检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Gao, Weibo Liu, Qi Wang, Hao Yue, Linan Bi, Haoyang Gu, Yin Yao, Fangzhou Zhang, Zheng Li, Xin He, Yuanjing University of Science and Technology of China China Anhui Province Key Laboratory of Big Data Analysis and Application State Key Laboratory of Cognitive Intelligence China Artificial Intelligence Research Institute iFLYTEK Co. Ltd China The Open University of China China

Cognitive diagnosis seeks to estimate the cognitive states of students by exploring their logged practice quiz data. It plays a pivotal role in personalized learning guidance within intelligent education systems. In this paper, we focus on an important, practical, yet often underexplored task: domain-level zero-shot cognitive diagnosis (DZCD), which arises due to the absence of student practice logs in newly launched domains. Recent cross-domain diagnostic models have been demonstrated to be a promising strategy for DZCD. These methods primarily focus on how to transfer student states across domains. However, they might inadvertently incorporate non-transferable information into student representations, thereby limiting the efficacy of knowledge transfer. To tackle this, we propose Zero-1-to-3, a domain-level zero-shot cognitive diagnosis framework via one batch of early-bird students towards three diagnostic objectives. Our approach initiates with pre-training a diagnosis model with dual regularizers, which decouples student states into domain-shared and domain-specific parts. The shared cognitive signals can be transferred to the target domain, enriching the cognitive priors for the new domain, which ensures the cognitive state propagation objective. Subsequently, we devise a strategy to generate simulated practice logs for cold-start students through analyzing the behavioral patterns from early-bird students, fulfilling the domain-adaption goal. Consequently, we refine the cognitive states of cold-start students as diagnostic outcomes via virtual data, aligning with the diagnosis-oriented goal. Finally, extensive experiments on six real-world datasets highlight the efficacy of our model for DZCD and its practical application in question recommendation. The code is publicly available at https://***/bigdataustc/Zero-1-to-3. Copyright © 2023, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Generative Pre-trained Speech Language Model with Efficient Hierarchical Transformer

arXiv

引用

arXiv 2024年

作者： Zhu, Yongxin Su, Dan He, Liqiang Xu, Linli Yu, Dong School of Data Science University of Science and Technology of China China School of Computer Science and Technology University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence China Tencent AI Lab China

While recent advancements in speech language models have achieved significant progress, they face remarkable challenges in modeling the long acoustic sequences of neural audio codecs. In this paper, we introduce Generative Pre-trained Speech Transformer (GPST), a hierarchical transformer designed for efficient speech language modeling. GPST quantizes audio waveforms into two distinct types of discrete speech representations and integrates them within a hierarchical transformer architecture, allowing for a unified one-stage generation process and enhancing Hi-Res audio generation capabilities. By training on large corpora of speeches in an end-to-end unsupervised manner, GPST can generate syntactically consistent speech with diverse speaker identities. Given a brief 3-second prompt, GPST can produce natural and coherent personalized speech, demonstrating in-context learning abilities. Moreover, our approach can be easily extended to spoken cross-lingual speech generation by incorporating multi-lingual semantic tokens and universal acoustic tokens. Experimental results indicate that GPST significantly outperforms the existing speech language models in terms of word error rate, speech quality, and speaker similarity. The code is available at https://***/youngsheen/GPST. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Morphological Guided Causal Constraint Network for Medical Image Multi-Object Segmentation

Morphological Guided Causal Constraint Network for Medical I...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Gao, Yifan Li, Jun Chang, Xinyue Zhang, Yulong Chen, Riqing Yang, Changcai Wei, Yi Dong, Heng Wei, Lifang Fujian Agriculture and Forestry University College of Computer and Information Science Fujian China Nanjing University of Information Science and Technology Institute for Ai in Medicine School of Artificial Intelligence Nanjing China Fujian Medical University College of Clinical Medicine for Obstetrics & Gynecology and Pediatrics Fujian China Fujian Agriculture and Forestry University Digital Fujian Research Institute of Big Data for Agriculture and Forestry Fujian China Wuyi University School of Mathematics and Computer Science Fujian Key Laboratory of Big Data Application and Intellectualization for Tea Industry Fujian China

ISBN: (纸本)9798350337488

Multi-objective segmentation (MOS) in medical images is to simultaneously extract multiple regions of interest in the medical images. Due to the unbalanced distribution of samples and the similarity and significant differences between features in medical images, current methods still struggle to achieve satisfactory results. In this context, we propose a novel Morphological Guided Causal Constrain segmentation network (MCCSeg) for medical image multi-object segmentation. We introduced a Causal Constrain Module (CCM) for feature decorrelation by sample reweighting. The morphological guidance module (MG) is designed to extract the boundary features as the prior shape information for enhancing feature representation. Our experiments demonstrate that MCCSeg outperforms other state-of-the-art methods, obtaining up 3.76% and 5.41% improvements in DICE and HD95 scores on Synapse dataset, respectively. © 2023 IEEE.

