检索结果-内蒙古大学图书馆

Hierarchical graph transformer with adaptive node sampling 22

学校读者我要写书评

暂无评论

Hierarchical graph transformer with adaptive node sampling

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Zaixi Zhang Qi Liu Qingyong Hu Chee-Kong Lee Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China and State Key Laboratory of Cognitive Intelligence Hefei Anhui China Hong Kong University of Science and Technology Tencent America

ISBN: (纸本)9781713871088

The Transformer architecture has achieved remarkable success in a number of domains including natural language processing and computer vision. However, when it comes to graph-structured data, transformers have not achieved competitive performance, especially on large graphs. In this paper, we identify the main deficiencies of current graph transformers: (1) Existing node sampling strategies in Graph Transformers are agnostic to the graph characteristics and the training process. (2) Most sampling strategies only focus on local neighbors and neglect the long-range dependencies in the graph. We conduct experimental investigations on synthetic datasets to show that existing sampling strategies are sub-optimal. To tackle the aforementioned problems, we formulate the optimization strategies of node sampling in Graph Transformer as an adversary bandit problem, where the rewards are related to the attention weights and can vary in the training procedure. Meanwhile, we propose a hierarchical attention scheme with graph coarsening to capture the long-range interactions while reducing computational complexity. Finally, we conduct extensive experiments on real-world datasets to demonstrate the superiority of our method over existing graph transformers and popular GNNs.

关键词：

XNLI: Explaining and Diagnosing NLI-based Visual Data Analysis

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Feng, Yingchaojie Wang, Xingbo Pan, Bo Wong, Kam Kwai Ren, Yi Liu, Shi Yan, Zihan Ma, Yuxin Qu, Huamin Chen, Wei The State Key Lab of CAD & CG Zhejiang University Zhejiang Hangzhou China The Laboratory of Art and Archaeology Image Zhejiang University Ministry of Education China The Hong Kong University of Science and Technology Hong Kong The MIT Media Lab CambridgeMA United States The Department of Computer Science and Engineering Southern University of Science and Technology Guangdong China

Natural language interfaces (NLIs) enable users to flexibly specify analytical intentions in data visualization. However, diagnosing the visualization results without understanding the underlying generation process is challenging. Our research explores how to provide explanations for NLIs to help users locate the problems and further revise the queries. We present XNLI, an explainable NLI system for visual data analysis. The system introduces a Provenance Generator to reveal the detailed process of visual transformations, a suite of interactive widgets to support error adjustments, and a Hint Generator to provide query revision hints based on the analysis of user queries and interactions. Two usage scenarios of XNLI and a user study verify the effectiveness and usability of the system. Results suggest that XNLI can significantly enhance task accuracy without interrupting the NLI-based analysis process. Copyright © 2023, The Authors. All rights reserved.

关键词： Data visualization

HeGTa: Leveraging Heterogeneous Graph-enhanced Large Language Models for Few-shot Complex Table Understanding

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jin, Rihui Li, Yu Qi, Guilin Hu, Nan Li, Yuan-Fang Chen, Jiaoyan Wang, Jianan Chen, Yongrui Min, Dehai Bi, Sheng School of Computer Science and Engineering Southeast University China Key Laboratory of New Generation Artificial Intelligence Technology and its Interdisciplinary Applications Southeast University Ministry of Education China Monash University Australia The University of Manchester United Kingdom Alibaba Group China Law and Innovation Lab Law School Southeast University China State Key Laboratory for Novel Software Technology Nanjing University China

Table Understanding (TU) has achieved promising advancements, but it faces the challenges of the scarcity of manually labeled tables and the presence of complex table structures. To address these challenges, we propose HeGTa, a heterogeneous graph (HG)-enhanced large language model (LLM) designed for few-shot TU tasks. This framework aligns structural table semantics with the LLM’s parametric knowledge through soft prompts and instruction tuning. It also addresses complex tables with a multi-task pre-training scheme by incorporating novel multi-granularity self-supervised HG pretext tasks. We empirically demonstrate the effectiveness of HeGTa, showing that it outperforms the SOTA for few-shot complex TU on several benchmarks. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

