检索结果-内蒙古大学图书馆

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Sili Huang Jifeng Hu Zhejian Yang Liwei Yang Tao Luo Hechang Chen Lichao Sun Bo Yang Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education and School of Artificial Intelligence Jilin University China School of Artificial Intelligence Jilin University China Institute of High Performance Computing Agency for Science Technology and Research Singapore Lehigh University Bethlehem Pennsylvania Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education

ISBN: (纸本)9798331314385

Recent works have shown the remarkable superiority of transformer models in reinforcement learning (RL), where the decision-making problem is formulated as sequential generation. Transformer-based agents could emerge with self-improvement in online environments by providing task contexts, such as multiple trajectories, called in-context RL. However, due to the quadratic computation complexity of attention in transformers, current in-context RL methods suffer from huge computational costs as the task horizon increases. In contrast, the Mamba model is renowned for its efficient ability to process long-term dependencies, which provides an opportunity for in-context RL to solve tasks that require long-term memory. To this end, we first implement Decision Mamba (DM) by replacing the backbone of Decision Transformer (DT). Then, we propose a Decision Mamba-Hybrid (DM-H) with the merits of transformers and Mamba in high-quality prediction and long-term memory. Specifically, DM-H first generates high-value sub-goals from long-term memory through the Mamba model. Then, we use sub-goals to prompt the transformer, establishing high-quality predictions. Experimental results demonstrate that DM-H achieves state-of-the-art in long and short-term tasks, such as D4RL, Grid World, and Tmaze benchmarks. Regarding efficiency, the online testing of DM-H in the long-term task is 28× times faster than the transformer-based baselines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Shortcut Learning in In-Context Learning: A Survey

arXiv

引用

arXiv 2024年

作者： Song, Rui Li, Yingji Shi, Lida Giunchiglia, Fausto Xu, Hao College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Jilin University China Department of Information Engineering and Computer Science University of Trento Italy

Shortcut learning refers to the phenomenon where models employ simple, non-robust decision rules in practical tasks, which hinders their generalization and robustness. With the rapid development of Large Language Models (LLMs) in recent years, an increasing number of studies have shown the impact of shortcut learning on LLMs. This paper provides a novel perspective to review relevant research on shortcut learning in In-Context Learning (ICL). It conducts a detailed exploration of the types of shortcuts in ICL tasks, their causes, available benchmarks, and strategies for mitigating shortcuts. Based on the corresponding observations, we summarize the unresolved issues in existing research and attempts to outline the future research landscape of shortcut learning. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Simple Graph Contrastive Learning Framework for Short Text Classification

arXiv

引用

arXiv 2025年

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

Short text classification has gained significant attention in the information age due to its prevalence and real-world applications. Recent advancements in graph learning combined with contrastive learning have shown promising results in addressing the challenges of semantic sparsity and limited labeled data in short text classification. However, existing models have certain limitations. They rely on explicit data augmentation techniques to generate contrastive views, resulting in semantic corruption and noise. Additionally, these models only focus on learning the intrinsic consistency between the generated views, neglecting valuable discriminative information from other potential views. To address these issues, we propose a Simple graph contrastive learning framework for Short Text Classification (SimSTC). Our approach involves performing graph learning on multiple text-related component graphs to obtain multi-view text embeddings. Subsequently, we directly apply contrastive learning on these embeddings. Notably, our method eliminates the need for data augmentation operations to generate contrastive views while still leveraging the benefits of multi-view contrastive learning. Despite its simplicity, our model achieves outstanding performance, surpassing large language models on various datasets. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Deep Feature-Based Text Clustering and Its Explanation

Deep Feature-Based Text Clustering and Its Explanation

引用

International Conference on Data engineering

作者： Renchu Guan Hao Zhang Yanchun Liang Fausto Giunchiglia Lan Huang Xiaoyue Feng Key Laboratory for Symbol Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Jilin University Changchun China DISI University of Trento Trento Italy

