检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Huang, Sili Hu, Jifeng Chen, Hechang Sun, Lichao Yang, Bo School of Artificial Intelligence Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China Lehigh University BethlehemPA United States

In-context learning is a promising approach for offline reinforcement learning (RL) to handle online tasks, which can be achieved by providing task prompts. Recent works demonstrated that in-context RL could emerge with self-improvement in a trial-and-error manner when treating RL tasks as an across-episodic sequential prediction problem. Despite the self-improvement not requiring gradient updates, current works still suffer from high computational costs when the across-episodic sequence increases with task horizons. To this end, we propose an In-context Decision Transformer (IDT) to achieve self-improvement in a high-level trial-and-error manner. Specifically, IDT is inspired by the efficient hierarchical structure of human decision-making and thus reconstructs the sequence to consist of high-level decisions instead of low-level actions that interact with environments. As one high-level decision can guide multi-step low-level actions, IDT naturally avoids excessively long sequences and solves online tasks more efficiently. Experimental results show that IDT achieves state-of-the-art in long-horizon tasks over current in-context RL methods. In particular, the online evaluation time of our IDT is 36× times faster than baselines in the D4RL benchmark and 27× times faster in the Grid World benchmark. Copyright 2024 by the author(s)

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Simple but Effective Approach for Unsupervised Few-Shot Graph Classification 24

A Simple but Effective Approach for Unsupervised Few-Shot Gr...

引用

33rd ACM Web Conference, WWW 2024

作者： Liu, Yonghao Huang, Lan Cao, Bowen Li, Ximing Giunchiglia, Fausto Feng, Xiaoyue Guan, Renchu College of Computer Science and Technology Jilin University Changchun China Department of Information Engineering and Computer Science University of Trento Trento Italy Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education China

ISBN: (纸本)9798400701719

Graphs, as a fundamental data structure, have proven efficacy in modeling complex relationships between objects and are therefore found in wide web applications. Graph classification is an essential task in graph data analysis, which can effectively assist in extracting information and mining content from the web. Recently, few-shot graph classification, a more realistic and challenging task, has garnered great research interest. Existing few-shot graph classification models are all supervised, assuming abundant labeled data in base classes for meta-training. However, sufficient annotation is often challenging to obtain in practice due to high costs or demand for expertise. Moreover, they commonly adopt complicated meta-learning algorithms via episodic training to transfer prior knowledge from base classes. To break free from these constraints, in this paper, we propose a simple yet effective approach named SMART for unsupervised few-shot graph classification without using any labeled data. SMART employs transfer learning philosophy instead of the previously prevailing meta-learning paradigm, avoiding the need for sophisticated meta-learning algorithms. Additionally, we adopt a novel mixup strategy to augment the original graph data and leverage unsupervised pretraining on these data to obtain the expressive graph encoder. We also utilize the prompt tuning technique to alleviate the overfitting and low fine-tuning efficiency caused by the limited support samples of novel classes. Extensive experimental results demonstrate the superiority of our proposed approach, significantly surpassing even leading supervised few-shot graph classification models. Our code is available here. © 2024 ACM.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A METHOD FOR INCREMENTAL DISCOVERY OF FINANCIAL EVENT TYPES BASED ON ANOMALY DETECTION

arXiv

引用

arXiv 2023年

作者： Gu, Dianyue Li, Zixu Guan, Zhenhai Zhang, Rui Huang, Lan Key Laboratory of Symbolic Computation and Knowledge Engineering of MOE Jilin University Changchun China

Event datasets in the financial domain are often constructed based on actual application scenarios, and their event types are weakly reusable due to scenario constraints;at the same time, the massive and diverse new financial big data cannot be limited to the event types defined for specific scenarios. This limitation of a small number of event types does not meet our research needs for more complex tasks such as the prediction of major financial events and the analysis of the ripple effects of financial events. In this paper, a three-stage approach is proposed to accomplish incremental discovery of event types. For an existing annotated financial event dataset, the three-stage approach consists of: for a set of financial event data with a mixture of original and unknown event types, a semi-supervised deep clustering model with anomaly detection is first applied to classify the data into normal and abnormal events, where abnormal events are events that do not belong to known types;then normal events are tagged with appropriate event types and abnormal events are reasonably clustered. Finally, a cluster keyword extraction method is used to recommend the type names of events for the new event clusters, thus incrementally discovering new event types. The proposed method is effective in the incremental discovery of new event types on real data sets. Copyright © 2023, The Authors. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

A Method for Extracting Electronic Medical Record Entities by Fusing Multichannel Self-Attention Mechanism with Location Relationship Features 9th

A Method for Extracting Electronic Medical Record Entities b...