NEXT:a neural network framework for next POI recommendation

学校读者我要写书评

暂无评论

Frontiers of computer science 2020年第2期14卷 314-333页

作者： Zhiqian ZHANG Chenliang LI Zhiyong WU Aixin SUN Dengpan YE Xiangyang LUO Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of EducationSchool of Cyber Science and EngineeringWuhan UniversityWuhan 430072China Department of Computer Science The University of Hong KongPokfulam RoadHong Kong 999077China School of Computer Science and Engineering Nanyang Technological UniversitySingapore 639798Singapore State Key Lab of Mathematical Engineering and Advanced Computing Zhengzhou 450001China

The task of next POI recommendations has been studied extensively in recent ***,developing a unified recommendation framework to incorporate multiple factors associated with both POIs and users remains challenging,because of the heterogeneity nature of these ***,effective mechanisms to smoothly handle cold-start cases are also a difficult *** by the recent success of neural networks in many areas,in this paper,we propose a simple yet effective neural network framework,named NEXT,for next POI *** is a unified framework to learn the hidden intent regarding user's next move,by incorporating different factors in a unified ***,in NEXT,we incorporate meta-data information,e.g.,user friendship and textual descriptions of POIs,and two kinds of temporal contexts(i.e.,time interval and visit time).To leverage sequential relations and geographical influence,we propose to adopt DeepWalk,a network representation learning technique,to encode such *** evaluate the effectiveness of NEXT against other state-of-the-art alternatives and neural networks based *** results on three publicly available datasets demonstrate that NEXT significantly outperforms baselines in real-time next POI *** experiments show inherent ability of NEXT in handling cold-start.

关键词： POI neural networks POI recommendation

StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ma, Yifeng Wang, Suzhen Hu, Zhipeng Fan, Changjie Lv, Tangjie Ding, Yu Deng, Zhidong Yu, Xin Department of Computer Science and Technology BNRist THUAI State Key Laboratory of Intelligent Technology and Systems Tsinghua University China Virtual Human Group Netease Fuxi AI Lab China Zhejiang University China University of Technology Sydney Australia

Different people speak with diverse personalized speaking styles. Although existing one-shot talking head methods have made significant progress in lip sync, natural facial expressions, and stable head motions, they still cannot generate diverse speaking styles in the final talking head videos. To tackle this problem, we propose a one-shot style-controllable talking face generation framework. In a nutshell, we aim to attain a speaking style from an arbitrary reference speaking video and then drive the one-shot portrait to speak with the reference speaking style and another piece of audio. Specifically, we first develop a style encoder to extract dynamic facial motion patterns of a style reference video and then encode them into a style code. Afterward, we introduce a style-controllable decoder to synthesize stylized facial animations from the speech content and style code. In order to integrate the reference speaking style into generated videos, we design a style-aware adaptive transformer, which enables the encoded style code to adjust the weights of the feed-forward layers accordingly. Thanks to the style-aware adaptation mechanism, the reference speaking style can be better embedded into synthesized videos during decoding. Extensive experiments demonstrate that our method is capable of generating talking head videos with diverse speaking styles from only one portrait image and an audio clip while achieving authentic visual effects. Project Page: https://***/FuxiVirtualHuman/styletalk. Copyright © 2023, The Authors. All rights reserved.

关键词： Decoding

Transformation from System Design Models in SysML to Executable IEC 61499 Function Block Models 6

学校读者我要写书评

暂无评论

Transformation from System Design Models in SysML to Executa...

6th International Conference on Control, Robotics and Cybernetics, CRC 2021

作者： Cao, Yue Liu, Yusheng Huang, Bo Huang, Ganming Ye, Xiaoping Zhejiang University of Technology College of Computer Science and Technology Hangzhou China Zhejiang University State Key Lab. of CADCG Hangzhou China Digital Twin Shanghai Key Laboratory of Aircraft Engine China Lishui University College of Engineering and Design Lishui China

ISBN: (纸本)9781665424370

Designing automation systems requires a joint effort from different domains including the control software and controlled plants. System design is the foundation of the discipline-specific design processes and hence its verification is critical to the success of the whole project. Transforming system design models to simulation models is a common method for system verification. IEC 61499 Function Block (FB) is a feasible target simulation modeling language because of its executable specification nature. However, existing approaches can only generate initial control design from SysML models, which means the generated FB models are not executable. In this study, an approach to transform SysML design models into executable FB models is proposed. First, the execution semantics of hybrid automaton (HA) and execution control chart (ECC), which are the behavior modeling formalisms of SysML and IEC 61499, respectively is analyzed. Then, their semantic similarities and differences are identified. Finally, transformation rules to tackle the semantic differences are proposed so that the missing execution details of FB models can be automatically generated. A CNC bending machine is used as a case study to illustrate the proposed approach. © 2021 IEEE.

