检索结果-内蒙古大学图书馆

Knowledge Graph Augmented Network Towards Multiview Representation Learning for Aspect-Based Sentiment Analysis

IEEE Transactions on Knowledge and Data Engineering 2023年第10期35卷 10098-10111页

作者： Zhong, Qihuang Ding, Liang Liu, Juhua Du, Bo Jin, Hua Tao, Dacheng Wuhan University National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Hubei Key Laboratory of Multimedia and Network Communication Engineering Hubei Wuhan430072 China Jd Explore Academy at *** Beijing100101 China Wuhan University Research Center for Graphic Communication Printing and Packaging Institute of Artificial Intelligence Hubei Wuhan430072 China Hospital of Kunming University of Science and Technology Kunming650032 China

Aspect-based sentiment analysis (ABSA) is a fine-grained task of sentiment analysis. To better comprehend long complicated sentences and obtain accurate aspect-specific information, linguistic and commonsense knowledge are generally required in this task. However, most current methods employ complicated and inefficient approaches to incorporate external knowledge, e.g., directly searching the graph nodes. Additionally, the complementarity between external knowledge and linguistic information has not been thoroughly studied. To this end, we propose a knowledge graph augmented network (KGAN), which aims to effectively incorporate external knowledge with explicitly syntactic and contextual information. In particular, KGAN captures the sentiment feature representations from multiple different perspectives, i.e., context-, syntax- and knowledge-based. First, KGAN learns the contextual and syntactic representations in parallel to fully extract the semantic features. Then, KGAN integrates the knowledge graphs into the embedding space, based on which the aspect-specific knowledge representations are further obtained via an attention mechanism. Last, we propose a hierarchical fusion module to complement these multi-view representations in a local-to-global manner. Extensive experiments on five popular ABSA benchmarks demonstrate the effectiveness and robustness of our KGAN. Notably, with the help of the pretrained model of RoBERTa, KGAN achieves a new record of state-of-the-art performance among all datasets. © 1989-2012 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Large-Scale Multi-Camera Person Trajectory Tracking Based on Low Sampling Rate of Camera 10

Large-Scale Multi-Camera Person Trajectory Tracking Based on...

引用

10th International Conference on Big Data Computing and Communications, BIGCOM 2024

作者： Wang, Yan Zhang, Lan Wang, Xianwen Ding, Ke Yan, Jin Anhui University AHU-IAI AI Joint Laboratory Hefei230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230088 China School of Computer Science and Technology University of Science and Technology of China Hefei230026 China

ISBN: (纸本)9798331509538

With the development of smart cities, particularly on campuses and in industrial parks, the rapid increase in the number of cameras has boosted the demand for multi-target, multi-camera tracking technology. However, current work on multi-target multi-camera tracking often involves a small number of cameras with limited monitoring coverage and short duration, insufficient for the analytical tasks required in smart parks. Moreover, existing works rely on high frame rate video streams as the data source, which, despite providing rich information, demand high storage and computational resources, limiting their application in long-term, large-scale trajectory tracking scenarios. In response to these challenges, we propose a new application scenario: large-scale multi-camera pedestrian tracking based on low-sampling-rate images. By utilizing low-sampling-rate surveillance images instead of videos and we have designed a Multi-dimensional Fusion Identity Verification architecture and a new trajectory tracking process to address the challenges brought about by large-scale camera tracking scenarios, such as environmental factors, diverse camera installation conditions, and the similarity in clothing among a large number of covered individuals. Our approach was tested in a real-world surveillance system with 2,456 cameras covering over 494.2 acres. Despite a significant reduction in data volume by over 60 times and an increase in camera count by 200 times compared to using video data sources of the real world such as WildTrack, our method still attained a pedestrian tracking accuracy of 75.8% and a recall rate of 57.4%. These results affirm our method's effectiveness and feasibility in large-scale environments. © 2024 IEEE.

关键词： Image sampling

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Learning Network Optimization Based on Weight Adaptive 11

Multi-Task Learning Network Optimization Based on Weight Ada...