Text clustering is a critical step in text data analysis and has been extensively studied by the text mining community. Most existing text clustering algorithms are based on the bag-of-words model, which faces the high-dimensional and sparsity problems and ignores text structural and sequence information. Deep learning-based models such as convolutional neural networks and recurrent neural networks regard texts as sequences but lack supervised signals and explainable results. In this paper, we propose a deep feature-based text clustering (DFTC) framework that incorporates pretrained text encoders into text clustering tasks. This model, which is based on sequence representations, breaks the dependency on supervision. The experimental results show that our model outperforms classic text clustering algorithms on almost all the considered datasets. In addition, the explanation of the clustering results is significant for understanding the principles of the deep learning approach. Our proposed clustering framework includes an explanation module that can help users understand the meaning and quality of the clustering results. Our code is available at https://***/KEAML-JLU/DeepTextClustering.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Community discovery algorithm and its technical improvement based on link structure–taking web community algorithm as an example

Community discovery algorithm and its technical improvement ...

引用

International Conference on Applications and Techniques in Cyber Intelligence, ATCI 2020

作者： Gao, Rui Yang, Wenzhe Shi, Xiaohu Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Jilin University 2699 Qianjin Street Changchun130012 China

ISBN: (纸本)9783030539795

Link analysis is an important way to discover potential web communities. This paper analyzes the characteristics of the Web link structure, and studies the traditional maximum flow algorithm and the maximum flow algorithm based on HITS algorithm for edge capacity allocation. The traditional maximum flow problem, but there are still shortcomings. Based on the analysis of existing link similarity definitions, this paper proposes a new definition of link similarity and topic dissimilarity to better describe the relationship between linked pages, and to measure based on link similarity and topic dissimilarity. The similarity of the pages gives a more reasonable and efficient maximum flow-side capacity allocation scheme. The community discovery of 6 topics shows that the maximum flow algorithm proposed in this paper using the link similarity and topic dissimilarity model to allocate edge capacity can better solve the problems of existing algorithms and significantly improve the quality of the Web community. This paper proposes new methods and ideas for page similarity measurement, and provides new strategies for improving the Web community discovery algorithm based on link analysis. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021.

关键词： Computer programming

来源：评论

学校读者我要写书评

暂无评论

Research on Ethnic Pattern Generation Based on Generative Adversarial Networks

Research on Ethnic Pattern Generation Based on Generative Ad...

引用

International Workshop on Advanced computational Intelligence (IWACI)

作者： Hao Wu Wenze He Xiongfei Li Yanchun Liang Zhuhai Sub Laboratory of Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education Zhuhai College of Science and Technology Zhuhai China Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Jilin University Changchun China

In this paper, we take Mongolian ethnic patterns as the research object and conduct a technical study on ethnic pattern generation and super-resolution reconstruction based on deep learning generative adversarial networks to address the problems of low quality of ethnic pattern data collection and lack of innovation. In this paper, we use a database including 1621 Mongolian ethnic patterns, train StyleGAN2 on the pre-processed images, and generate images After that, we use ESRGAN to perform super-resolution reconstruction on the generated images to generate high-resolution patterns with Mongolian style. The model designed in this paper can generate high quality images with ethnic characteristics in the case of insufficient original data. Compared with the time-consuming and labor-intensive traditional ethnic pattern design methods, the model designed in this paper lowers the threshold of ethnic pattern innovation and contributes to the innovative design of ethnic patterns to a certain extent, which has some positive significance for the protection and inheritance of ethnic patterns.

关键词：

来源：评论

学校读者我要写书评

暂无评论

2D-3D Feature Co-Embedding Network with Sparse Annotation for 3D Medical Image Segmentation

2D-3D Feature Co-Embedding Network with Sparse Annotation fo...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhu, Mingzhu Guo, Shuyu Wang, Ziwei Jiao, Jianhang Bai, Tian Jilin University College of Computer Science and Technology Changchun China Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Changchun China Jilin University College of Software Changchun China The Second Norman Bethune Hospital Jilin University Department of Orthopedics Changchun China

