检索结果-内蒙古大学图书馆

CSMDC: Exploring consistently context semantics for multi-view document clustering

EXPERT SYSTEMS WITH APPLICATIONS 2025年 261卷

作者： Bai, Ruina Huang, Ruizhang Xu, Le Qin, Yongbin Guizhou Univ Coll Comp Sci & Technol Text Comp & Cognit Intelligence Engn Res Ctr Natl State Key Lab Publ Big Data Guiyang 550025 Guizhou Peoples R China

Multi-view document clustering, which aims to discover clustering partitions based on multiple document views, has attracted increasing research interest. However, the potential advantages of incorporating context semantics to enhance multi-view document clustering are yet to be fully explored. To address the above limitation, we propose a deep multi-view document clustering model that explores consistent context semantics called CSMDC which consists of three modules. Specifically, a novel view-translator is designed to convert non-contextual document views into contextual views. With its help, all document views can be processed to obtain their semantic representations within the view-translator representation learning module. Then the data-based view consistency self-supervising module is developed to fine-tune the semantic representations of document views by jointly incorporating view-wise representation relevance and consistent clustering assignments. Additionally, the task-based document clustering module is employed to simultaneously improve the view semantic representations and document clustering results. To the best of our knowledge, this is the first study to explicitly apply consistent context semantics under the guidance of data-based and task- based objectives in multi-view document clustering. comprehensive experimental results demonstrated the effectiveness of the proposed model.

关键词： Multi-view document clustering View-translator Context semantics View consistency self-supervising

来源：评论

学校读者我要写书评

暂无评论

Adaptive structural enhanced representation learning for deep document clustering

引用

APPLIED intelligence 2024年第23期54卷 12315-12331页

作者： Xue, Jingjing Huang, Ruizhang Bai, Ruina Chen, Yanping Qin, Yongbin Lin, Chuan Guizhou Univ Coll Comp Sci & Technol Text Comp & Cognit Intelligence EngnRes Ctr Natl State Key Lab Publ Big Data Guiyang 550000 Guizhou Peoples R China

tructural deep document clustering methods, which leverage both structural information and inherent data properties to learn document representations using deep neural networks for clustering, have recently garnered increased research interest. However, the structural information used in these methods is usually static and remains unchanged during the clustering process. This can negatively impact the clustering results if the initial structural information is inaccurate or noisy. In this paper, we present an adaptive structural enhanced representation learning network for document clustering. This network can adjust the structural information with the help of clustering partitions and consists of two components: an adaptive structure learner, which automatically evaluates and adjusts structural information at both the document and term levels to facilitate the learning of more effective structural information, and a structural enhanced representation learning network. The latter incorporates integrates this adjusted structural information to enhance text document representations while reducing noise, thereby improving the clustering results. The iterative process between clustering results and the adaptive structural enhanced representation learning network promotes mutual optimization, progressively enhancing model performance. Extensive experiments on various text document datasets demonstrate that the proposed method outperforms several state-of-the-art *** abstractThe overall framework of adaptive structural enhanced representation learning network

关键词： Adaptive learning Document clustering Representation learning

来源：评论

学校读者我要写书评

暂无评论

GSAM: A simple and General Stereo Alignment Module for multi-view document clustering

引用

KNOWLEDGE-BASED SYSTEMS 2025年 316卷

作者： Bai, Ruina Huang, Ruizhang Chen, Yanping Qin, Yongbin Guizhou Univ Coll Comp Sci & Technol Text Comp & Cognit Intelligence Engn Res Ctr Natl Educ MinistState Key Lab Publ Big Data Guiyang 550025 Guizhou Peoples R China

Multi-view document clustering leverages diverse information from multiple perspectives to enhance clustering performance. In practice, multi-view datasets exist in a stereo space comprising features, views, and document samples. Although view alignment has become essential for maintaining representation consistency across views, current approaches face two critical limitations: (1) if semantically related features in different views are not properly associated, it may lead to a fragmented understanding of the data, and (2) if existing methods ignore sample alignment during the representation learning process, they may fail to preserve cluster structures. To address these limitations, we proposed and investigated a General Stereo Alignment Module (GSAM) with three key aspects: (1) a feature-level alignment mechanism to capture cross-view feature correlations by establishing connections between feature representations from different views;(2) view-level alignment to maintain semantic consistency across different views of identical samples, ensuring that the learned representations preserve view-specific characteristics;and (3) sample-level alignment to optimize the similarity relationships between samples during representation learning, enhancing the discriminative power for multi-view clustering. For effective feature extraction, GSAM employs specialized backbone networks (pre-trained language models for contextual views and statistical approaches for non-contextual views), followed by learnable view-specific autoencoders to enhance feature representations. Through this hierarchical alignment strategy, GSAM effectively captures the intrinsic relationships within multi-view document datasets that inherently exist in a sophisticated stereo space. Notably, GSAM is designed as a lightweight plug-and-play module that can seamlessly be integrated into various multi-view learning frameworks. The experimental results on five different types of multi-view document datasets d

