检索结果-内蒙古大学图书馆

32nd ACM World Wide Web Conference, WWW 2023

作者： Wan, Liangtian Fu, Zhenqiang Sun, Lu Wang, Xianpeng Xu, Gang Yan, Xiaoran Xia, Feng Key Laboratory for Ubiquitous Network Service Software of Liaoning Province School of Software Dalian University of Technology Dalian China Department of Communication Engineering Institute of Information Science Technology Dalian Maritime University Dalian China State Key Laboratory of Marine Resource Utilization in South China Sea School of Information and Communication Engineering Hainan University Haikou China State Key Laboratory of Millimeter Waves School of Information Science and Engineering Southeast University Nanjing China Research Center of Big Data Intelligence Research Institute of Artificial Intelligence Zhejiang Lab Hangzhou China School of Computing Technologies Rmit University Melbourne Australia

ISBN: (纸本)9781450394161

Recent years have witnessed significant advances in graph contrastive learning (GCL), while most GCL models use graph neural networks as encoders based on supervised learning. In this work, we propose a novel graph learning model called GraphTL, which explores self-supervised teaching and learning of representations on graphs. One critical objective of GCL is to retain original graph information. For this purpose, we design an encoder based on the idea of unsupervised dimensionality reduction of locally linear embedding (LLE). Specifically, we map one iteration of the LLE to one layer of the network. To guide the encoder to better retain the original graph information, we propose an unbalanced contrastive model consisting of two views, which are the learning view and the teaching view, respectively. Furthermore, we consider the nodes that are identical in muti-views as positive node pairs, and design the node similarity scorer so that the model can select positive samples of a target node. Extensive experiments have been conducted over multiple datasets to evaluate the performance of GraphTL in comparison with baseline models. Results demonstrate that GraphTL can reduce distances between similar nodes while preserving network topological and feature information, yielding better performance in node classification. © 2023 ACM.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Generalizable Black-Box Adversarial Attack with Meta Learning

arXiv

引用

arXiv 2023年

作者： Yin, Fei Zhang, Yong Wu, Baoyuan Feng, Yan Zhang, Jingyi Fan, Yanbo Yang, Yujiu Tsinghua Shenzhen International Graduate School Tsinghua University Beijing100190 China The School of Data Science Shenzhen Research Institute of Big Data Chinese University of Hong Kong Shenzhen518172 China Tencent AI Lab Guangdong Shenzhen518057 China The Center for Future Media The School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu610056 China

In the scenario of black-box adversarial attack, the target model's parameters are unknown, and the attacker aims to find a successful adversarial perturbation based on query feedback under a query budget. Due to the limited feedback information, existing query-based black-box attack methods often require many queries for attacking each benign example. To reduce query cost, we propose to utilize the feedback information across historical attacks, dubbed example-level adversarial transferability. Specifically, by treating the attack on each benign example as one task, we develop a meta-learning framework by training a meta generator to produce perturbations conditioned on benign examples. When attacking a new benign example, the meta generator can be quickly fine-tuned based on the feedback information of the new task as well as a few historical attacks to produce effective perturbations. Moreover, since the meta-train procedure consumes many queries to learn a generalizable generator, we utilize model-level adversarial transferability to train the meta generator on a white-box surrogate model, then transfer it to help the attack against the target model. The proposed framework with the two types of adversarial transferability can be naturally combined with any off-the-shelf query-based attack methods to boost their performance, which is verified by extensive experiments. The source code is available at https://***/SCLBD/MCG-Blackbox. Copyright © 2023, The Authors. All rights reserved.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Hybrid Parallel Inference for Large Model on Heterogeneous Clusters for High Throughput

Hybrid Parallel Inference for Large Model on Heterogeneous C...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Chaonong Xu Weiming Kong Min Liu Mingming Zhang Chao Li Luqi Gong Beijing Key Lab of Petroleum Data Mining China University of Petroleum (Beijing) Beijing China Institute of Intelligent Computing Zhejiang Lab Hangzhou China School of Computer Science (National Pilot Software Engineering School) BUPT Beijing China

In high-throughput intelligent computing scenarios, multi-device parallelism strategies based on data parallelism or pipeline parallelism have been extensively utilized to accelerate large deep neural network model inference. data parallelism offers nearly linear improvement in inference speed, but it is limited by the memory capacity of a single device which constrains the model size. On the other hand, pipeline parallelism can support larger models, but the total communication of the activations among devices is high, which limits the improvement of the inference speed. To address the demand for efficient model inference in high-throughput heterogeneous scenarios, we proposes a hybrid parallelism strategy that combines data parallelism and pipeline parallelism. The strategy involves grouping heterogeneous device clusters and then employing inter-group data parallelism along with intra-group pipeline parallelism. Moreover, we propose an algorithm to find an optimal hybrid parallel inference strategy with maximum throughput. The control variables of the strategy includes the number of groups, group-device assignments and model partition ratios. Our experimental evaluation demonstrates that compared to PipeEdge, a pipeline parallel inference framework for heterogeneous cluster, our strategy can achieve 1.7× −3.4× acceleration in an 8-device heterogeneous cluster without loss of accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards high-throughput and low-latency billion-scale vector search via CPU/GPU collaborative filtering and re-ranking 25

Towards high-throughput and low-latency billion-scale vector...

