tasks like image segmentation; (3) a sparse and dense feature fusion module to enhance collaboration between the two encoders. Experiments demonstrate that S 2 CCT outperforms previous state-of-the-art methods on two public medical image segmentation benchmarks, i.e., ACDC and KiTs19. The code and pretrained models will be released soon.

关键词： Image segmentation Three-dimensional displays Superresolution Collaboration Organizations Feature extraction Transformers Medical diagnosis Medical diagnostic imaging Knowledge transfer

Rephrasing the Reference for Non-Autoregressive Machine Translation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Shao, Chenze Zhang, Jinchao Zhou, Jie Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Pattern Recognition Center WeChat AI Tencent Inc China

Non-autoregressive neural machine translation (NAT) models suffer from the multi-modality problem that there may exist multiple possible translations of a source sentence, so the reference sentence may be inappropriate for the training when the NAT output is closer to other translations. In response to this problem, we introduce a rephraser to provide a better training target for NAT by rephrasing the reference sentence according to the NAT output. As we train NAT based on the rephraser output rather than the reference sentence, the rephraser output should fit well with the NAT output and not deviate too far from the reference, which can be quantified as reward functions and optimized by reinforcement learning. Experiments on major WMT benchmarks and NAT baselines show that our approach consistently improves the translation quality of NAT. Specifically, our best variant achieves comparable performance to the autoregressive Transformer, while being 14.7 times more efficient in inference. Copyright © 2022, The Authors. All rights reserved.

关键词： Neural machine translation

Characterization and construction of optimal binary linear codes with one-dimensional hull

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Shitao Shi, Minjia Kim, Jon-Lark The School of Mathematical Sciences Anhui University Hefei230601 China The Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education The School of Mathematical Sciences Anhui University Hefei230601 China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China The Department of Mathematics Sogang University Seoul Korea Republic of

The hull of a linear code over finite fields is the intersection of the code and its dual, and linear codes with small hulls have applications in computational complexity and information protection. Linear codes with the smallest hull are LCD codes, which have been widely studied. Recently, several papers were devoted to related LCD codes over finite fields with size greater than 3 to linear codes with one-dimensional or higher dimensional hull. Therefore, an interesting and non-trivial problem is to study binary linear codes with one-dimensional hull with connection to binary LCD codes. The objective of this paper is to study some properties of binary linear codes with one-dimensional hull, and establish their relation with binary LCD codes. Some interesting inequalities are thus obtained. Using such a characterization, we study the largest minimum distance done(n, k) among all binary linear [n, k] codes with one-dimensional hull. We determine the largest minimum distances done(n, n − k) for k ≤ 5 and done(n, k) for k ≤ 4 or 14 ≤ n ≤ 24. We partially determine the exact value of done(n, k) for k = 5 or 25 ≤ n ≤ *** Codes 94B05, 15B05, 12E10 Copyright © 2022, The Authors. All rights reserved.

关键词： Optimal systems

ReconBoost: Boosting Can Achieve Modality Reconcilement

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hua, Cong Xu, Qianqian Bao, Shilong Yang, Zhiyong Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current paradigms of multi-modal learning tend to explore multi-modal features simultaneously. The resulting gradient prohibits further exploitation of the features in the weak modality, leading to modality competition, where the dominant modality overpowers the learning process. To address this issue, we study the modality-alternating learning paradigm to achieve reconcilement. Specifically, we propose a new method called ReconBoost to update a fixed modality each time. Herein, the learning objective is dynamically adjusted with a reconcilement regularization against competition with the historical models. By choosing a KL-based reconcilement, we show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others and help enhance the overall performance. The major difference with the classic GB is that we only preserve the newest model for each modality to avoid overfitting caused by ensembling strong learners. Furthermore, we propose a memory consolidation scheme and a global rectification scheme to make this strategy more effective. Experiments over six multi-modal benchmarks speak to the efficacy of the method. We release the code at https://***/huacong/ReconBoost. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

Interpretable multi-view attention network for drug-drug interaction prediction

学校读者我要写书评

暂无评论

Interpretable multi-view attention network for drug-drug int...

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xuan Lin Qi Wen Sijie Yang Zu-Guo Yu Yahui Long Xiangxiang Zeng College of Computer Science Xiangtan University China Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University China Singapore Immunology Network (SIgN) Agency for Science Technology and Research(A*STAR) Singapore College of Information Science and Engineering Hunan University China

Drug-drug interaction (DDI) plays an increasingly crucial role in drug discovery. Predicting potential DDI is also essential for clinical research. Given the high cost and risk of wet-lab experiments, in-silico DDI prediction is an alternative choice. Recently, deep learning methods have been developed for DDI prediction. However, most of existing methods focus on feature extraction from either molecular SMILES sequences or drug interactive networks, ignoring the valuable complementary information that can be derived from these two views. In this paper, we propose a novel interpretable Multi-View Attention network (MVA-DDI) for DDI prediction. MVA-DDI can effectively extracts drug representations from different perspectives to improve DDI prediction. Specifically, for a given drug, we design a transformer-based encoder and a graph convolutional networkbased encoder to learn sequence and graph representations from SMILES sequence and molecular graph, respectively. To fully exploit the complementary information between the sequence and molecular views, an attention mechanism is further adopted to adaptively aggregate the sequence and graph representations by taking the importance of different views into accounts, generating the final drug representations. Comparison experiments demonstrated that our MVA-DDI 1 model achieved superior performance to state-of-the-art models on DDI prediction.