关键词： Multi-view clustering General stereo alignment Feature correlations View coherence Sample relationship

来源：评论

学校读者我要写书评

暂无评论

Prior semantic-embedding representation learning for on-the-fly FG-SBIR

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年第PartA期255卷

作者： Liu, Yingge Dai, Dawei Zou, Kenan Tan, Xiufang Wu, Yiqiao Wang, Guoyin Chongqing Univ Posts & Telecommun Chongqing Key Lab Computat Intelligence Key Lab Big Data Intelligent Comp Key Lab Cyberspace Big Data Intelligent SecurMini Chongqing 400065 Peoples R China

In fine-grained sketch -based image retrieval (FG-SBIR) framework, sketch drawing is a time-consuming and skill -intensive process that greatly restricts its practical application. Our study aims to enhance the early -stage retrieval efficiency by utilizing partial sketches with a minimum number of strokes in the on -the -fly FG-SBIR framework. Nevertheless, partial sketches with few strokes usually lack global information and consist only of sparse local details. This lack of detail results in ambiguous semantic content and indistinct differences among images, which consequently impairs early -stage retrieval. To acquire an efficient representation for these sketches, we propose a multi -granularity feature representation model that utilizes prior knowledge embedding to deal with the sketch drawing process. In the first stage,we design a triplet network to learn the joint a coarse representation embedding space that is common between the complete sketch and the image. In the second stage, We enhanced the semantic representation of sketches by utilizing prior knowledge, which aids in supplementing missing fine-grained features. This was achieved by formalizing the prior knowledge and integrating it into the feature vector obtained in the initial stage, thereby acquiring the final representation of a subset of sketches. Experiments conducted on two public datasets indicate that our method outperforms the state-of-the-art baseline during the early retrieval phase. In practical applications, our approach has also achieved good results.

关键词： Sketch-based image retrieval Semantic embedding Representation learning

来源：评论

学校读者我要写书评

暂无评论

LGRL: Local-Global Representation Learning for On-the-Fly FG-SBIR

引用

IEEE TRANSACTIONS ON BIG data 2024年第4期10卷 543-555页

作者： Dai, Dawei Liu, Yingge Li, Yutang Fu, Shiyu Xia, Shuyin Wang, Guoyin Chongqing Univ Posts & Telecommun Chongqing Key Lab Computat Intelligence Key Lab Big Data Intelligent Comp Key Lab Cyberspace Big Data Intelligent SecurMini Chongqing 400065 Peoples R China

On-the-fly Fine-grained sketch-based image retrieval (On-the-fly FG-SBIR) framework aim to break the barriers that sketch drawing requires excellent skills and is time-consuming. Considering such problems, a partial sketch with fewer strokes contains only the little local information, and the drawing process may show great difference among users, resulting in poor performance at the early retrieval. In this study, we developed a local-global representation learning (LGRL) method, in which we learn the representations for both the local and global regions of the partial sketch and its target photos. Specifically, we first designed a triplet network to learn the joint embedding space shared between the local and global regions of the entire sketch and its corresponding region of the photo. Then, we divided each partial sketch in the sketch-drawing episode into several local regions;Another learnable module following the triplet network was designed to learn the representations for the local regions of the partial sketch. Finally, by combining both the local and global regions of the sketches and photos, the final distance was determined. In the experiments, our method outperformed state-of-the-art baseline methods in terms of early retrieval efficiency on two publicly sketch-retrieval datasets and the practice test.