引用

Proceedings of the 23rd USENIX Conference on File and Storage Technologies

作者： Bing Tian Haikun Liu Yuhang Tang Shihai Xiao Zhuohui Duan Xiaofei Liao Hai Jin Xuecang Zhang Junhua Zhu Yu Zhang National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Huawei Technologies Co. Ltd Towards high-throughput and low-latency billion-scale vector search via CPU/GPU collaborative filtering and re-ranking

ISBN: (纸本)9781939133458

Approximate nearest neighbor search (ANNS) has emerged as a crucial component of database and AI infrastructure. Ever-increasing vector datasets pose significant challenges in terms of performance, cost, and accuracy for ANNS services. None of modern ANNS systems can address these issues simultaneously. In this paper, we present Fusion-ANNS, a high-throughput, low-latency, cost-efficient, and high-accuracy ANNS system for billion-scale datasets using SSDs and only one entry-level GPU. The key idea of Fusion-ANNS lies in CPU/GPU collaborative filtering and reranking mechanisms, which significantly reduce I/O operations across CPUs, GPU, and SSDs to break through the I/O performance bottleneck. Specifically, we propose three novel designs: (1) multi-tiered indexing to avoid data swapping between CPUs and GPU, (2) heuristic re-ranking to eliminate unnecessary I/Os and computations while guaranteeing high accuracy, and (3) redundant-aware I/O deduplication to further improve I/O efficiency. We implement FusionANNS and compare it with the state-of-the-art SSD-based ANNS system-SPANN and GPU-accelerated in-memory ANNS system-RUMMY. Experimental results show that FusionANNS achieves 1) 9.4-13.1× higher query per second (QPS) and 5.7-8.8× higher cost efficiency compared with SPANN; 2) and 2-4.9× higher QPS and 2.3-6.8× higher cost efficiency compared with RUMMY, while guaranteeing low latency and high accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CCLNet: Causal and Contrastive Learning Framework for Enhanced Pulmonary Embolism Detection

CCLNet: Causal and Contrastive Learning Framework for Enhanc...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Zhipeng Wang Ruiquan Ge Jianxun Yu Feiwei Qin Yuan Tian Nannan Li Wenwen Min Ahmed Elazab Changmiao Wang HDU-ITMO Joint Institute Hangzhou Dianzi University Hangzhou China School of Computer Science Hangzhou Dianzi University Hangzhou China School of Management Dalian Polytechnic University Dalian China Second Affiliated Hospital Chinese University of Hong Kong Shenzhen China School of Science and Technology Macau University Macau China School of Information Science and Engineering Yunnan University Yunnan China School of Biomedical Engineering Shenzhen University Shenzhen China Medical Big Data Lab Shenzhen Research Institute of Big Data Shenzhen China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

The fusion of multimodal medical data is crucial for helping doctors make accurate treatment decisions. For example, combining Computed Tomography Pulmonary Angiography (CTPA) with Electronic Health Records (EHR) can significantly improve the accuracy of Pulmonary Embolism (PE) detection, thereby increasing patient survival rates. Although multimodal learning has advantages in PE diagnosis, the heterogeneity of multimodal data poses a significant challenge to accurate diagnosis. The natural semantic and structural differences between data modalities make it difficult to effectively integrate their information. In addition, within a single modality, the existence of redundant and irrelevant information introduces unnecessary variability, making the data more complex, and making stable diagnosis challenging. To address these issues, we propose a new framework called CCLNet, which includes a contrastive learning component for addressing inter-modality heterogeneity and a causal learning component for handling intra-modality heterogeneity. Specifically, we achieve precise alignment between visual and tabular modalities by using global-level information to soften labels during contrastive learning. In addition, by using causal intervention methods to eliminate the influence of heterogeneous factors within the modality, we can accurately reveal the causal relationship between features and targets, thereby improving the accuracy and stability of the model. Experimental results demonstrate that our method performs excellently, achieving the best results. Our code is available at https://***/LeavingStarW/CLPE.

