检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Li, Kewei Kong, Yanwen Xu, Yiping Su, Jianlin Huang, Lan Zhang, Ruochi Zhou, Fengfeng College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Jilin Changchun130012 China Moonshot AI Ltd. Beijing100086 China

Since the emergence of research on improving the length extrapolation capabilities of large models in 2021, some studies have made modifications to the scaling factor in the scaled dot-product attention mechanism as part of their proposed methods without rigorous theoretical justifications. To fill this gap, we propose two new scaled temperatures based on entropy invariance to enhance length extrapolation. First, a training-free method InfoScale is designed for dot-product attention, and preserves focus on original tokens during length extrapolation by ensuring consistent entropy. Second, we theoretically analyze the impact of scaling (CosScale) on cosine attention. Experimental data demonstrates that combining InfoScale and CosScale achieves state-of-the-art performance on the GAU-α model with a context window extended to 64 times the training length, and outperforms seven existing methods. Our analysis reveals that significantly increasing CosScale approximates the Windowed Attention, and highlights the significance of attention score dilution as a key challenge in long-range context handling. The code and data are available at https://***/HT-NEKO/InfoScale. © 2025, CC BY-NC-ND.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

Learning Semantic Textual Similarity via Topic-informed Discrete Latent Variables

Learning Semantic Textual Similarity via Topic-informed Disc...

引用

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Yu, Erxin Du, Lan Jin, Yuan Wei, Zhepei Chang, Yi School of Artificial Intelligence Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering Jilin University China International Center of Future Science Jilin University China Faculty of Information Technology Monash University Australia

Recently, discrete latent variable models have received a surge of interest in both Natural Language Processing (NLP) and Computer Vision (CV), attributed to their comparable performance to the continuous counterparts in representation learning, while being more interpretable in their predictions. In this paper, we develop a topic-informed discrete latent variable model for semantic textual similarity, which learns a shared latent space for sentence-pair representation via vector quantization. Compared with previous models limited to local semantic contexts, our model can explore richer semantic information via topic modeling. We further boost the performance of semantic similarity by injecting the quantized representation into a transformer-based language model with a well-designed semantic-driven attention mechanism. We demonstrate, through extensive experiments across various English language datasets, that our model is able to surpass several strong neural baselines in semantic textual similarity tasks. © 2022 Association for computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought

arXiv

引用

arXiv 2024年

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, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Stochastic Block Models for Complex Network Analysis: A Survey

引用

ACM Transactions on knowledge Discovery from Data 2025年第3期19卷 1-35页

作者： Liu, Xueyan Song, Wenzhuo Musial, Katarzyna Li, Yang Zhao, Xuehua Yang, Bo College of Computer Science and Technology Jilin University Changchun China School of Information Science and Technology Northeast Normal University Changchun China Complex Adaptive Systems Lab Data Science Institute University of Technology Sydney Sydney Australia Aviation University of the Air Force Changchun China School of Digital Media Shenzhen Institute of Information Technology Shenzhen China Key Laboratory of Symbolic Computation and Knowledge Engineer Jilin University Ministry of Education Changchun China

Complex networks enable to represent and characterize the interactions between entities in various complex systems which widely exist in the real world and usually generate vast amounts of data about all the elements, their behaviors and interactions over time. The studies concentrating on new network analysis approaches and methodologies are vital because of the diversity and ubiquity of complex networks. The stochastic block model (SBM), based on Bayesian theory, is a statistical network model. SBMs are essential tools for analyzing complex networks since SBMs have the advantages of interpretability, expressiveness, flexibility and generalization. Thus, designing diverse SBMs and their learning algorithms for various networks has become an intensively researched topic in network analysis and data mining. In this article, we review, in a comprehensive and in-depth manner, SBMs for different types of networks (i.e., model extensions), existing methods (including parameter estimation and model selection) for learning optimal SBMs for given networks and SBMs combined with deep learning. Finally, we provide an outlook on the future research directions of SBMs. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Complex Networks Structural Pattern Discovery Stochastic Block models Learning Methods of SBMs

