检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and signal processing, ICASSP 2025

作者： Ti, Zheng Hao, Xuze Chen, Renhai College of Intelligence and Computing Tianjin University Tianjin China School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China

ISBN: (纸本)9798350368741

Continual Semantic Segmentation (CSS) aims to continuously learn new classes while mitigating catastrophic forgetting. Existing CSS methods primarily address this challenge through knowledge distillation. While they focus on maintaining stability for old classes, this emphasis often restricts plasticity in learning new ones. In this work, we propose two plug-and-play methods to better balance stability and plasticity. First, for feature map distillation, we replace pixel-level constraints with statistical information extraction within a window, improving the learning of new classes while preserving structural integrity to overcome forgetting. Second, we use relative ranks of predictions to replace exact probabilistic values to loosen the constraints in the logit distribution of old classes. Extensive experiments demonstrate that our methods outperform state-of-the-art methods when integrating into several baselines across various CSS scenarios. © 2025 IEEE.

关键词： Continual Learning Knowledge Distillation Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

An Entity Alignment Algorithm Based on Ontology Enhancement and Multi-Feature Fusion 6

An Entity Alignment Algorithm Based on Ontology Enhancement ...

引用

6th International Conference on Frontier Technologies of Information and Computer, ICFTIC 2024

作者： Song, Hao Lei, Yuxia Zi, Kangli Quan, Fuyuan Zhang, Tianhang Li, Qi School of Computer Science Qufu Normal University Shandong Rizhao China Institute of Computing Technology Chinese Academy of Sciences Key Laboratory of Intelligent Information Processing Beijing China

ISBN: (纸本)9798331541750

Entity alignment plays a crucial role in the integration of knowledge graphs. However, current knowledge graphs often suffer from inconsistent construction standards, structural heterogeneity, and imprecise semantic representation of entities, which can lead to suboptimal embedding of structural information. Moreover, most existing entity alignment methods rely heavily on structural information, which limits alignment efficiency. To address these challenges, this paper presents Onto-IMF, an ontology-enhanced entity alignment method based on multi-feature fusion. This approach aims to enhance the semantic representation of entities by incorporating ontology information, thereby reducing structural discrepancies among heterogeneous graphs and improving the embedding of structural information. The multi-feature fusion entity alignment leverages diverse semantic features, including relations, attributes, and entity names, to achieve more accurate alignment. Experimental results on various DBP15K subsets indicate that the proposed method achieves Hits@l scores of 86.6%, 93.0%, and 97.7%, respectively, representing an average improvement of 7.9% over the best-performing baseline models. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Leveraging Knowledge Distillation for Improved Event Extraction in QA Models 6

Leveraging Knowledge Distillation for Improved Event Extract...

引用

6th International Conference on Frontier Technologies of Information and Computer, ICFTIC 2024

作者： Zhou, Peiyao Hu, Zhikui Zi, Kangli Zhang, Dawei School of Computer Science Jiangsu University of Science and Technology Zhenjiang China Institute of Computing Technology Chinese Academy of Sciences Key Laboratory of Intelligent Information Processing Beijing China

ISBN: (纸本)9798331541750

Event extraction is an important task in natural language processing, and it is widely utilized in intelligence domains such as business and military for information extraction. Recently, many works have successfully transformed document-level event extraction into Question-answering (QA) tasks with remarkable results. This approach embeds event argument information within the questions, introducing prior knowledge into the process. Jin et al. highlighted the importance of high-quality QA pairs for practical QA tasks, emphasizing that constructing these pairs remains a key challenge[1]. In this study, we propose a Prompt-based question generation method to automatically generate questions containing event arguments, which converts event extraction into a QA task. We introduce an event ontology-based information retrieval module to enhance answer accuracy and select the most relevant document segments as input text. Additionally, we employ knowledge distillation to build the QA model, transferring knowledge from a large pre-trained model to a more compact and efficient one, improving the student model's performance. Experiments show that our model performs strongly in mainstream benchmarks, with 4.8 improvements on WikiEvents. © 2024 IEEE.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration 38

Speculative Decoding with CTC-based Draft Model for LLM Infe...

引用

38th Conference on Neural Information processing Systems, NeurIPS 2024

作者： Wen, Zhuofan Gui, Shangtong Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences China Key Laboratory of Al Safety Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China

Inference acceleration of large language models (LLMs) has been put forward in many application scenarios and speculative decoding has shown its advantage in addressing inference acceleration. Speculative decoding usually introduces a draft model to assist the base LLM where the draft model produces drafts and the base LLM verifies the draft for acceptance or rejection. In this framework, the final inference speed is decided by the decoding speed of the draft model and the acceptance rate of the draft provided by the draft model. Currently the widely used draft models usually generate draft tokens for the next several positions in a non-autoregressive way without considering the correlations between draft tokens. Therefore, it has a high decoding speed but an unsatisfactory acceptance rate. In this paper, we focus on how to improve the performance of the draft model and aim to accelerate inference via a high acceptance rate. To this end, we propose a CTC-based draft model which strengthens the correlations between draft tokens during the draft phase, thereby generating higher-quality draft candidate sequences. Experiment results show that compared to strong baselines, the proposed method can achieve a higher acceptance rate and hence a faster inference speed. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Gradient-Based Differential kWTA Network With Application to Competitive Coordination of Multiple Robots