关键词： Visualization Accuracy Smoothing methods Hospitals Pulmonary diseases Lungs Semantics Contrastive learning Stability analysis Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Iteratively Coupled Multiple Instance Learning from Instance to Bag Classifier for Whole Slide Image Classification

arXiv

引用

arXiv 2023年

作者： Wang, Hongyi Luo, Luyang Wang, Fang Tong, Ruofeng Chen, Yen-Wei Hu, Hongjie Lin, Lanfen Chen, Hao College of Computer Science and Technology Zhejiang University Hangzhou China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Department of Radiology Sir Run Run Shaw Hospital Hangzhou China Research Center for Healthcare Data Science Zhejiang Lab Hangzhou China College of Information Science and Engineering Ritsumeikan University Kusatsu Japan Department of Chemical and Biological Engineering The Hong Kong University of Science and Technology Hong Kong

Whole Slide Image (WSI) classification remains a challenge due to their extremely high resolution and the absence of fine-grained labels. Presently, WSI classification is usually regarded as a Multiple Instance Learning (MIL) problem when only slide-level labels are available. MIL methods involve a patch embedding module and a bag-level classification module, but they are prohibitively expensive to be trained in an end-to-end manner. Therefore, existing methods usually train them separately, or directly skip the training of the embedder. Such schemes hinder the patch embedder’s access to slide-level semantic labels, resulting in inconsistency within the entire MIL pipeline. To overcome this issue, we propose a novel framework called Iteratively Coupled MIL (ICMIL), which bridges the loss back-propagation process from the bag-level classifier to the patch embedder. In ICMIL, we use category information in the bag-level classifier to guide the patch-level fine-tuning of the patch feature extractor. The refined embedder then generates better instance representations for achieving a more accurate bag-level classifier. By coupling the patch embedder and bag classifier at a low cost, our proposed framework enables information exchange between the two modules, benefiting the entire MIL classification model. We tested our framework on two datasets using three different backbones, and our experimental results demonstrate consistent performance improvements over state-of-the-art MIL methods. The code is available at: https://***/Dootmaan/ICMIL. Copyright © 2023, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Towards Unified Prompt Tuning for Few-shot Text Classification

arXiv

引用

arXiv 2022年

作者： Wang, Jianing Wang, Chengyu Luo, Fuli Tan, Chuanqi Qiu, Minghui Yang, Fei Shi, Qiuhui Huang, Songfang Gao, Ming School of Data Science and Engineering East China Normal University China Alibaba Group China Zhejiang Lab China Ant Group China

Prompt-based fine-tuning has boosted the performance of Pre-trained Language Models (PLMs) on few-shot text classification by employing task-specific prompts. Yet, PLMs are unfamiliar with prompt-style expressions during pre-training, which limits the few-shot learning performance on downstream tasks. It would be desirable if the models can acquire some prompting knowledge before adaptation to specific NLP tasks. We present the Unified Prompt Tuning (UPT) framework, leading to better few-shot text classification for BERT-style models by explicitly capturing prompting semantics from non-target NLP datasets. In UPT, a novel paradigm Prompt-Options-Verbalizer is proposed for joint prompt learning across different NLP tasks, forcing PLMs to capture task-invariant prompting knowledge. We further design a self-supervised task named Knowledge-enhanced Selective Masked Language Modeling to improve the PLM's generalization abilities for accurate adaptation to previously unseen tasks. After multi-task learning across multiple tasks, the PLM can be better prompt-tuned towards any dissimilar target tasks in low-resourced settings. Experiments over a variety of NLP tasks show that UPT consistently outperforms state-of-the-arts for prompt-based fine-tuning. Copyright © 2022, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Empowering Precision Medicine: AI-Driven Schizophrenia Diagnosis via EEG Signals: A Comprehensive Review from 2002-2023

arXiv

引用

arXiv 2023年

作者： Jafari, Mahboobeh Sadeghi, Delaram Shoeibi, Afshin Alinejad-Rokny, Hamid Beheshti, Amin García, David López Chen, Zhaolin Acharya, U. Rajendra Gorriz, Juan M. Internship in BioMedical Machine Learning Lab The Graduate School of Biomedical Engineering UNSW Sydney SydneyNSW2052 Australia Data Science and Computational Intelligence Institute University of Granada Spain BioMedical Machine Learning Lab The Graduate School of Biomedical Engineering UNSW Sydney SydneyNSW2052 Australia UNSW Data Science Hub The University of New South Wales SydneyNSW2052 Australia Health Data Analytics Program Centre for Applied Artificial Intelligence Macquarie University Sydney2109 Australia Data Science Lab School of Computing Macquarie University SydneyNSW2109 Australia Monash University Melbourne Australia School of Mathematics Physics and Computing University of Southern Queensland Springfield Australia Department of Psychiatry University of Cambridge United Kingdom