来源：评论

学校读者我要写书评

暂无评论

A Semantic-Aware and Multi-Guided Network for Infrared-Visible Image Fusion

arXiv

引用

arXiv 2024年

作者： Zhang, Xiaoli Wang, Liying Zhao, Libo Li, Xiongfei Ma, Siwei The Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China The Institute of Digital Media School of Electronic Engineering and Computer Science Peking University Beijing100871 China

Multi-modality image fusion aims at fusing modality-specific (complementarity) and modality-shared (correlation) information from multiple source images. To tackle the problem of the neglect of inter-modal information, high-frequency information loss and limited attention to downstream tasks, this paper focuses on how to model correlation-driven decomposing features and reason high-level graph representation by efficiently extracting complementary features and aggregating multi-guided features. We propose a three-branch encoder-decoder architecture along with corresponding fusion layers as the fusion strategy. The transformer with Multi-Dconv Head Transposed Attention and Local-enhanced Feed Forward network is used to extract shallow features after the depthwise convolution. In the three parallel branches of the encoder, Cross Attention and Invertible Block (CAI) enables to extract local features and preserve high-frequency texture details. Base Feature Extraction Module (BFE) with residual connections can capture long-range dependencies and enhance modality-shared information. Graph Reasoning Module (GR) is introduced to reason high-level cross-modality relations and simultaneously extract low-level detail features as CAI’s modality-specific complementary information. Experiments demonstrate that our method obtains competitive results compared with state-of-the-art methods in visible/infrared image fusion and medical image fusion tasks. Moreover, we surpass other fusion methods in terms of subsequent tasks, averagely scoring 8.27% mAP@0.5 higher in object detection and 5.85% mIoU higher in semantic segmentation. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Fine-Grained Classification of Histological Images

Few-Shot Fine-Grained Classification of Histological Images

引用

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Yingdong Jiang Jing Huang Zihe Jin Leqi Shen Ziyi Zhang Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education College of Software Jilin University Jilin University ChangChun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University Jilin University ChangChun China College of Computer Science and Technology Jilin University ChangChun China

Histological image classification plays a crucial role in cancer diagnosis. However, the acquisition of well-labeled histological images is prohibitively expensive, and obtaining rare abnormal samples is challenging. Therefore, applying few-shot learning methods to histological image classification tasks holds significant clinical value. Nevertheless, existing research predom-inantly relies on coarse-grained image classification approaches based on natural image datasets, which struggle to address the fine-grained challenges encountered in histological image classification, such as intra-class diversity and inter-class similarity. To tackle this issue, this study proposes a novel few-shot fine-grained classification method for histological images, named “Category-Aware Feature Map Reconstruction Network.” This method employs channel weights to localize the differences between inter-class and intra-class regions, composed of intra-class channel weights and inter-class channel weights, collectively referred to as category-aware weights. Specifically, intra-class channel weights indicate the matching degree of salient regions within the support set of a particular class, while inter-class channel weights represent the degree of containing distinct information between classes. The category-aware weights are utilized to transform the support feature maps and query feature maps, generating feature maps that capture differentiating details between categories. Finally, the distance between the transformed query feature map and support feature map is calculated to achieve probabilistic predictions for the categories. On a histological few-shot dataset, this method achieves an accuracy of 90.23% using ResNet-12 as the feature extractor, surpassing the baseline model by 5.24% and outperforming other few-shot methods by at least 10% in the 5-way 10-shot experimental setting. The proposed method exhibits exceptional performance on histological image few-shot datasets, playing a

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving Local Search for Pseudo Boolean Optimization by Fragile Scoring Function and Deep Optimization 29

Improving Local Search for Pseudo Boolean Optimization by Fr...