引用

11th IEEE International Conference on Behavioural and Social Computing, BESC 2024

作者： Cao, Zizhuo Li, Yidong Ding, Chuntao Zhang, Zhuxi School of Computer Science and Technology Beijing Jiaotong University Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education Beijing100044 China General Logistics Information Center Beijing100036 China

ISBN: (纸本)9798331531904

Multi-task learning has emerged as a significant topic in artificial intelligence research, where a singular network model performs numerous tasks. This approach simultaneously processes multiple related tasks and shared knowledge, enhancing model generalization while increasing efficiency. This methodology provides innovative solutions to complex real-world problems. However, the single-model-based approach for multi-task learning suffers from inter-task interference in practice. Therefore, the exploration of more efficient multi-task learning strategies, aimed at balancing the synergy and conflict among tasks and minimizing the dependence on computational resources, is pivotal for the field's future progress. We propose a strategy that autonomously adjusts both the parameters and structures of the model to alleviate gradient interference in multi-task learning. This method includes integrating a lightweight, weight-adaptive module that enhances the network's ability to process tasks by optimally balancing parameter sharing and isolation. This adaptation enables the model to share common features across tasks while allocating distinct spaces for each task, thereby reducing interference. Our extensive experimental validation indicates that our framework surpasses other multi-task learning approaches, achieving joint optimization of tasks more effectively. This enhancement not only bolsters performance but also maintains an equilibrium between accuracy and inference speed. © 2024 IEEE.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Learning for UAV Trajectory and Caching With Federated Cloud-Assisted Knowledge Distillation

引用

IEEE Transactions on Network and Service Management 2025年第3期22卷 2516-2533页

作者： Tietaa Maale, Gerald Arden Elorm Kuadey, Noble Arafat, Yeasin Thomas, Kwantwi Sun, Guolin Liu, Guisong Research Institute of Intelligent Computing University of Electronic Science and Technology of China School of Computer Science and Engineering National Key Laboratory of Intelligent Collaborative Computing Chengdu611731 China McCoy University College of Education Department of Mathematics and ICT Nadowli Ghana Research Institute of Intelligent Computing at the University of Electronic Science and Technology of China School of Computer Science and Engineering National Key Laboratory of Intelligent Collaborative Computing Chengdu611731 China Ho Technical University Department of Computer Science Ho Ghana University of Mines and Technology Department of Computer Science and Engineering Tarkwa Ghana Southwestern University of Finance and Economics Complex Laboratory of New Finance and Economics School of Computing and Artificial Intelligence Chengdu610074 China Ministry of Education Engineering Research Center of Intelligent Finance Chengdu610030 China

The proliferation of Internet of Things (IoT) technologies and ubiquitous connectivity has led to uncrewed aerial vehicles (UAVs) playing key role as edge servers, revolutionizing the wireless communications landscape by facilitating computing and caching resources closer to ground users (GUs). This advancement significantly alleviates core network loads, reduces latency, and guarantees content availability even in congested or remote areas. However, jointly optimizing UAV caching strategies and trajectories gives rise to a multi-task optimization (MTO) problem. This paper introduces a novel multi-task geo-temporal caching (MT-GTC) framework that addresses the interplay between UAV caching mechanisms and trajectory optimization in a cohesive manner. Leveraging a proposed multi-task learning (MTL) model for joint optimization of UAV caching and trajectory design, we develop a federated learning cloud-assisted knowledge distillation (FL-CAKD) scheme to preserve data privacy and adapt to data heterogeneity. FL-CAKD transfers knowledge from a cloud model orchestrator (CMO), which houses a large and sophisticated teacher model, to a lightweight on-device MTL student models using soft target distributions instead of large model parameters, significantly reducing communication costs. MT-GTC optimizes caching and trajectories to maximize cache hits and minimize latency. Evaluations on real-world mobility datasets demonstrate up to 95% cache hit rates and 21% lower delays compared to baselines. © 2004-2012 IEEE.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

SOFA: A Compute-Memory Optimized Sparsity Accelerator via Cross-Stage Coordinated Tiling 57

SOFA: A Compute-Memory Optimized Sparsity Accelerator via Cr...

引用

57th Annual IEEE/ACM International Symposium on Microarchitecture, MICRO 2024

作者： Wang, Huizheng Fang, Jiahao Tang, Xinru Yue, Zhiheng Li, Jinxi Qin, Yubin Guan, Sihan Yang, Qinze Wang, Yang Li, Chao Hu, Yang Yin, Shouyi School of Integrated Circuits Tsinghua University Beijing100084 China School of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Shanghai Artificial Intelligence Laboratory Shanghai200433 China