关键词： causal learning deep learning Medical image morphological guidance multi-object segmentation

来源：评论

学校读者我要写书评

暂无评论

FormerTime: Hierarchical Multi-Scale Representations for Multivariate Time Series Classification

arXiv

引用

arXiv 2023年

作者： Cheng, Mingyue Liu, Qi Liu, Zhiding Li, Zhi Luo, Yucong Chen, Enhong Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China Shenzhen International Graduate School Tsinghua University Shenzhen China

Deep learning-based algorithms, e.g., convolutional networks, have significantly facilitated multivariate time series classification (MTSC) task. Nevertheless, they suffer from the limitation in modeling long-range dependence due to the nature of convolution operations. Recent advancements have shown the potential of transformers to capture long-range dependence. However, it would incur severe issues, such as fixed scale representations, temporal-invariant and quadratic time complexity, with transformers directly applicable to the MTSC task because of the distinct properties of time series data. To tackle these issues, we propose FormerTime, an hierarchical representation model for improving the classification capacity for the MTSC task. In the proposed FormerTime, we employ a hierarchical network architecture to perform multi-scale feature maps. Besides, a novel transformer encoder is further designed, in which an efficient temporal reduction attention layer and a well-informed contextual positional encoding generating strategy are developed. To sum up, FormerTime exhibits three aspects of merits: (1) learning hierarchical multi-scale representations from time series data, (2) inheriting the strength of both transformers and convolutional networks, and (3) tacking the efficiency challenges incurred by the self-attention mechanism. Extensive experiments performed on 10 publicly available datasets from UEA archive verify the superiorities of the FormerTime compared to previous competitive baselines. Copyright © 2023, The Authors. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Semantic-Preserving Abstractive Text Summarization with Siamese Generative Adversarial Net

Semantic-Preserving Abstractive Text Summarization with Siam...

引用

2022 Findings of the Association for Computational Linguistics: NAACL 2022

作者： Sheng, Xin Xu, Linli Xu, Yinlong Jiang, Deqiang Ren, Bo School of Computer Science and Technology University of Science and Technology of China. China Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China China IFLYTEK Co. Ltd. China Tencent Youtu Lab China

ISBN: (纸本)9781955917766

We propose a novel siamese generative adversarial net for abstractive text summarization (SSPGAN), which can preserve the main semantics of the source text. Different from previous generative adversarial net based methods, SSPGAN is equipped with a siamese semanticpreserving discriminator, which can not only be trained to discriminate the machine-generated summaries from the human-summarized ones, but also ensure the semantic consistency between the source text and target summary. As a consequence of the min-max game between the generator and the siamese semantic-preserving discriminator, the generator can generate a summary that conveys the key content of the source text more accurately. Extensive experiments on several text summarization benchmarks in different languages demonstrate the effectiveness of the proposed method. © Findings of the Association for Computational Linguistics: NAACL 2022 - Findings.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

GL-BKGNN: Graphlet-based Bi-Kernel Interpretable Graph Neural Networks

引用

Information Fusion 2025年 123卷

作者： Xu, Lixiang Jiang, Kang Niu, Xin Chen, Enhong Luo, Bin Yu, Philip S. School of Artificial Intelligence Hefei Institute of Technology Hefei China School of Artificial Intelligence and Big Data Hefei University Hefei China Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China Hefei China Department of Computer Science University of Illinois at Chicago ChicagoIL United States

While graph neural networks (GNNs) have successfully applied generalized convolution operations to the graph domain, providing a direct method to explain the dependency between the output and the presence of certain features and structural patterns in the input graph remains challenging. Inspired by image filters in standard convolutional neural networks (CNN), we propose a neural framework that connects bi-kernel with GNNs, incorporating predefined rules and focusing on the interpretability of graph filters during training. We address graph kernels based on their differentiability, using backpropagation of differentiable graph kernels for end-to-end training to generate gradient information for model optimization. Simultaneously, we leverage the stronger stability of non-differentiable graph kernels to capture local critical subgraphs, achieving deep fusion of structural features for node updates. Extensive experiments demonstrate that our model achieves competitive performance on graph classification datasets while providing additional benefits in interpretability. © 2025

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Adaptive normalization for non-stationary time series forecasting: a temporal slice perspective 23

Adaptive normalization for non-stationary time series foreca...

引用

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

作者： Zhiding Liu Mingyue Cheng Zhi Li Zhenya Huang Qi Liu Yanhu Xie Enhong Chen Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China and State Key Laboratory of Cognitive Intelligence Shenzhen International Graduate School Tsinghua University The First Affiliated Hospital of University of Science and Technology of China

