检索结果-内蒙古大学图书馆

4th Southern African Conference for Artificial Intelligence Research, SACAIR 2023

作者： du Toit, Jaco Dunaiski, Marcel Department of Mathematical Science Computer Science Division Stellenbosch University Stellenbosch South Africa School for Data Science and Computational Thinking Stellenbosch University Stellenbosch South Africa

ISBN: (纸本)9783031490019

Hierarchical text classification (HTC) is a natural language processing task with the objective of categorising text documents into a set of classes from a structured class hierarchy. Recent HTC approaches combine encodings of the class hierarchy with the language understanding capabilities of pre-trained language models (PLMs) to improve classification performance. Furthermore, label-wise attention mechanisms have been shown to improve performance in HTC tasks by placing larger weight on more important parts of the document for each class individually to obtain label-specific representations of the document. However, using label-wise attention mechanisms to fine-tune PLMs for downstream HTC tasks has not been comprehensively investigated in previous work. In this paper, we evaluate the performance of a HTC approach which adds label-wise attention mechanisms, along with a label-wise classification layer, to a PLM which is subsequently fine-tuned on the downstream HTC dataset. We evaluate several existing label-wise attention mechanisms and propose an adaptation to one of the approaches which separates the attention mechanisms for the different levels of the hierarchy. Our proposed approach allows the prediction task at a certain level to leverage the information gained from the predictions performed at all ancestor levels. We compare the different label-wise attention mechanisms on three HTC benchmark datasets and show that our proposed approach generally outperforms the other label-wise attention mechanisms. Furthermore, we show that without using the complex techniques proposed in recent HTC approaches, our relatively simple approach outperforms state-of-the-art approaches on two of the three benchmark datasets. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

LEARNING ADVERSARIAL LINEAR MIXTURE MARKOV DECISION PROCESSES WITH BANDIT FEEDBACK AND UNKNOWN TRANSITION 11

LEARNING ADVERSARIAL LINEAR MIXTURE MARKOV DECISION PROCESSE...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Zhao, Canzhe Yang, Ruofeng Wang, Baoxiang Li, Shuai John Hopcroft Center for Computer Science Shanghai Jiao Tong University China School of Data Science The Chinese University of Hong Kong Shenzhen China

We study reinforcement learning (RL) with linear function approximation, unknown transition, and adversarial losses in the bandit feedback setting. Specifically, the unknown transition probability function is a linear mixture model (Ayoub et al., 2020;Zhou et al., 2021;He et al., 2022) with a given feature mapping, and the learner only observes the losses of the experienced state-action pairs instead of the whole loss function. We propose an efficient algorithm LSUOB-REPS which achieves Oe(dS2 √K + √HSAK) regret guarantee with high probability, where d is the ambient dimension of the feature mapping, S is the size of the state space, A is the size of the action space, H is the episode length and K is the number of episodes. Furthermore, we also prove a lower bound of order Ω(dH √K+ √HSAK) for this setting. To the best of our knowledge, we make the first step to establish a provably efficient algorithm with a sublinear regret guarantee in this challenging setting and solve the open problem of He et al. (2022). © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledge 38

FreqBlender: Enhancing DeepFake Detection by Blending Freque...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Li, Hanzhe Zhou, Jiaran Li, Yuezun Wu, Baoyuan Li, Bin Dong, Junyu School of Computer Science and Technology Ocean University of China China School of Data Science The Chinese University of Hong Kong Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China

Generating synthetic fake faces, known as pseudo-fake faces, is an effective way to improve the generalization of DeepFake detection. Existing methods typically generate these faces by blending real or fake faces in spatial domain. While these methods have shown promise, they overlook the simulation of frequency distribution in pseudo-fake faces, limiting the learning of generic forgery traces in-depth. To address this, this paper introduces FreqBlender, a new method that can generate pseudo-fake faces by blending frequency knowledge. Concretely, we investigate the major frequency components and propose a Frequency Parsing Network to adaptively partition frequency components related to forgery traces. Then we blend this frequency knowledge from fake faces into real faces to generate pseudo-fake faces. Since there is no ground truth for frequency components, we describe a dedicated training strategy by leveraging the inner correlations among different frequency knowledge to instruct the learning process. Experimental results demonstrate the effectiveness of our method in enhancing DeepFake detection, making it a potential plug-and-play strategy for other methods. © 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