ISBN: (纸本)9798350350579

Benefiting from the self-attention mechanism, Transformer models have attained impressive contextual comprehension capabilities for lengthy texts. The requirements of highthroughput inference arise as the large language models (LLMs) become increasingly prevalent, which calls for large-scale token parallel processing (LTPP). However, existing dynamic sparse accelerators struggle to effectively handle LTPP, as they solely focus on separate stage optimization, and with most efforts confined to computational enhancements. By re-examining the endto- end flow of dynamic sparse acceleration, we pinpoint an everoverlooked opportunity that the LTPP can exploit the intrinsic coordination among stages to avoid excessive memory access and redundant computation. Motivated by our observation, we present SOFA, a cross-stage compute-memory efficient algorithmhardware co-design, which is tailored to tackle the challenges posed by LTPP of Transformer inference effectively. We first propose a novel leading zero computing paradigm, which predicts attention sparsity by using log-based add-only operations to avoid the significant overhead of prediction. Then, a distributed sorting and a sorted updating FlashAttention mechanism are proposed with cross-stage coordinated tiling principle, which enables finegrained and lightweight coordination among stages, helping optimize memory access and latency. Further, we propose a SOFA accelerator to support these optimizations efficiently. Extensive experiments on 20 benchmarks show that SOFA achieves 9.5× speed up and 71.5× higher energy efficiency than Nvidia A100 GPU. Compared to eight SOTA accelerators, SOFA achieves an average 15.8× energy efficiency, 10.3× area efficiency and 9.3× speed up, respectively. © 2024 IEEE.

关键词： Integrated circuit design

来源：评论

学校读者我要写书评

暂无评论

Multiscale and Auto-Tuned Semi-Supervised Deep Subspace Clustering and Its Application in Brain Tumor Clustering

引用

computers, Materials & Continua 2024年第6期79卷 4741-4762页

作者： Zhenyu Qian Yizhang Jiang Zhou Hong Lijun Huang Fengda Li Khin Wee Lai Kaijian Xia School of Artificial Intelligence and Computer Science Jiangnan UniversityWuxi214122China Department of Medical Imaging The Changshu Affiliated Hospital of Soochow UniversitySuzhou215500China Department of Neurosurgery The Changshu Affiliated Hospital of Soochow UniversityChangshu215500China Department of Scientific Research The Changshu Affiliated Hospital of Soochow UniversitySuzhou215500China Changshu Key Laboratory of Medical Artificial Intelligence and Big Data Suzhou215500China Department of Biomedical Engineering Faculty of EngineeringUniversity of MalayaKuala Lumpur50603Malaysia

In this paper,we introduce a novel Multi-scale and Auto-tuned Semi-supervised Deep Subspace Clustering(MAS-DSC)algorithm,aimed at addressing the challenges of deep subspace clustering in high-dimensional real-world data,particularly in the field of medical *** deep subspace clustering algorithms,which are mostly unsupervised,are limited in their ability to effectively utilize the inherent prior knowledge in medical *** MAS-DSC algorithm incorporates a semi-supervised learning framework that uses a small amount of labeled data to guide the clustering process,thereby enhancing the discriminative power of the feature ***,the multi-scale feature extraction mechanism is designed to adapt to the complexity of medical imaging data,resulting in more accurate clustering *** address the difficulty of hyperparameter selection in deep subspace clustering,this paper employs a Bayesian optimization algorithm for adaptive tuning of hyperparameters related to subspace clustering,prior knowledge constraints,and model loss *** experiments on standard clustering datasets,including ORL,Coil20,and Coil100,validate the effectiveness of the MAS-DSC *** results show that with its multi-scale network structure and Bayesian hyperparameter optimization,MAS-DSC achieves excellent clustering results on these ***,tests on a brain tumor dataset demonstrate the robustness of the algorithm and its ability to leverage prior knowledge for efficient feature extraction and enhanced clustering performance within a semi-supervised learning framework.

关键词： Deep subspace clustering multiscale network structure automatic hyperparameter tuning semi-supervised medical image clustering

来源：评论

学校读者我要写书评

暂无评论

On the emergence of cross-task linearity in pretraining-finetuning paradigm 24

On the emergence of cross-task linearity in pretraining-fine...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Zhanpeng Zhou Zijun Chen Yilan Chen Bo Zhang Junchi Yan School of Artificial Intelligence & Department of Computer Science and Engineering & MoE Lab of AI Shanghai Jiao Tong University Shanghai China School of Artificial Intelligence & Department of Computer Science and Engineering & MoE Lab of AI Shanghai Jiao Tong University Shanghai China and Shanghai Artificial Intelligence Laboratory Computer Science and Engineering University of California San Diego Shanghai Artificial Intelligence Laboratory

The pretraining-finetuning paradigm has become the prevailing trend in modern deep learning. In this work, we discover an intriguing linear phenomenon in models that are initialized from a common pretrained checkpoint and finetuned on different tasks, termed as Cross-Task Linearity (CTL). Specifically, we show that if we linearly interpolate the weights of two finetuned models, the features in the weight-interpolated model are often approximately equal to the linear interpolation of features in two finetuned models at each layer. We provide comprehensive empirical evidence supporting that CTL consistently occurs for finetuned models that start from the same pretrained checkpoint. We conjecture that in the pretraining-finetuning paradigm, neural networks approximately function as linear maps, mapping from the parameter space to the feature space. Based on this viewpoint, our study unveils novel insights into explaining model merging/editing, particularly by translating operations from the parameter space to the feature space. Furthermore, we delve deeper into the root cause for the emergence of CTL, highlighting the role of pretraining. We released our source code at https://***/zzp1012/Cross-Task-Linearity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intraoperative 2D/3D Image Registration via Differentiable X-Ray Rendering