Deep learning models have progressively advanced time series forecasting due to their powerful capacity in capturing sequence dependence. Nevertheless, it is still challenging to make accurate predictions due to the existence of non-stationarity in real-world data, denoting the data distribution rapidly changes over time. To mitigate such a dilemma, several efforts have been conducted by reducing the non-stationarity with normalization operation. However, these methods typically overlook the distribution discrepancy between the input series and the horizon series, and assume that all time points within the same instance share the same statistical properties, which is too ideal and may lead to suboptimal relative improvements. To this end, we propose a novel slice-level adaptive normalization, referred to SAN, which is a novel scheme for empowering time series forecasting with more flexible normalization and denormalization. SAN includes two crucial designs. First, SAN tries to eliminate the non-stationarity of time series in units of a local temporal slice (i.e., sub-series) rather than a global instance. Second, SAN employs a slight network module to independently model the evolving trends of statistical properties of raw time series. Consequently, SAN could serve as a general model-agnostic plugin and better alleviate the impact of the non-stationary nature of time series data. We instantiate the proposed SAN on four widely used forecasting models and test their prediction results on benchmark datasets to evaluate its effectiveness. Also, we report some insightful findings to deeply analyze and understand our proposed SAN. We make our codes publicly available https://***/icantnamemyself/SAN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AdaptSSR: Pre-training User Model with Augmentation-Adaptive Self-Supervised Ranking

arXiv

引用

arXiv 2023年

作者： Yu, Yang Liu, Qi Zhang, Kai Zhang, Yuren Song, Chao Hou, Min Yuan, Yuqing Ye, Zhihao Zhang, Zaixi Yu, Sanshi Lei Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence China OPPO Research Institute China Hefei University of Technology China

User modeling, which aims to capture users' characteristics or interests, heavily relies on task-specific labeled data and suffers from the data sparsity issue. Several recent studies tackled this problem by pre-training the user model on massive user behavior sequences with a contrastive learning task. Generally, these methods assume different views of the same behavior sequence constructed via data augmentation are semantically consistent, i.e., reflecting similar characteristics or interests of the user, and thus maximizing their agreement in the feature space. However, due to the diverse interests and heavy noise in user behaviors, existing augmentation methods tend to lose certain characteristics of the user or introduce noisy behaviors. Thus, forcing the user model to directly maximize the similarity between the augmented views may result in a negative transfer. To this end, we propose to replace the contrastive learning task with a new pretext task: Augmentation-Adaptive Self-Supervised Ranking (AdaptSSR), which alleviates the requirement of semantic consistency between the augmented views while pre-training a discriminative user model. Specifically, we adopt a multiple pairwise ranking loss which trains the user model to capture the similarity orders between the implicitly augmented view, the explicitly augmented view, and views from other users. We further employ an in-batch hard negative sampling strategy to facilitate model training. Moreover, considering the distinct impacts of data augmentation on different behavior sequences, we design an augmentation-adaptive fusion mechanism to automatically adjust the similarity order constraint applied to each sample based on the estimated similarity between the augmented views. Extensive experiments on both public and industrial datasets with six downstream tasks verify the effectiveness of AdaptSSR. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Reversible data Hiding Using Convolutional Neural Network and Digital Signal Processing Techniques

Reversible Data Hiding Using Convolutional Neural Network an...

引用

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Peng Qingmei Li Shaozi Lin Yaojin Yu Xiehua Key Laboratory of Big Data and Artificial Intelligence University of Fujian Province MinNan Science and Technology University Quanzhou China School of Informatics Xiamen University Xiamen China School of Computer Science Lab of Data Science and Intelligence Application Minnan Normal University Zhangzhou China

Reversible data hiding is a data hiding process in which data is encrypted into an image as a means of authentication, and hidden data is used to hide the original image, and RDH is often used in areas where data authenticity and data preservation are important, such as legal/criminal investigations, medical images. In this study, this paper designed a novel reversible data hiding system that utilizes the Steghide algorithm to encrypt images and hide data, as well as an artificial neural network to recover embedded text and structure. Based on the analysis of the test results, it was concluded that the RDH scheme proposed in this article has the same or higher system accuracy and reliability as the existing RDH scheme. To further refine the system results in future studies, this paper proposes to increase the number of training iterations and the number of images in the training dataset to further improve the accuracy and reliability of the development.

关键词： Training System testing Signal processing algorithms Digital signal processing Reliability Cryptography Time factors

来源：评论

学校读者我要写书评

暂无评论

Event-triggered H∞ Consensus of Leader-follower Multi-agent Systems 43

Event-triggered H∞ Consensus of Leader-follower Multi-agent...

引用

43rd Chinese Control Conference, CCC 2024

作者： Gong, Cheng Ai, Chenguang Zuo, Xuemin Ma, Zhuang Dai, W. Hebei Jianzhi Casting Group Ltd Pangzhuangzi Yutian County Tangshan064100 China College Tangshan University Key Lab of Intelligent Data Information Processing and Control of Hebei Province Key Lab of Intelligent Motion Control System of Tangshan City Intelligence and Information Engineering Tangshan063000 China North China University of Science and Technology College of Electrical Engineering Tangshan063210 China Kernel University FullertonCA92832 United States

ISBN: (纸本)9789887581581

This paper discusses the H∞ consensus problem of leader-follower multi-agent systems. The controller for each agent is crafted to utilize comprehensive information from all connected agents, while an innovative event-triggered strategy is incorporated to minimize communication costs. Based on the Lyapunov function theory, an H∞ controller is proposed that can ensure both system stability and a prescribed disturbance attenuation level γ. Finally, a numerical example validated the effectiveness of the proposed method. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Multi agent systems

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：