Schizophrenia (SZ) is a prevalent mental disorder characterized by cognitive, emotional, and behavioral changes. Symptoms of SZ include hallucinations, illusions, delusions, lack of motivation, and difficulties in concentration. While the exact causes of SZ remain unproven, factors such as brain injuries, stress, and psychotropic drugs have been implicated in its development. SZ can be classified into different types, including paranoid, disorganized, catatonic, undifferentiated, and residual. Diagnosing SZ involves employing various tools, including clinical interviews, physical examinations, psychological evaluations, the Diagnostic and Statistical Manual of Mental Disorders (DSM), and neuroimaging techniques. Electroencephalography (EEG) recording is a significant functional neuroimaging modality that provides valuable insights into brain function during SZ. However, EEG signal analysis poses challenges for neurologists and scientists due to the presence of artifacts, long-term recordings, and the utilization of multiple channels. To address these challenges, researchers have introduced artificial intelligence (AI) techniques, encompassing conventional machine learning (ML) and deep learning (DL) methods, to aid in SZ diagnosis. This study reviews papers focused on SZ diagnosis utilizing EEG signals and AI methods. The introduction section provides a comprehensive explanation of SZ diagnosis methods and intervention techniques. Subsequently, review papers in this field are discussed, followed by an introduction to the AI methods employed for SZ diagnosis and a summary of relevant papers presented in tabular form. Additionally, this study reports on the most significant challenges encountered in SZ diagnosis, as identified through a review of papers in this field. Future directions to overcome these challenges are also addressed. The discussion section examines the specific details of each paper, culminating in the presentation of conclusions and findings. © 2023,

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models

arXiv

引用

arXiv 2023年

作者： Huang, Yuzhou Xie, Liangbin Wang, Xintao Yuan, Ziyang Cun, Xiaodong Ge, Yixiao Zhou, Jiantao Dong, Chao Huang, Rui Zhang, Ruimao Shan, Ying School of Data Science Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China ARC Lab Tencent PCG China University of Macau China Tencent AI Lab China Shenzhen Institute of Advanced Technology China School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Shanghai Artificial Intelligence Laboratory China Tsinghua University China

Current instruction-based editing methods, such as InstructPix2Pix, often fail to produce satisfactory results in complex scenarios due to their dependence on the simple CLIP text encoder in diffusion models. To rectify this, this paper introduces SmartEdit, a novel approach to instruction-based image editing that leverages Multimodal Large Language Models (MLLMs) to enhance their understanding and reasoning capabilities. However, direct integration of these elements still faces challenges in situations requiring complex reasoning. To mitigate this, we propose a Bidirectional Interaction Module that enables comprehensive bidirectional information interactions between the input image and the MLLM output. During training, we initially incorporate perception data to boost the perception and understanding capabilities of diffusion models. Subsequently, we demonstrate that a small amount of complex instruction editing data can effectively stimulate SmartEdit’s editing capabilities for more complex instructions. We further construct a new evaluation dataset, Reason-Edit, specifically tailored for complex instruction-based image editing. Both quantitative and qualitative results on this evaluation dataset indicate that our SmartEdit surpasses previous methods, paving the way for the practical application of complex instruction-based image editing. Copyright © 2023, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

CLAPSep: Leveraging Contrastive Pre-trained Model for Multi-Modal Query-Conditioned Target Sound Extraction

arXiv

引用

arXiv 2024年

作者： Ma, Hao Peng, Zhiyuan Li, Xu Shao, Mingjie Wu, Xixin Liu, Ju School of Information Science and Engineering Shandong University Qingdao China Department of Computer Science North Carolina State University NC United States ARC Lab Tencent PCG China Stanley Ho Big Data Decision Analytics Research Centre The Chinese University of Hong Kong Hong Kong

Universal sound separation (USS) aims to extract arbitrary types of sounds from real-world recordings. This can be achieved by language-queried target sound extraction (TSE), which typically consists of two components: a query network that converts user queries into conditional embeddings, and a separation network that extracts the target sound accordingly. Existing methods commonly train models from scratch. As a consequence, substantial data and computational resources are required to make the randomly initialized model comprehend sound events and perform separation accordingly. In this paper, we propose to integrate pre-trained models into TSE models to address the above issue. To be specific, we tailor and adapt the powerful contrastive language-audio pre-trained model (CLAP) for USS, denoted as CLAPSep. CLAPSep also accepts flexible user inputs, taking both positive and negative user prompts of uni- and/or multi-modalities for target sound extraction. These key features of CLAPSep can not only enhance the extraction performance but also improve the versatility of its application. We provide extensive experiments on 5 diverse datasets to demonstrate the superior performance and zero- and few-shot generalizability of our proposed CLAPSep with fast training convergence, surpassing previous methods by a significant margin. Full codes and some audio examples are released for reproduction and evaluation1 © 2024, CC BY.

关键词： Query languages

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：