引用

9th International Conference of Pioneering Computer Scientists, Engineers and Educators, ICPCSEE 2023

作者： Xu, Hongyan Wang, Hong Feng, Yong Wang, Rongbing Zhang, Yonggang College of Information Liaoning University Shenyang110036 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China

ISBN: (纸本)9789819959709

With the implementation of the "Internet+" strategy, electronic medical records are generally applied in the medical field. Deep mining of electronic medical record content data is an effective means to obtain medical knowledge and analyse patients’ states, but the existing methods for extracting entities from electronic medical records have problems of redundant information, overlapping entities, and low accuracy rates. Therefore, this paper proposes an entity extraction method for electronic medical records based on the network framework of BERT-BiLSTM, which incorporates a multichannel self-attention mechanism and location relationship features. First, the text input sequence was encoded using the BERT-BiLSTM network framework, and the global semantic information of the sentence was mined more deeply using the multichannel self-attention mechanism. Then, the position relation characteristic was used to extract the local semantic message of the text, and the position relation characteristic of the word and the position embedding matrix of the whole sentence were obtained. Next, the extracted global semantic information was stitched with the positional embedding matrix of the sentence to obtain the current entity classification matrix. Finally, the proposed method was validated on the dataset of Chinese medical text entity relationship extraction and the 2010i2b2/VA relationship corpus, and the experimental results indicate that the proposed method surpasses existing methods in terms of precision, recall, F1 value and training time. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

A novel hybrid butterfly optimization algorithm for feature selection with sine cosine velocity in the high-dimensional classification data

引用

Journal of Intelligent and Fuzzy Systems 2024年第5-6期47卷 369-391页

作者： Zhang, Li Chen, Xiaobo Key Laboratory of Data Science and Intelligence Education Hainan Normal University Ministry of Education Haikou Hainan China School of Computer Engineering Jiangsu University of Technology Changzhou Jiangsu China Changzhou City Center Branch People's Bank of China Changzhou Jiangsu China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun China

Aiming at the shortcomings of the traditional butterfly optimization algorithm in solving the high-dimensional classification feature selection problem, which has low convergence and is prone to fall into local optimal solutions, a new hybrid butterfly optimization algorithm is proposed, i.e., HBOA-SCV (A novel hybrid butterfly optimization algorithm with sine cosine velocity). The algorithm is applied to solve a high-dimensional classification feature selection problem. Firstly, the algorithm's global exploration and local exploitation ability can be dynamically balanced by introducing inertia weight coefficients w based on multiple learning strategies. Secondly, using the updated speed position formula of the sine-cosine acceleration strategy, individual butterflies' autonomous search ability and convergence speed can be further improved. Finally, according to the fitness value of each butterfly individual, the moving step length and direction of the butterfly individual are automatically adjusted better to fit the actual search process of the butterfly individual, increase the search ability in the global range, and avoid the algorithm from falling into the local optimum. To verify the algorithm's effectiveness, 18 high-dimensional classification numbers are selected to carry out simulation and comparison experiments between HBOA-SCV and traditional BOA algorithm, five improved BOA algorithms and other comparative algorithms for high-dimensional classification data successively. The experimental results show that the average fitness value and classification accuracy of the HBOA-SCV algorithm are better than the comparison algorithm, thus verifying the superiority of the HBOA-SCV algorithm. © 2024 - IOS Press. All rights reserved.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

A frequency and two-hop configuration checking-driven local search algorithm for the minimum weakly connected dominating set problem

引用

Neural Computing and Applications 2024年第22期36卷 13833-13852页

作者： Li, Ruizhi He, Jintao Lin, Cuisong Liu, Ying Hu, Shuli Yin, Minghao Jilin University of Finance and Economics Changchun130117 China Northeast Normal University Changchun130117 China Business Big Data Research Center of Jilin Province Changchun130117 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China

The minimum weakly connected dominating set problem is a typical NP-hard problem with a wide range of applications. To solve this problem, we propose a frequency property and two-hop configuration checking strategy-driven local search algorithm (FCC2LS). In this algorithm, we first propose a lock-vertex-based initial solution construction procedure. This procedure guarantees that certain vertices, which must be included in the optimal solution, are added to the solution. Second, we propose a two-hop configuration checking strategy and a frequency property. The two-hop configuration checking strategy is a new variant of the original configuration checking strategy, which prohibits vertices with unchanged configuration from being added to the candidate solution. The frequency property is used to record the number of times for each vertex is added to the solution, which can increase the diversity of selected vertices. Third, we combine two scoring functions, Dscore and Nscore, with the above strategies and propose effective vertex selection methods to help the algorithm select suitable vertices to add into or remove from the candidate solutions. Finally, we evaluate the proposed algorithm FCC2LS with four state-of-the-art algorithms on four groups of benchmark instances. Experimental results show that our algorithm performs better on four classical benchmark instances. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

Enhancing Nested Named Entity Recognition in Chinese EMRs: A Collaborative Approach

Enhancing Nested Named Entity Recognition in Chinese EMRs: A...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Yue, Hongtao Feng, Xiaoyue Xu, Hanchi Chu, Haoxuan Wang, Yushi Guan, Renchu Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Changchun China First Hospital Jilin University Cardiovascular Center Changchun China