引用

IEEE/CAA Journal of Automatica Sinica 2022年第8期9卷 1452-1463页

作者： Mei Liu Xiaoyan Zhang Mingsheng Shang Long Jin School of Information Science and Engineering Lanzhou UniversityLanzhou 730000 State Key Laboratory of Tibetan Intelligent Information Processing and Application Xining 810016China Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent TechnologyChinese Academy of SciencesChongqing 400714China Shenzhen Research Institute Lanzhou UniversityShenzhen 518063China

Aiming at the k-winners-take-all(kWTA)operation,this paper proposes a gradient-based differential kWTA(GDk WTA)*** obtaining the network,theorems and related proofs are provided to guarantee the exponential convergence and noise resistance of the proposed GD-kWTA ***,numerical simulations are conducted to substantiate the preferable performance of the proposed network as compared with the traditional ***,the GD-k WTA network,backed with a consensus filter,is utilized as a robust control scheme for modeling the competition behavior in the multi-robot coordination,thereby further demonstrating its effectiveness and feasibility.

关键词： Consensus filter k-winners-take-all(kWTA) multirobot coordination noise resistance

来源：评论

学校读者我要写书评

暂无评论

Evolutionary neural architecture search for transformer in knowledge tracing 23

Evolutionary neural architecture search for transformer in k...

引用

Proceedings of the 37th International Conference on Neural Information processing Systems

作者： Shangshang Yang Xiaoshan Yu Ye Tian Xueming Yan Haiping Ma Xingyi Zhang Anhui University and Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Guangdong University of Foreign Studies Anhui University and Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education and Department of Information Materials and Intelligent Sensing Laboratory of Anhui Province

Transformer has achieved excellent performance in the knowledge tracing (KT) task, but they are criticized for the manually selected input features for fusion and the defect of single global context modelling to directly capture students' forgetting behavior in KT, when the related records are distant from the current record in terms of time. To address the issues, this paper first considers adding convolution operations to the Transformer to enhance its local context modelling ability used for students' forgetting behavior, then proposes an evolutionary neural architecture search approach to automate the input feature selection and automatically determine where to apply which operation for achieving the balancing of the local/global context modelling. In the search space design, the original global path containing the attention module in Transformer is replaced with the sum of a global path and a local path that could contain different convolutions, and the selection of input features is also considered. To search the best architecture, we employ an effective evolutionary algorithm to explore the search space and also suggest a search space reduction strategy to accelerate the convergence of the algorithm. Experimental results on the two largest and most challenging education datasets demonstrate the effectiveness of the architecture found by the proposed approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Structure-constrain Source Free Domain Adaptation with Regularized Knowledge Distillation of Source Model 13

Structure-constrain Source Free Domain Adaptation with Regul...

引用

13th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2024

作者： Yang, Dan Peng, Xin Su, Cheng Tan, Dayu Chen, Chaoyang Zhong, Weimin Ministry of Education East China University of Science and Technology Key Laboratory of Smart Manufacturing in Energy Chemical Process Shanghai200237 China Ministry of Education Anhui University Key Laboratory of Intelligent Computing and Signal Processing Anhui Hefei230601 China School of Information and Electrical Engineering Hunan University of Science and Technology Xiangtan China

ISBN: (纸本)9798350361674

Transfer learning aims to leverage the knowledge of the source domain to help the learning of unlabeled target domain models. However, all conventional transfer learning methods assume that samples from source and target domains are always freely accessible. However, this assumption is rarely plausible in real-world due to data privacy. To combat this challenge, we introduce Structure-constrain Source Free Domain Adaptation with regularized Knowledge Distillation of source model (SSFDA-KD). Our method is based on the observations that a deterministic classification result can be obtained when the target data distribution aligns with the source data distribution, and a well-trained model not only yields a deterministic classification for a sample but also has clear category boundaries, which implies samples that are close together belong to the same category. From those, we first generate the source model with labeled source data, which is regarded as a well-trained model. Then, we identify target prototypes with lower self-entropy and assign the pseudo-labels to other samples according to the neighborhood structure. Finally, we refine the target model by minimizing prediction loss, constraining internal structure via triplet loss, and reducing knowledge distillation loss. Experiments of fault diagnosis based on WWTPs are conducted to validate its effectiveness. © 2024 IEEE.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

ADHD diagnosis guided by functional brain networks combined with domain knowledge

引用

Computers in Biology and Medicine 2024年 177卷 108611-108611页

作者： Cao, Chunhong Fu, Huawei Li, Gai Wang, Mengyang Gao, Xieping MOE Key Laboratory of Intelligent Computing and Information Processing Xiangtan University Xiangtan411100 China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha410081 China

