检索结果-内蒙古大学图书馆

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

作者： Hailin Zhang Yujing Wang Qi Chen Ruiheng Chang Ting Zhang Ziming Miao Yingyan Hou Yang Ding Xupeng Miao Haonan Wang Bochen Pang Yuefeng Zhan Hao Sun Weiwei Deng Qi Zhang Fan Yang Xing Xie Mao Yang Bin Cui School of Computer Science & Key Lab of High Confidence Software Technologies Peking University and Microsoft Microsoft Microsoft and Aerospace Information Research Institute & Key Laboratory of Target Cognition and Application Technology Chinese Academy of Sciences Microsoft and Institute of Information Engineering Chinese Academy of Sciences Carnegie Mellon University National University of Singapore School of Computer Science & Key Lab of High Confidence Software Technologies Peking University and National Engineering Laboratory for Big Data Analysis and Applications Peking University

Embedding-based retrieval methods construct vector indices to search for document representations that are most similar to the query representations. They are widely used in document retrieval due to low latency and decent recall performance. Recent research indicates that deep retrieval solutions offer better model quality, but are hindered by unacceptable serving latency and the inability to support document updates. In this paper, we aim to enhance the vector index with end-to-end deep generative models, leveraging the differentiable advantages of deep retrieval models while maintaining desirable serving efficiency. We propose Model-enhanced Vector Index (MEVI), a differentiable model-enhanced index empowered by a twin-tower representation model. MEVI leverages a Residual Quantization (RQ) codebook to bridge the sequence-to-sequence deep retrieval and embedding-based models. To substantially reduce the inference time, instead of decoding the unique document ids in long sequential steps, we first generate some semantic virtual cluster ids of candidate documents in a small number of steps, and then leverage the well-adapted embedding vectors to further perform a fine-grained search for the relevant documents in the candidate virtual clusters. We empirically show that our model achieves better performance on the commonly used academic benchmarks MSMARCO Passage and Natural Questions, with comparable serving latency to dense retrieval solutions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Graph Transformer with Adaptive Node Sampling

arXiv

引用

arXiv 2022年

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

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. Our code is open-sourced at https://***/zaixizhang/ANS-GT. © 2022, CC BY-SA.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

BroadCAM: Outcome-agnostic Class Activation Mapping for Small-scale Weakly Supervised applications

arXiv

引用

arXiv 2023年

作者： Lin, Jiatai Han, Guoqiang Xu, Xuemiao Liang, Changhong Wong, Tien-Tsin Chen, C.L. Philip Liu, Zaiyi Han, Chu The School of Computer Science and Engineering South China University of Technology Guangdong Guangzhou510006 China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangzhou510080 China Southern Medical University Guangzhou510080 China School of Computer Science and Engineering South China University of Technology State Key Laboratory of Subtropical Building Science Ministry of Education Key Laboratory of Big Data and Intelligent Robot Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong

Class activation mapping (CAM), a visualization technique for interpreting deep learning models, is now commonly used for weakly supervised semantic segmentation (WSSS) and object localization (WSOL). It is the weighted aggregation of the feature maps by activating the high class-relevance ones. Current CAM methods achieve it relying on the training outcomes, such as predicted scores (forward information), gradients (backward information), etc. However, when with small-scale data, unstable training may lead to less effective model outcomes and generate unreliable weights, finally resulting in incorrect activation and noisy CAM seeds. In this paper, we propose an outcome-agnostic CAM approach, called BroadCAM, for small-scale weakly supervised applications. Since broad learning system (BLS) is independent to the model learning, BroadCAM can avoid the weights being affected by the unreliable model outcomes when with small-scale data. By evaluating BroadCAM on VOC2012 (natural images) and BCSS-WSSS (medical images) for WSSS and OpenImages30k for WSOL, BroadCAM demonstrates superior performance than existing CAM methods with small-scale data (less than 5%) in different CNN architectures. It also achieves SOTA performance with large-scale training data. Extensive qualitative comparisons are conducted to demonstrate how BroadCAM activates the high class-relevance feature maps and generates reliable CAMs when with small-scale training data. © 2023, CC BY.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Model-enhanced Vector Index