ISBN: (纸本)9798350386226

Supervised methods on 3D medical image segmentation need large amounts of annotated data, but annotating is time-consuming. Also, existing 3D segmentation methods capture more global structural information but overlook local detailed features, which negatively impacts the segmentation of small tissues. In this paper, we propose a novel weakly-supervised 2D-3D Feature Co-Embedding Network (2D-3D CoENet) that includes 2D and 3D encoding layers, simultaneously extracting 2D local detailed and 3D global structural features. To reduce annotation costs, we use fewer labeled slices as ground truth and pseudo-labels are generated by 2D-3D CoENet for other slices. Additionally, multi-view learning is introduced to capture more 2D local detailed information, and a Multi-view Semantic Consistency loss (MSC loss) is proposed to constrain features from multiple perspectives. To further enhance the local detailed texture features, we propose an Edge Enhancement Module (EEM) in the 3D segmentation network to enhance the edge detail features. Our experimental results on the SKI10 dataset and OAI ZIB dataset demonstrate that our method outperforms the SOTA weakly-supervised segmentation methods. Moreover, our approach achieves results that are comparable to the fully-supervised upper bound results. © 2024 IEEE.

关键词： Medical imaging

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

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

引用

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

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-Bi LSTM, 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.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Underwater Target Detection Based on Reinforcement Learning and Ant Colony Optimization

引用

Journal of Ocean University of China 2022年第2期21卷 323-330页

作者： WANG Xinhua ZHU Yungang LI Dayu ZHANG Guang School of Computer Science Northeast Electric Power UniversityJilin 132012China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education College of Computer Science and TechnologyJilin UniversityChangchun 130012China State Key Laboratory of Applied Optics Changchun Institute of OpticsFine Mechanics and PhysicsChinese Academy of SciencesChangchun 130033China

Underwater optical imaging produces images with high resolution and abundant information and hence has outstanding advantages in short-distance underwater target ***,low-light and high-noise scenarios pose great challenges in un-derwater image and video *** improve the accuracy and anti-noise performance of underwater target image edge detection,an underwater target edge detection method based on ant colony optimization and reinforcement learning is proposed in this ***,the reinforcement learning concept is integrated into artificial ants’movements,and a variable radius sensing strategy is pro-posed to calculate the transition probability of each *** methods aim to avoid undetection and misdetection of some pixels in image ***,a double-population ant colony strategy is proposed,where the search process takes into account global search and local search *** results show that the algorithm can effectively extract the contour information of underwater targets and keep the image texture well and also has ideal anti-interference performance.

关键词： ant colony optimization reinforcement learning underwater target edge detection

来源：评论

学校读者我要写书评

暂无评论

Combining GCN and Bi-LSTM for Protein Secondary Structure Prediction

Combining GCN and Bi-LSTM for Protein Secondary Structure Pr...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Jin, Hailong Du, Wei Gu, Jiawei Zhang, Tianhao Shi, Xiaohu College of Computer Science and Technology of Jilin University Changchun China Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Changchun China

ISBN: (纸本)9781665401265

Protein secondary structure prediction is still a challenging task in bioinformatics, especially for 8-state (Q8) classification. To address this problem, we have proposed a deep learning based model by integrating graph convolutional network(GCN) and bidirectional long short-term memory (Bi-LSTM) network in this paper. In the model, GCN is utilized to synthesize the information of amino acids and their interactions, while Bi-LSTM has strong ability to capture the long-range dependencies of amino acids. For sequence representation, a new protein embedding derived by ProtTrans is used instead of the traditional amino acid one-hot encoding, together with evolutionary features of PSSM and HHM profiles. Amino acid contact potential derived from SPOTContact-Helical is used to construct amino acid graph. To verify the effectiveness of our proposed model, it is applied to several benchmark datasets, and obtained 78.05%, 76.81% 72.84%, 74.46% and 76.04% Q8 accuracy on CASP10, CASP11, CASP12, CB513 and TS115 datasets, respectively. Compared with 8 state-of-the-art competitions, our model obtained the best performance in most of datasets. © 2021 IEEE.

关键词： Amino acids

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：