Utilizing functional magnetic resonance imaging (fMRI) to model functional brain networks (FBNs) is increasingly prominent in attention-deficit/hyperactivity disorder (ADHD) research, revealing neural impact and mechanisms through the exploration of activated brain regions. However, current FBNs-based methods face two major challenges. The primary challenge stems from the limitations of existing modeling methods in accurately capturing both regional correlations and long-distance dependencies (LDDs) within the dynamic brain, thereby affecting the diagnostic accuracy of FBNs as biomarkers. Additionally, limited sample size and class imbalance also pose a challenge to the learning performance of the model. To address the issues, we propose an automated diagnostic framework, which integrates modeling, multimodal fusion, and classification into a unified process. It aims to extract representative FBNs and efficiently incorporate domain knowledge to guide ADHD classification. Our work mainly includes three-fold: 1) A multi-head attention-based region-enhancement module (MAREM) is designed to simultaneously capture regional correlations and LDDs across the entire sequence of brain activity, which facilitates the construction of representative FBNs. 2) The multimodal supplementary learning module (MSLM) is proposed to integrate domain knowledge from phenotype data with FBNs from neuroimaging data, achieving information complementarity and alleviating the problems of insufficient medical data and unbalanced sample categories. 3) An ADHD automatic diagnosis framework guided by FBNs and domain knowledge (ADF-FAD) is proposed to help doctors make more accurate decisions, which is applied to the ADHD-200 dataset to confirm its effectiveness. The results indicate that the FBNs extracted by MAREM perform well in modeling and classification. After with MSLM, the model achieves accuracy of 92.4%, 74.4%, and 80% at NYU, PU, and KKI, respectively, demonstrating its ability to effecti

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

A numerical magnitude aware multi-channel hierarchical encoding network for math word problem solving

引用

Neural computing and Applications 2025年第3期37卷 1651-1672页

作者： Xu, Junjie Chen, Yuzhong Xiao, Lingsheng Liao, Hongmiao Zhong, Jiayuan Dong, Chen College of Computer and Data Science Fuzhou University Fujian Province Fuzhou350108 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fujian Province Fuzhou350108 China

Math word problem (MWP) represents a critical research area within reading comprehension, where accurate comprehension of math problem text is crucial for generating math expressions. However, current approaches still grapple with unresolved challenges in grasping the sensitivity of math problem text and delineating distinct roles across various clause types, and enhancing numerical representation. To address these challenges, this paper proposes a Numerical Magnitude Aware Multi-Channel Hierarchical Encoding Network (NMA-MHEA) for math expression generation. Firstly, NMA-MHEA implements a multi-channel hierarchical context encoding module to learn context representations at three different channels: intra-clause channel, inter-clause channel, and context-question interaction channel. NMA-MHEA constructs hierarchical constituent-dependency graphs for different levels of sentences and employs a Hierarchical Graph Attention Neural Network (HGAT) to learn syntactic and semantic information within these graphs at the intra-clause and inter-clause channels. NMA-MHEA then refines context clauses using question information at the context-question interaction channel. Secondly, NMA-MHEA designs a number encoding module to enhance the relative magnitude information among numerical values and type information of numerical values. Experimental results on two public benchmark datasets demonstrate that NMA-MHEA outperforms other state-of-the-art models. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A method for generating Dunhuang dance instrumental images based on optimized diffusion model

A method for generating Dunhuang dance instrumental images b...

引用

2024 International Conference on Algorithms, High Performance computing, and Artificial Intelligence, AHPCAI 2024

作者： Wang, Jiaxin He, Xiangzhen Suzuki, Kenneth M. Northwest Minzu University Key Laboratory of Linguistic and Cultural Computing Ministry of Education Gansu Lanzhou730030 China Northwest Minzu University Key Laboratory of Minzu Languages and Cultures Intelligent Information Processing Gansu Lanzhou730030 China

ISBN: (纸本)9781510685840

Dunhuang culture is a treasure house of human history and culture. As an integral part of Dunhuang culture, Dunhuang dance is famous for its unique national characteristics and artistic characteristics. In the form of Dunhuang dance, instrumental music and props are used to greatly enrich the stage expression, forming a unique dance form of "holding music while dancing, dancing with instruments". However, the phenomenon of homogenization of instrumental props occurs frequently, which hinders the overall presentation effect and beauty of Dunhuang dance. The development based on the generative diffusion model provides new ideas for the design of Dunhuang dance instrumental props. First, the role played by musical instruments and props in the presentation of Dunhuang dance art was sorted out, and the Dunhuang dance instrumental props were digitally collected and processed, and a special data set was constructed. Secondly, based on the recognition of related instruments, a diffusion model instrumental prop image generation that can be used in the Chinese context is trained. Experimental results show that the instrumental props generated by this method not only conform to realistic logic but also have strong applicability. © 2024 SPIE.

关键词： Photons

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：