arXiv

引用

arXiv 2023年

作者： Zhang, Hailin Wang, Yujing Chen, Qi Chang, Ruiheng Zhang, Ting Miao, Ziming Hou, Yingyan Ding, Yang Miao, Xupeng Wang, Haonan Pang, Bochen Zhan, Yuefeng Sun, Hao Deng, Weiwei Zhang, Qi Yang, Fan Xie, Xing Yang, Mao Cui, Bin School of Computer Science Key Lab of High Confidence Software Technologies Peking University China Microsoft United States Aerospace Information Research Institute Key Laboratory of Target Cognition and Application Technology Chinese Academy of Sciences China Institute of Information Engineering Chinese Academy of Sciences China Carnegie Mellon University United States National University of Singapore Singapore National Engineering Laboratory for Big Data Analysis and Applications Peking University China

Embedding-based retrieval methods construct vector indices to search for document representations that are most similar to the query representations. They are widely used in document retrieval due to low latency and decent recall performance. Recent research indicates that deep retrieval solutions offer better model quality, but are hindered by unacceptable serving latency and the inability to support document updates. In this paper, we aim to enhance the vector index with endto- end deep generative models, leveraging the differentiable advantages of deep retrieval models while maintaining desirable serving efficiency. We propose Modelenhanced Vector Index (MEVI), a differentiable model-enhanced index empowered by a twin-tower representation model. MEVI leverages a Residual Quantization (RQ) codebook to bridge the sequence-to-sequence deep retrieval and embeddingbased models. To substantially reduce the inference time, instead of decoding the unique document ids in long sequential steps, we first generate some semantic virtual cluster ids of candidate documents in a small number of steps, and then leverage the well-adapted embedding vectors to further perform a fine-grained search for the relevant documents in the candidate virtual clusters. We empirically show that our model achieves better performance on the commonly used academic benchmarks MSMARCO Passage and Natural Questions, with comparable serving latency to dense retrieval solutions. Copyright © 2023, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Stable and Diverse: A Unified Approach for computerized Adaptive Testing

Stable and Diverse: A Unified Approach for Computerized Adap...

引用

IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS)

作者： Yuting Ning Ye Liu Zhenya Huang Haoyang Bi Qi Liu Enhong Chen Dan Zhang Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China School of Data Science University of Science and Technology of China iFLYTEK Research iFLYTEK CO. LTD

ISBN: (纸本)9781665441506

computerized Adaptive Testing (CAT), aiming to provide personalized tests for each examinee, is an emerging task in the intelligent education field. A CAT system selects questions step by step according to the knowledge states of each examinee, which are estimated by Cognitive Diagnosis Models (CDM). Most existing methods depend on the performance of a single CDM, which is often unstable. Besides, they may select similar questions to generate a test, which to some extent ignores the diversity of selected questions. To this end, in this paper, we propose a novel framework, namely Ensembled computerized Adaptive Testing (EnCAT). Specifically, EnCAT comprises two components, ensemble part and explore part. In the ensemble part, we ensemble multiple CDMs to determine whether a question is informative, which ensures the stability of CAT process. Then, in the explore part, we learn the question representation from the question content and design a mechanism to quantify the similarity of different questions, which avoids the selection of similar questions and is free of expensive human labeling. Finally, extensive experiments are conducted on a real-world dataset, where the experimental results demonstrate the effectiveness of our proposed EnCAT framework with good performance.