引用

29th International Conference on Principles and Practice of Constraint Programming, CP 2023

作者： Zhou, Wenbo Zhao, Yujiao Wang, Yiyuan Cai, Shaowei Wang, Shimao Wang, Xinyu Yin, Minghao School of Information Science and Technology Northeast Normal University Changchun China Key Laboratory of Applied Statistics of MOE Northeast Normal University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of MOE Jilin University Changchun China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783959773003

Pseudo-Boolean optimization (PBO) is usually used to model combinatorial optimization problems, especially for some real-world applications. Despite its significant importance in both theory and applications, there are few works on using local search to solve PBO. This paper develops a novel local search framework for PBO, which has three main ideas. First, we design a two-level selection strategy to evaluate all candidate variables. Second, we propose a novel deep optimization strategy to disturb some search spaces. Third, a sampling flipping method is applied to help the algorithm jump out of local optimum. Experimental results show that the proposed algorithms outperform three state-of-the-art PBO algorithms on most instances. © Wenbo Zhou, Yujiao Zhao, Yiyuan Wang, Shaowei Cai, Shimao Wang, Xinyu Wang, and Minghao Yin.

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

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

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

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

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.

关键词： Costs Annotations Large language models Collaboration Named entity recognition Medical services knowledge graphs Predictive models Chatbots Cardiovascular diseases

来源：评论

学校读者我要写书评

暂无评论

Affine Invariant Feature Based on Local Color

引用

Chinese Journal of Electronics 2023年第3期22卷 511-516页

作者： LIU Pingping ZHOU Qiuzhan ZHAO Hongwci School of Computer Science and Technology Jilin University Changchun China Ministry of Education Key Laboratory of Symbolic Computation and Knowledge Engineering Jilin University Changchun China School of Communication Engineering Jilin University Changchun China

Image localization using local features has attracted a lot of attention in recent mobile robots research. A novel, fast local invariant feature in affine transformation is proposed in this article, called AIFLC (Affine invariant feature based on local color). We adopt affine moment invariants to build affine invariant descriptors. Moreover, we use color gradient based center moment instead of original pixel values in order to enhance discriminative power and robustness of descriptor in photometric transformations. Simulation results show that the run time of AIFLC using optimal selection parameters is about 1/3 of classical SIFT algorithm. Using the standard evaluation images and the ones taken by mobile robots, we experimentally demonstrate that the AIFLC outperforms the state-of-art approaches such as SIFT and SURF in terms of image scaling, rotation, viewpoint changing, and blur transformations.

关键词： Location awareness Image color analysis Navigation Simulation Lighting Real-time systems Robustness

来源：评论

学校读者我要写书评

暂无评论

LLM-Powered User Simulator for Recommender System

arXiv

引用

arXiv 2024年

作者： Zhang, Zijian Liu, Shuchang Liu, Ziru Zhong, Rui Cai, Qingpeng Zhao, Xiangyu Zhang, Chunxu Liu, Qidong Jiang, Peng Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University China Kuaishou Technology China City University of Hong Kong Hong Kong Xi’an Jiaotong University China

User simulators can rapidly generate a large volume of timely user behavior data, providing a testing platform for reinforcement learning-based recommender systems, thus accelerating their iteration and optimization. However, prevalent user simulators generally suffer from significant limitations, including the opacity of user preference modeling and the incapability of evaluating simulation accuracy. In this paper, we introduce an LLM-powered user simulator to simulate user engagement with items in an explicit manner, thereby enhancing the efficiency and effectiveness of reinforcement learning-based recommender systems training. Specifically, we identify the explicit logic of user preferences, leverage LLMs to analyze item characteristics and distill user sentiments, and design a logical model to imitate real human engagement. By integrating a statistical model, we further enhance the reliability of the simulation, proposing an ensemble model that synergizes logical and statistical insights for user interaction simulations. Capitalizing on the extensive knowledge and semantic generation capabilities of LLMs, our user simulator faithfully emulates user behaviors and preferences, yielding high-fidelity training data that enrich the training of recommendation algorithms. We establish quantifying and qualifying experiments on five datasets to validate the simulator’s effectiveness and stability across various recommendation scenarios. Copyright © 2024, 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

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：