The DKU Post-Challenge Audio-Visual Wake Word Spotting System for the 2021 MISP Challenge: Deep Analysis 48

The DKU Post-Challenge Audio-Visual Wake Word Spotting Syste...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Wang, Haoxu Cheng, Ming Fu, Qiang Li, Ming Wuhan University School of Computer Science Wuhan China Duke Kunshan University Data Science Research Center Kunshan China Alibaba Group China

ISBN: (纸本)9781728163277

This paper further explores our previous wake word spotting system ranked 2-nd in Track 1 of the MISP Challenge 2021. First, we investigate a robust unimodal approach based on 3D and 2D convolution and adopt the simple attention module (SimAM) for our system to improve performance. Second, we explore different combinations of data augmentation methods for better performance. Finally, we study the fusion strategies, including score-level, cascaded and neural fusion. Our proposed multimodal system leverages multimodal features and uses the complementary visual information to mitigate the performance degradation of audio-only systems in complex acoustic scenarios. Our system obtains a false reject rate of 2.15% and a false alarm rate of 3.44% in the evaluation set of the competition database, which achieves the new state-of-the-art performance by 21% relative improvement compared to previous systems. Related resource can be found at: https://***/Mashiro009/DKU-WWS-MISP. © 2023 IEEE.

关键词： audio-visual wake-up word spotting complex acoustic scenarios multimodal system simple attention module

来源：评论

学校读者我要写书评

暂无评论

Futures Quantitative Investment With Heterogeneous Continual Graph Neural Network 24

Futures Quantitative Investment With Heterogeneous Continual...

引用

24th IEEE International Conference on data Mining, ICDM 2024

作者： Tan, Zhizhong Hu, Min Liu, Bin Yin, Guosheng School of Computer Science and Engineering Macau University of Science and Technolog China School of Finance Southwestern University of Finance and Economics China Center of Statistical Research School of Statistics Southwestern University of Finance and Economics China School of Computing and Data Science The University of Hong Kong Hong Kong Hong Kong

ISBN: (纸本)9798331506681

It is challenging to predict futures prices with traditional econometric models as it necessitates a comprehensive consideration of both historical observations and correlations among various futures. Spatial-temporal graph neural networks (STGNNs) offer a promising approach for modeling such complex spatio-temporal data. Nevertheless, the direct application of STGNNs to high-frequency futures data remains a challenge, as traders must account for both short- and long-term characteristics when making decisions. To capture these distinct timeframes, we leverage additional label information by devising four heterogeneous tasks: price regression, price gap regression, price moving average regression, and change-point detection. To make full use of these labels, we train the model in a continual manner. Traditional continual GNNs define the gradient of losses as parameter importance to overcome the catastrophic forgetting (CF) issue, while this is unsuitable for our heterogeneous tasks with losses in distinct spaces. Therefore, we propose to calculate the parameter importance with mutual information between the original observations and the extracted features. The empirical results based on 49 varieties of commodity futures demonstrate that our model achieves superior performance compared to the leading approaches, highlighting the effectiveness of our approach in modeling the intricate dynamics of the futures market. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Impact of Cloud Computing in Digital Healthcare 5

Impact of Cloud Computing in Digital Healthcare

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Thakur, Shreya Sharma, Simran Sharma, Arvind K. Kaur, Rajinder Anju Shoolini University Yogananda School of AI Computers and Data Science Himachal Pradesh Solan India Trinity College Department of Computer Sciences Punjab Jalandhar India