关键词： Fine-grained sketch-based image retrieval (FG-SBIR) representation learning triplet loss Fine-grained sketch-based image retrieval (FG-SBIR) representation learning triplet loss

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Centered Dual-Process Reasoning for Math Word Problems With Large Language Models

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND data ENGINEERING 2025年第6期37卷 3457-3471页

作者： Liu, Jiayu Huang, Zhenya Liu, Qi Ma, Zhiyuan Zhai, Chengxiang Chen, Enhong Univ Sci & Technol China Sch Data Sci State Key Lab Cognit Intelligence Hefei 230000 Peoples R China Univ Sci & Technol China Sch Comp Sci & Technol State Key Lab Cognit Intelligence Hefei 230000 Peoples R China Univ Illinois Dept Comp Sci Champaign IL 61820 USA

Math word problem (MWP) serves as a critical milestone for assessing the text mining ability and knowledge mastery level of models. Recent advancements have witnessed large language models (LLMs) showcasing remarkable performance on MWP. However, current LLMs still frequently exhibit logical errors, which highlights their inability to fully grasp the knowledge required for genuine step-by-step mathematical reasoning. To this end, in this paper, we propose a novel Knowledge-guided Solver (KNOS) framework that empowers LLMs to simulate human mathematical reasoning, whose core idea is to Invoke-Verify-Inject necessary knowledge to solve MWP. We draw inspiration from the dual-process theory to construct two cooperative systems: a Knowledge System and an Inference System. Specifically, the Knowledge System employs LLMs as the knowledge base and develops a novel knowledge invoker that can elicit their relevant knowledge to support the strict step-level mathematical reasoning. In the Inference System, we propose a knowledge verifier and a knowledge injector to evaluate the knowledge rationality and further guide the step-wise symbolic deduction in an interpretable manner based on human cognitive mechanism, respectively. Moreover, to tackle the potential scarcity issue of mathematics-specific knowledge in LLMs, we consider an open-book exam scenario and propose an improved version of KNOS called EKNOS. In EKNOS, we meticulously design knowledge selectors to extract the most relevant commonsense and math formulas from external knowledge sources for each reasoning step. This knowledge is utilized to assist the knowledge invoker in better stimulating LLMs' reasoning abilities. Both KNOS and EKNOS are flexible to empower different LLMs. Our experiments with GPT3, ChatGPT, and GPT4 not only demonstrate their reasoning accuracy improvement but also show how they bring the strict step-wise interpretability of mathematical thinking.

关键词： cognition Knowledge based systems Chatbots Mathematical models Large language models Symbols Games Problem-solving Electronic mail Accuracy Knowledge reasoning math word problem large language model

来源：评论

学校读者我要写书评

暂无评论

Dual-stream Noise and Speech Information Perception based Speech Enhancement

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 261卷

作者： Li, Nan Wang, Longbiao Zhang, Qiquan Dang, Jianwu Tianjin Univ Coll Intelligence & Comp Tianjin Key Lab Cognit Comp & Applicat Tianjin Peoples R China Univ New South Wales Sydney Australia

In real-world scenarios, dynamic ambient noise often degrades speech quality, highlighting the need for advanced speech enhancement techniques. Traditional methods, which rely on static embeddings as auxiliary features, struggle to address the complexities of varying noise conditions. To overcome this, we propose a Dual- stream Noise and Speech Information Perception (DNSIP) approach that dynamically detects and processes both noise and speech through innovative information extraction and suppression mechanisms. Initially, non- speech segments predominantly contain environmental noise, while speech segments carry information about the intended speaker. To handle this dynamic nature, real-time voice activity detection (VAD) is employed to accurately differentiate between speech and noise components. Building on VAD estimates, we propose an innovative information extraction framework that selectively extracts relevant noise and speech features from the noisy input, establishing a dual-stream network for concurrent noise and speech learning. To account for the temporal and spectral variability of noise and speech, a frequency-sequence attention mechanism is integrated, enhancing the model's ability to learn contextual and spectral dependencies. Additionally, an information suppression module is introduced to minimize cross-stream interference by attenuating noise within the speech stream and suppressing speech content within the noise stream. The derived noise and speech spectrograms are then utilized to formulate a minimum mean square error log-spectral amplitude (MMSE-LSA) estimator for robust speech enhancement. Experimental evaluations on the WSJ0 and VCTK+DEMAND datasets demonstrate that our DNSIP approach surpasses existing state-of-the-art methods, underscoring its efficacy in challenging acoustic environments.

关键词： Speech enhancement Dual-stream Attention MMSE-LSA

来源：评论

学校读者我要写书评

暂无评论

Dual Enhanced Meta-Learning With Adaptive Task Scheduler for Cold-Start Recommendation

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND data ENGINEERING 2025年第4期37卷 1728-1741页

作者： He, Dongxiao Cui, Jiaqi Wang, Xiaobao Song, Guojie Huang, Yuxiao Wu, Lingfei Tianjin Univ Coll Intelligence & Comp Tianjin Key Lab Cognit Comp & Applicat Tianjin 300350 Peoples R China Peking Univ Sch Intelligence Sci & Technol State Key Lab Gen Artificial Intelligence Beijing 100871 Peoples R China George Washington Univ Data Sci Dept Washington DC 20052 USA Anytime AI Armonk NY 10504 USA