Intraoperative 2D/3D Image Registration via Differentiable X...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Vivek Gopalakrishnan Neel Dey Polina Golland Harvard-MIT Health Sciences and Technology MIT Computer Science and Artificial Intelligence Laboratory

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Surgical decisions are informed by aligning rapid portable 2D intraoperative images (e.g. X-rays) to a high-fidelity 3D preoperative reference scan (e.g. CT). However, 2D/3D registration can often fail in practice: conventional optimization methods are prohibitively slow and suscepti-ble to local minima, while neural networks trained on small datasets fail on new patients or require impractical land-mark supervision. We present DiffPose, a self-supervised approach that leverages patient-specific simulation and differentiable physics-based rendering to achieve accurate 2D/3D registration without relying on manually labeled data. Preoperatively, a CNN is trained to regress the pose of a randomly oriented synthetic X-ray rendered from the pre-operative CT. The CNN then initializes rapid intraoperative test-time optimization that uses the differentiable X-ray ren-derer to refine the solution. Our work further proposes several geometrically principled methods for sampling camera poses from SE (3), for sparse differentiable rendering, and for driving registration in the tangent space sc(3) with geodesic and multiscale locality-sensitive losses. DiffPose achieves sub-millimeter accuracy across surgical datasets at intraoperative speeds, improving upon existing unsupervised methods by an order of magnitude and even outperforming supervised baselines. Our implementation is at https://***/eigenvivek/DiffPose.

关键词： Accuracy Three-dimensional displays Runtime Computed tomography Neural networks Surgery Optimization methods

来源：评论

学校读者我要写书评

暂无评论

Non-Gaussian Uncertainty Minimization Based Control of Stochastic Nonlinear Robotic Systems

Non-Gaussian Uncertainty Minimization Based Control of Stoch...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Weiqiao Han Ashkan Jasour Brian Williams Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology

In this paper, we consider the closed-loop control problem of nonlinear robotic systems in the presence of probabilistic uncertainties and disturbances. More precisely, we design a state feedback controller that minimizes deviations of the states of the system from the nominal state trajectories due to uncertainties and disturbances. Existing approaches to address the control problem of probabilistic systems are limited to particular classes of uncertainties and systems such as Gaussian uncertainties and processes and linearized systems. We present an approach that deals with nonlinear dynamics models and arbitrary known probabilistic uncertainties. We formulate the controller design problem as an optimization problem in terms of statistics of the probability distributions including moments and characteristic functions. In particular, in the provided optimization problem, we use moments and characteristic functions to propagate uncertainties throughout the nonlinear motion model of robotic systems. In order to reduce the tracking deviations, we minimize the uncertainty of the probabilistic states around the nominal trajectory by minimizing the trace and the determinant of the covariance matrix of the probabilistic states. To obtain the state feedback gains, we solve deterministic optimization problems in terms of moments, characteristic functions, and state feedback gains using off-the-shelf interior-point optimization solvers. To illustrate the performance of the proposed method, we compare our method with existing probabilistic control methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning 41

Energy-Guided Diffusion Sampling for Offline-to-Online Reinf...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Xu-Hui Liu, Tian-Shuo Jiang, Shengyi Chen, Ruifeng Zhang, Zhilong Chen, Xinwei Yu, Yang National Key Laboratory for Novel Software Technology Nanjing University China School of Artificial Intelligence Nanjing University China Polixir Technologies China Department of Computer Science The University of Hong Kong Hong Kong

Combining offline and online reinforcement learning (RL) techniques is indeed crucial for achieving efficient and safe learning where data acquisition is expensive. Existing methods replay offline data directly in the online phase, resulting in a significant challenge of data distribution shift and subsequently causing inefficiency in online fine-tuning. To address this issue, we introduce an innovative approach, Energy-guided DIffusion Sampling (EDIS), which utilizes a diffusion model to extract prior knowledge from the offline dataset and employs energy functions to distill this knowledge for enhanced data generation in the online phase. The theoretical analysis demonstrates that EDIS exhibits reduced suboptimality compared to solely utilizing online data or directly reusing offline data. EDIS is a plug-in approach and can be combined with existing methods in offline-to-online RL setting. By implementing EDIS to off-the-shelf methods Cal-QL and IQL, we observe a notable 20% average improvement in empirical performance on MuJoCo, AntMaze, and Adroit environments. Code is available at https://***/liuxhym/EDIS. Copyright 2024 by the author(s)

关键词： Adversarial machine 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：