ISBN: (纸本)9798350386226

Named entity recognition (NER) in electronic medical records (EMRs) is critical for identifying medical entities, constructing medical knowledge graphs, and supporting clinical decision-making. However, the scarcity of EMR datasets and the challenges posed by the complexity of Chinese medical texts hinder progress in this area. To address these issues, we introduce CMR-NER, a nested named entity recognition model that enhances entity prediction by integrating multiple features and considering a global view of entity boundaries. Leveraging the robust generalization capabilities of the large language model, CMR-NER involves collaboration with medical experts to ensure accuracy and reduce annotation costs. Additionally, we present HF-NER, a high-quality dataset specifically curated for Chinese EMR entity recognition focusing on heart failure. This dataset, constructed through a methodology combining ChatGPT's capabilities and expert validation, is a significant contribution to the field. It facilitates a comprehensive evaluation of CMR-NER. Experimental results demonstrate that our approach achieves comparable or superior performance to existing methods, underscoring its effectiveness in this challenging domain. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

A Morphology Focused Cell Detection Model for Histopathology Images

A Morphology Focused Cell Detection Model for Histopathology...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Wang, Zhe Wei, Fangyue Guo, Shuyu Che, Xiaoting Bai, Tian Jilin University College of Computer Science and Technology Changchun China Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun China

ISBN: (纸本)9798350337488

The accurate automatic recognition of cell locations is of great significance for downstream tasks in pathology. Due to the various size and distribution of different cell types, previous cell detection methods applied fixed circles as labels to localize cell position by default, which makes less precise and more difficult to adapt various cell morphology. In this paper, we integrate adaptive areas of interests based on morphology to address the limitation in detecting cells with irregular shapes in pathological images. Moreover, a EGSI module is proposed to extract global distribution of cells in slices, which enables model to acquire more rich semantic information. We exhibit favorable F1 score of our method on four public datasets. Experimental results demonstrate that the proposed method could detect cells more accurately in those images with different cell morphologies and dense cell distribution. © 2023 IEEE.

关键词： cell detection cellular morphology digital pathology medical image analysis

来源：评论

学校读者我要写书评

暂无评论

Transformer-based multi-level attention integration network for video saliency prediction

引用

Multimedia Tools and Applications 2025年第13期84卷 11833-11854页

作者： Tan, Rui Sun, Minghui Liang, Yanhua Software College Jilin University Qianjin Street Jilin Changchun130012 China College of Computer Science and Technology Jilin University Qianjin Street Jilin Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Qianjin Street Jilin Changchun130012 China

Most existing models for video saliency prediction heavily rely on 3D convolutional operations to extract spatio-temporal features. However, it is worth noting that 3D convolution produces a local receptive field, which may struggle to capture long-range spatio-temporal dependencies effectively. To compensate for such shortage, this paper introduces a novel approach called the Transformer-based Multi-level Attention Integration Network (TMAI-Net) for video saliency prediction. TMAI-Net is designed as a two-stream encoder-decoder model, carefully integrating multi-level features of semantic information. Our model incorporates a Multi-level Interactive Attention(MLIA) module and a Transformer, both implemented based on self-attention mechanism, which are placed at different levels of the model to capture long-range spatio-temporal feature dependencies. Additionally, our model operates on input video frames and attentional patches, allowing the Transformer module to capture structural similarities between related objects in global features and attention features. This, in turn, enables the model to allocate increased attention to salient areas. The efficacy of our proposed approach is validated through extensive experiments conducted on three widely recognized benchmark datasets. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Sparse Optical Flow Method for Camera Tracking under Fisheye Camera Models 5

A Sparse Optical Flow Method for Camera Tracking under Fishe...

引用

5th International Conference on Frontiers Technology of Information and Computer, ICFTIC 2023

作者： Zhang, Zuoming Wang, Xin College of Computer Science and Technology Jilin China College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin China

ISBN: (纸本)9798350309034

In computer image processing, optical flow is a classic task used to track the motion of pixels. In the field of robotics, methods like SLAM extensively employ sparse optical flow as a substitute for time-consuming feature point matching methods, enabling rapid and stable camera tracking. However, the widespread use of fisheye cameras introduces distortion issues in practical applications. Traditional sparse optical flow struggles to accurately track pixel positions in such scenarios, affecting the precision of camera pose tracking. Therefore, we introduce a sparse optical flow method designed for fisheye camera models, which correctly utilizes prior information obtained during camera tracking to enhance the accuracy of sparse optical flow. Finally, we propose a scheme for constructing a semi-distortion lookup table to accelerate distortion operations and reduce memory requirements. We conducted extensive testing on simulated datasets with various camera motion scenarios, and the experimental results demonstrate that our method outperforms OpenCV in terms of accuracy and versatility. © 2023 IEEE.

关键词： camera tracking component distortion fisheye camera model optical flow

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：