关键词： Adaptation models Cloud computing Computational modeling Conferences Education Stability analysis Labeling

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal Effects of Built Environment on Varying Rail Transit Station Ridership Patterns

SSRN

引用

SSRN 2022年

作者： Wang, Jing Wan, Feng Dong, Chunjiao Yin, Chaoying Chen, Xiaoyu Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport Ministry of Transport Beijing Jiaotong University Beijing100044 China Hikvision Research Institute Hangzhou310012 China College of Automobile and Traffic Engineering Nanjing Forestry University Nanjing210037 China School of Computer and Information Technology Beijing Key Laboratory of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing100044 China

Although many studies have explored the impacts of the built environment on rail transit station ridership, spatiotemporal heterogeneity of the effects and different ridership patterns are rarely considered. Using multi-source data from China, three direct models (DRMs) based on the geographically and temporally weighted regression (GTWR) model are proposed to reveal the spatiotemporal effects of daily, weekday hourly and weekend hourly ridership patterns. The results show that employment density, entertainment places, housing prices, and entrances/exits are the dominant variables affecting ridership in the three models;however, their effects vary in spatiotemporal ranges. For example, the positive effect of employment density decreases from Monday to Sunday, and its coefficients during the peak hours are highest in the northwest center, where is the largest technology park situated. The results also highlight the importance of bus stations and parking lots in attracting commuter ridership. The findings provide insights into urban rail transit planning. © 2022, The Authors. All rights reserved.

关键词： Housing

来源：评论

学校读者我要写书评

暂无评论

Existence of periodic and S-asymptotically periodic solutions to fractional diffusion equations with analytic semigroups

Existence of periodic and S-asymptotically periodic solution...

引用

作者： Mu, Jia Nan, Jiecuo Zhou, Yong Key Laboratory of China's Ethnic Languages and Information Technology of Ministry Northwest Minzu University Lanzhou730000 China School of Mathematics and Computer Science Northwest Minzu University Lanzhou730000 China Key Laboratory of Streaming Data Computing Technologies and Application Northwest Minzu University Lanzhou730000 China School of Mathematics and Computer Science Xiangtan University Hunan411105 China Nonlinear Analysis and Applied Mathematics Research Group Faculty of Science King Abdulaziz University Jeddah21589 Saudi Arabia

In this paper, we study periodic and S-asymptotically periodic solutions for fractional diffusion equations (FDE). As we all know, there is no exact periodic solution to differential equations with Caputo or Riemann-Liouville fractional derivatives. Even so, in this paper, periodic (S-asymptotically periodic) mild or classical solutions for FDE with Weyl-Liouville fractional derivatives could be obtained in various fractional power spaces. In addition, a numerical simulation example and a specific example of fractional diffusion equation are given to verify the main theoretical results. © 2019 John Wiley & Sons, Ltd.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Full-Atom Protein Pocket Design via Iterative Refinement

arXiv

引用

arXiv 2023年

作者： Zhang, Zaixi Lu, Zepu Hao, Zhongkai Zitnik, Marinka Liu, Qi Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence Anhui Hefei China Dept. of Comp. Sci. and Tech. Institute for AI THBI Lab BNRist Center Tsinghua-Bosch Joint ML Center Tsinghua China Harvard University United States

The design of de novo functional proteins that bind specific ligand molecules is paramount in therapeutics and bio-engineering. A critical yet formidable task in this endeavor is the design of the protein pocket, which is the cavity region of the protein where the ligand binds. Current methods are plagued by inefficient generation, inadequate context modeling of the ligand molecule, and the inability to generate side-chain atoms. Here, we present the Full-Atom Iterative Refinement (FAIR) method, designed to address these challenges by facilitating the co-design of protein pocket sequences, specifically residue types, and their corresponding 3D structures. FAIR operates in two steps, proceeding in a coarse-to-fine manner (transitioning from protein backbone to atoms, including side chains) for a full-atom generation. In each iteration, all residue types and structures are simultaneously updated, a process termed full-shot refinement. In the initial stage, the residue types and backbone coordinates are refined using a hierarchical context encoder, complemented by two structure refinement modules that capture both inter-residue and pocket-ligand interactions. The subsequent stage delves deeper, modeling the side-chain atoms of the pockets and updating residue types to ensure sequence-structure congruence. Concurrently, the structure of the binding ligand is refined across iterations to accommodate its inherent flexibility. Comprehensive experiments show that FAIR surpasses existing methods in designing superior pocket sequences and structures, producing average improvement exceeding 10% in AAR and RMSD metrics. FAIR is available at https://***/zaixizhang/FAIR. © 2023, CC BY.