ISBN: (纸本)9798350383522

The continuous and sustainable development in healthcare is taking place from decades and with prompt technological advancement in engineering nowadays the healthcare can't be imagined without the advent tools like Cloud Computing, Internet of Medical Things etc., for quality medical practices, electronic medical records management, patient control on private health information, tracking/tracing of pharmaceutical shipments etc. The eminent cloud-computing not only spreading its feet but also exploring new dimensions in healthcare to make the digital-health possible with its remarkable fundamental benefits in quality healthcare application development. The paper is focused especially on cloud-computing, its applications and services more specifically in healthcare towards best medical practices. © 2024 IEEE.

关键词： Cloud Computing Digital Health Electronic Health Records Healthcare Privacy Telemedicine Wearable Device

来源：评论

学校读者我要写书评

暂无评论

Improving Raft Performance with Bulk Transfers 11

Improving Raft Performance with Bulk Transfers

引用

11th International Symposium on Computing and Networking Workshops, CANDARW 2023

作者： Yamashita, Aoi Tanaka, Masahiro Bessho, Yutaro Fujiwara, Yasuhiro Kawashima, Hideyuki Graduate School of Keio University Japan Ntt Computer and Data Science Laboratories Japan Ntt Communication Science Laboratories Japan Keio University Japan

ISBN: (纸本)9798350306941

Raft is known as a replicating state machine that tolerates crash faults, and its use enables various distributed systems, including distributed transaction processing systems. The original Raft protocol creates an intra-cluster consensus by having the leader generate a log of each incoming client request and replicate it to its followers. When requests arrive frequently, the number of replications increases, increasing the number of communications and possibly leading to performance degradation. To solve this problem, we propose a bulk-transfer protocol that replicates multiple requests at once. We implemented the Raft system to verify the effect of the proposed method. We measured the performance of the implemented system when multiple requests were transferred in bulk and observed an increase in throughput with an increase in the amount of data replicated at a time. The highest throughput of 214 MB/sec was achieved when replicating 12.5 MB at a time. This is 12,066 times higher than the performance when replicating one request (18 B) at a time. Besides, the size of the log is reduced to 5/9 of the conventional method. © 2023 IEEE.

关键词： Distributed computer systems

来源：评论

学校读者我要写书评

暂无评论

A Two-Stage Hybrid GA-Cellular Encoding Approach to Neural Architecture Search

A Two-Stage Hybrid GA-Cellular Encoding Approach to Neural A...

引用

2023 IEEE Symposium Series on Computational Intelligence, SSCI 2023

作者： Londt, Trevor Gao, Xiaoying Andreae, Peter Mei, Yi Centre for Data Science and Artificial Intelligence School of Engineering and Computer Science Victoria University of Wellington PO Box 600 Wellington6140 New Zealand

ISBN: (纸本)9781665430654

Neural Architecture Search (NAS) aims to automate the creation of Artificial Neural Networks, including Convolutional Neural Networks (CNN), lessening the reliance on labour-intensive manual design by human experts. A CNN architecture can be decomposed into a micro- and macro-architecture, each influenced by distinct design and optimisation strategies to con-tribute to the overall construction and performance of the CNN. Cellular Encoding (CE), an evolutionary computation technique, has been successfully used to represent diverse network topologies of varying complexities. Recently, CE has been applied to evolve CNN architectures, showing promising results. However, current CE-based NAS approaches focus on evolving either the micro-or macro-architectures without considering the evolution of both in the same algorithm. Evolving the micro- and macro-architecture together can increase the performance of evolved CNN architectures. This research introduces a novel two-stage hybrid approach, combining Genetic Algorithms (GA) and CE to evolve both the micro- and macro-architectures to synthesise CNNs for classification tasks. Candidate macro-architectures are evolved using a CE approach, while a GA approach is used to explore the micro-architecture search space. The proposed algorithm is evaluated across four commonly used datasets and compared against six NAS peer competitors and five state-of-the-art manually designed CNN architectures. The results validate the approach's high competitiveness, outperforming several peer competitors on image and text classification tasks. © 2023 IEEE.