Recommendation systems typically rely on users' historical behavior to infer their preferences. However, when new entries emerge, the system cannot make accurate prediction due to the lack of historical data. This is known as the "cold-start" problem, which not only limits the exposure of new items but also impacts the first experience of new users severely. Meta-learning has emerged as a promising approach to address this issue, but existing methods have limitations in dealing with the differences in user preferences and sparse monitoring data. To overcome these limitations, Dual enhanced Meta-learning with Adaptive Task Sampling is proposed. First, we propose an embedding enhancement strategy for cold nodes. Specifically, we map the cold-start embeddings into the warm space based on the common features shared across all nodes, and then add uniform noise to create the contrastive views. This strategy injects warm co-occurrence signals into the content of cold nodes, effectively enriching the feature space of cold nodes. Second, we introduce an adaptive task scheduler to measure the effectiveness of different meta-tasks and filter out the noise from invalid tasks. We assign different sampling probabilities to the tasks based on the learning process (gradient similarity) and the learning result (loss) of the meta-tasks. Finally, we consider the above two modules as auxiliary tasks for the main meta-model. Then, joint optimization is carried out through a multi-task learning framework. Experiments in three cold-start scenarios show that our approach outperforms the most advanced baselines, including traditional methods, HIN-based methods, and meta-learning-based methods.

关键词： Metalearning Optimization Adaptation models Transfer learning Noise data models Contrastive learning Training Monitoring Collaborative filtering Recommendation system meta-learning self-supervised learning cold-start recommendation

来源：评论

学校读者我要写书评

暂无评论

A New Fuzzy Smoothing Term Model For Stereo Matching

引用

compUTER JOURNAL 2024年第2期67卷 746-761页

作者： Zhang, Hongjin Hui, Wei Bo, Wang Fudan Univ Sch Comp Sci Lab Algorithms Cognit Models Shanghai Key Lab Data Sci Shanghai 200433 Peoples R China

In this study, we construct a smoothing term structure, which is an essential part of the energy function in binocular matching. However, the existing energy models are mainly deterministic, which cannot adapt to processing low-quality images, especially when there exists a large proportion of vague areas. In order to perform better in processing these low-quality images, in this paper, we construct the smoothing term based on a fuzzy model, which includes fuzzy segmentation, the fuzzy network between the superpixels and the fuzzy relationship between the pixels. These can be compatible with the uncertainty in the image. In addition, to explain the rationality of the calculation of the degree of correlation between superpixels and further elaborate on the property of these degrees between each superpixel, we propose five corresponding theorems with proofs. After we solve the energy model combined with our proposed smoothing term, we compare our disparity results with the corresponding deterministic model and several state-of-the-art algorithms in the experiment. The results verify the effectiveness of the proposed algorithm.

关键词： stereo matching smoothing term fuzzy classification graph connection iteration

来源：评论

学校读者我要写书评

暂无评论

Language-Emphasized Cross-Lingual In-Context Learning for Multilingual LLM 13th

Language-Emphasized Cross-Lingual In-Context Learning for Mu...

引用

13th International Conference on Natural Language Processing and Chinese computing

作者： Li, Jun Wei, Xiao Wang, Xiaobao Zhuang, Ning Wang, Longbiao Dang, Jianwu Tianjin Univ Tianjin Key Lab Cognit Comp & Applicat Coll Intelligence & Comp Tianjin 300350 Peoples R China

ISBN: (纸本)9789819794362;9789819794379

With the recent rise of large language models (LLMs), in-context learning (ICL) has shown remarkable performance, eliminating the need for fine-tuning parameters and reducing the reliance on extensive labeled data. However, the intricacies of cross-lingual ICL remain underexplored. Prior studies on cross-lingual ICL overlooked the significance of language-specific nuances, neglecting the intrinsic linguistic properties of sentences and the interlingual connections between sentences in different languages. In this paper, we propose a novel cross-lingual prompt structure: Language-Emphasized cross-lingual In-context learning (LEI). LEI teaches LLMs how to adapt to language conversion by adding explicit language conversion examples in demonstrations. Specifically, LEI introduces a third language (example language) as an example of language conversion to adapt LLMs to language conversion in cross-lingual tasks. In addition, language alignment of demonstrations is achieved by adding language aligners and label aligners. Extensive experiments validate the state-of-the-art performance of LEI on 42 cross-lingual tasks.

关键词： Large Language Models In-context Learning Cross-Lingual

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：