关键词： Systems analysis

Biofunctionalization-Optimized Mos2-Based Fet Biosensors for the Detection of Tau Protein

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Wen, Xiaohong Zhao, Xuefeng Shan, Xinzhi Lu, Hongliang Gao, Xiumin Zhuang, Songlin Engineering Research Center of Optical Instrument and System Ministry of Education Shanghai Key Lab of Modern Optical System School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology 516 Jungong Road Shanghai200093 China State Key Laboratory of High-Performance Ceramics and Superfine Microstructure Shanghai Institute of Ceramics Chinese Academy of Sciences Shanghai200050 China State Key Laboratory of ASIC System Shanghai Institute of Intelligent Electronics & Systems School of Microelectronics Fudan University Shanghai200433 China

Field effect transistor (FET)-based biosensors can accurately quantify changes in weak signals and show excellent performance advantages in the detection of trace biological disease markers. Biological functionalization (biofunctionalization) is an important factor in the fabrication of FET-based biosensors, which directly affects the performance of the biosensor. However, little attention from researchers has been paid to biofunctionalization, which results in uneven performance of biosensors. Herein, MoS2-based FET biosensors are designed and fabricated using four different biofunctionalization methods. The most suitable biofunctionalization method is obtained by comparing the sensing performances of different functionalized MoS2-based FET biosensors. Moreover, the working mechanism of the optimized biofunctionalization method is explored. Besides, the biofunctionalization-optimized MoS2-based FET biosensor exhibits excellent sensing performance, achieving sensitive detection of Tau protein in the concentration range of 10-2~103 pg/mL. This study provides a universal and effective strategy for the biofunctionalization optimization of two-dimensional materials-based FET biosensors. © 2024, The Authors. All rights reserved.

关键词： Molybdenum compounds

How to Reduce Change Detection to Semantic Segmentation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Guo-Hua Gao, Bin-Bin Wang, Chenjie State Key Laboratory for Novel Software Technology Nanjing University China Youtu Lab Tencent China Department of Computer Science and Engineering Shanghai Jiao Tong University China

Change detection (CD) aims to identify changes that occur in an image pair taken different times. Prior methods devise specific networks from scratch to predict change masks in pixel-level, and struggle with general segmentation problems. In this paper, we propose a new paradigm that reduces CD to semantic segmentation which means tailoring an existing and powerful semantic segmentation network to solve CD. This new paradigm conveniently enjoys the mainstream semantic segmentation techniques to deal with general segmentation problems in CD. Hence we can concentrate on studying how to detect changes. We propose a novel and importance insight that different change types exist in CD and they should be learned separately. Based on it, we devise a module named MTF to extract the change information and fuse temporal features. MTF enjoys high interpretability and reveals the essential characteristic of CD. And most segmentation networks can be adapted to solve the CD problems with our MTF module. Finally, we propose C-3PO, a network to detect changes at pixel-level. C-3PO achieves state-of-the-art performance without bells and whistles. It is simple but effective and can be considered as a new baseline in this field. Our code is at https://***/Doctorkey/C-3PO. Copyright © 2022, The Authors. All rights reserved.

关键词： Change detection

Biofunctionalization-Optimized MoS2-Based Fet Biosensors for the Detection of Tau Protein

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

Field effect transistor (FET)-based biosensors can accurately quantify changes in weak signals and show excellent performance advantages in the detection of trace biological disease markers. Biological functionalization (biofunctionalization) is an important factor in the fabrication of FET-based biosensors, which directly affects the performance of the biosensor. However, little attention from researchers has been paid to biofunctionalization, which results in uneven performance of biosensors. Herein, MoS2-based FET biosensors are designed and fabricated using four different biofunctionalization methods. The most suitable biofunctionalization method is obtained by comparing the sensing performances of different functionalized MoS2based FET biosensors. Moreover, the working mechanism of the optimized biofunctionalization method is explored. Besides, the biofunctionalization-optimized MoS2-based FET biosensor exhibits excellent sensing performance, achieving sensitive detection of Tau protein in the concentration range of 10-2~103 pg/mL. This study provides a universal and effective strategy for the biofunctionalization optimization of two-dimensional materials-based FET biosensors. © 2024, The Authors. All rights reserved.

关键词： Molybdenum compounds