关键词： Cellular Encoding Convolutional Neural Networks Neural Architecture Search

来源：评论

学校读者我要写书评

暂无评论

ANIMC: A Soft Approach for Autoweighted Noisy and Incomplete Multiview Clustering

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2022年第2期3卷 192-206页

作者： Fang, Xiang Hu, Yuchong Zhou, Pan Wu, Dapeng Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering The School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Information Storage System Ministry of Education of China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Department of Electrical and Computer Engineering University of Florida GainesvilleFL32611 United States

Multiview clustering has wide real-world applications because it can process data from multiple sources. However, these data often contain missing instances and noises, which are ignored by most multiview clustering methods. Missing instances may make these methods difficult to use directly, and noises will lead to unreliable clustering results. In this article, we propose a novel autoweighted noisy and incomplete multiview clustering (ANIMC) approach via a soft autoweighted strategy and a doubly soft regular regression model. First, by designing adaptive semiregularized nonnegative matrix factorization, the soft autoweighted strategy assigns a proper weight to each view and adds a soft boundary to balance the influence of noises and incompleteness. Second, by proposing θ-norm, the doubly soft regularized regression model adjusts the sparsity of our model by choosing different θ. Compared with previous methods, ANIMC has three unique advantages: 1) it is a soft algorithm to adjust our approach in different scenarios, thereby improving its generalization ability;2) it automatically learns a proper weight for each view, thereby reducing the influence of noises;3) it performs doubly soft regularized regression that aligns the same instances in different views, thereby decreasing the impact of missing instances. Extensive experimental results show its superior advantages over other state-of-the-art works. © 2020 IEEE.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Road Detection Based on Fusion of LiDAR data and Visual data 1

Road Detection Based on Fusion of LiDAR Data and Visual Data

引用

1st International Conference on Intelligent Transportation and Smart Cities, ICITSC 2024

作者： Yang, Chaoju Rong, Jian Chin, Soon Ku School of Big Data and Intelligent Engineering Southwest Forestry University Kunming China Department of Computer Science Universiti Tunku Abdul Rahman Kampar31900 Malaysia

ISBN: (纸本)9781643685205

Smart transportation is a new development model for intelligent traffic based on the combination of the Internet, the Internet of Things, and other networks. Road detection is one of the foundational and core technologies in smart transportation. It provides accurate, reliable, and real-time road information for applications such as autonomous driving, intelligent traffic management, and urban planning. This contributes to the improvement of traffic safety, efficiency, and sustainability. However, relying solely on visual images for road detection still faces numerous challenges, such as changes in lighting conditions, image blurring, and occlusions. To enhance the robustness and accuracy of road detection, leveraging LiDAR (Light Detection and Ranging) data as supplementary information is considered. LiDAR data is not affected by visual noise and can offer more precise depth and height information. Nevertheless, effectively integrating and adapting to different data and feature spaces remain crucial challenges. This paper proposes an improved road detection method based on the PLARD (Progressive LiDAR Adaptation for Road Detection) network. It introduces the U-Net network as an additional branch, collaborating with the image and point cloud branches for feature fusion and road detection. The U-Net network utilizes information from the images for initial segmentation, providing a better prior, and enhances the feature fusion capability of the PLARD network, thereby improving segmentation accuracy and robustness. Experiments conducted on the KITTI Road dataset demonstrate that the proposed method outperforms the PLARD network and other baseline methods in terms of the Dice coefficient. Particularly, it excels in complex urban scenarios and exhibits strong generalization capabilities. The introduced road detection approach, combining LiDAR and visual data, provides an efficient, robust, and versatile solution for smart transportation. It adapts to different scenarios

关键词： Autonomous vehicles

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：