关键词：

GK: A Graphormer Architecture Based Knowledge Graph Reasoning Model for Link Prediction

学校读者我要写书评

暂无评论

GK: A Graphormer Architecture Based Knowledge Graph Reasonin...

IEEE International Conference on Big Data and Cloud computing (BdCloud)

作者： Yueiia Wu Jian-tao Zhou Ministry of Education Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Inner Mongolia Key Laboratory of Social Computing and Data Processing College of Computer Science Inner Mongolia University National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Engineering Research Center of Ecological Big Data Hohhot China

Knowledge Graph has become a dominant research field in graph theory, but its incompleteness and sparsity hinder its application in various fields. Knowledge Graph Reasoning aims to alleviate these problems by deducing new knowledge or identifying false knowledge from existing knowledge. Recently, the Graph Convolution Network (GCN) based method is one of the most advanced methods to realize knowledge graph reasoning. However, it still suffers from some problems such as incomplete neighbor information aggregation and slow training speed. This paper proposes a knowledge graph reasoning model named GK for the link prediction task, which obtains better performance than existing GCN-based methods by introducing Graphormer into knowledge reasoning. The GK first proposes that nodes and their surroundings can be regarded as a hierarchical architecture that enables the model to capture more practical reasoning information to improve prediction accuracy. In addition, to accelerate the training speed of the model on the large-scale Knowledge Graph, we present a faster shortest path-finding method F-SPF in the edge coding process. Extensive experimental results show that the GK model can obtain the state-of-the-art prediction results of current GCN-based methods and can improve the training speed.

关键词： Training Knowledge engineering Knowledge graphs Predictive models Prediction algorithms Feature extraction Cognition

Dynamics-Based Algorithm-Level Privacy Preservation for Push-Sum Average Consensus

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cheng, Huqiang Xie, Mengying Yang, Xiaowei Lü, Qingguo Li, Huaqing Key Laboratory of Dependable Services Computing in Cyber Physical Society-Ministry of Education College of Computer Science Chongqing University Chongqing401331 China School of Software Engineering South China University of Technology Guangzhou510006 China Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing400715 China

In the intricate dance of multi-agent systems, achieving average consensus is not just vital–it is the backbone of their functionality. In conventional average consensus algorithms, all agents reach an agreement by individual calculations and sharing information with their respective neighbors. Nevertheless, the information interactions that occur in the communication network may make sensitive information be revealed. In this paper, we develop a new privacy-preserving average consensus method on unbalanced directed networks. Specifically, we ensure privacy preservation by carefully embedding randomness in mixing weights to confuse communications and introducing an extra auxiliary parameter to mask the state-updated rule in initial several iterations. In parallel, we exploit the intrinsic robustness of consensus dynamics to guarantee that the average consensus is precisely achieved. Theoretical results demonstrate that the designed algorithms can converge linearly to the exact average consensus value and can guarantee privacy preservation of agents against both honest-but-curious and eavesdropping attacks. © 2023, CC BY.

关键词： Consensus algorithm

Amplitude Expansion Phase Field Crystal (APFC) Modeling based Efficient Dislocation Simulations using Fourier Pseudospectral Method

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wei, Xinyi Wang, Yangshuai Jiang, Kai Zhang, Lei School of Mathematical Sciences Institute of Natural Sciences and MOE-LSC Shanghai Jiao Tong University Shanghai200240 China Department of Mathematics Faculty of Science National University of Singapore 10 Lower Kent Ridge Road Singapore Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China

Crystalline defects play a critical role in determining the properties of crystalline solids, underscoring the need for accurate computational methods to study them. Lattice deformation in dislocation simulations, which involves changes in atomic positions, can be described either microscopically by specific atomic configurations or macroscopically by continuum elasticity, each with inherent limitations. The complex amplitude expansion of the phase field crystal (APFC) model provides a mesoscopic approach that bridges these scales. In this paper, we introduce a Fourier pseudospectral method for efficiently solving the APFC model in the context of crystalline defect simulations. This study marks the first application of the Fourier pseudospectral method to the APFC model. The method fully exploits the system’s periodicity and facilitates the implementation of periodic boundary conditions, thanks to its high accuracy and computational efficiency. Numerical experiments conducted on two-dimensional triangular lattices and three-dimensional body-centered cubic lattices for edge dislocation geometry optimization have produced strain field images that align well with by continuum elasticity predictions. The findings demonstrate the potential of the APFC model to accurately capture the complex strain fields associated with dislocations at the mesoscopic scales, a key step toward modeling more intricate crystalline defect structures and dynamics. © 2024, CC BY.

关键词： Edge dislocations