关键词： Atoms

来源：评论

学校读者我要写书评

暂无评论

Group Multi-View Transformer for 3D Shape analysis with Spatial Encoding

arXiv

引用

arXiv 2023年

作者： Xu, Lixiang Cui, Qingzhe Hong, Richang Xu, Wei Chen, Enhong Yuan, Xin Li, Chenglong Tang, Yuanyan The College of Artificial Intelligence and Big Data Hefei University Hefei230027 China The School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China The Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China Anhui Hefei230000 China The School of Electrical and Mechanical Engineering The University of Adelaide AdelaideSA5005 Australia The School of Artificial Intelligence Anhui University Hefei230601 China The Zhuhai UM Science and Technology Research Institute FST University of Macau China

In recent years, the results of view-based 3D shape recognition methods have saturated, and models with excellent performance cannot be deployed on memory-limited devices due to their huge size of parameters. To address this problem, we introduce a compression method based on knowledge distillation for this field, which largely reduces the number of parameters while preserving model performance as much as possible. Specifically, to enhance the capabilities of smaller models, we design a high-performing large model called Group Multi-view Vision Transformer (GMViT). In GMViT, the view-level ViT first establishes relationships between view-level features. Additionally, to capture deeper features, we employ the grouping module to enhance view-level features into group-level features. Finally, the group-level ViT aggregates group-level features into complete, well-formed 3D shape descriptors. Notably, in both ViTs, we introduce spatial encoding of camera coordinates as innovative position embeddings. Furthermore, we propose two compressed versions based on GMViT, namely GMViT-simple and GMViT-mini. To enhance the training effectiveness of the small models, we introduce a knowledge distillation method throughout the GMViT process, where the key outputs of each GMViT component serve as distillation targets. Extensive experiments demonstrate the efficacy of the proposed method. The large model GMViT achieves excellent 3D classification and retrieval results on the benchmark datasets ModelNet, ShapeNetCore55, and MCB. The smaller models, GMViT-simple and GMViT-mini, reduce the parameter size by 8 and 17.6 times, respectively, and improve shape recognition speed by 1.5 times on average, while preserving at least 90% of the classification and retrieval performance. The code is available at https://***/bigdatagraph/*** Codes 68 Copyright © 2023, The Authors. All rights reserved.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Group-Level Cognitive Diagnosis: A Multi-Task Learning Perspective

Group-Level Cognitive Diagnosis: A Multi-Task Learning Persp...

引用

IEEE International Conference on data Mining (ICDM)

作者： Jie Huang Qi Liu Fei Wang Zhenya Huang Songtao Fang Runze Wu Enhong Chen Yu Su Shijin Wang Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China Fuxi AI Lab NetEase Inc. Hangzhou China IFLYTEK Research

ISBN: (纸本)9781665423991

Most cognitive diagnosis research in education has been concentrated on individual assessment, aiming at discovering the latent characteristics of students. However, in many real-world scenarios, group-level assessment is an important and meaningful task, e.g., class assessment in different regions can discover the difference of teaching level in different contexts. In this work, we consider assessing cognitive ability for a group of students, which aims to mine groups’ proficiency on specific knowledge concepts. The significant challenge in this task is the sparsity of group-exercise response data, which seriously affects the assessment performance. Existing works either do not make effective use of additional student-exercise response data or fail to reasonably model the relationship between group ability and individual ability in different learning contexts, resulting in sub-optimal diagnosis results. To this end, we propose a general Multi-Task based Group-Level Cognitive Diagnosis (MGCD) framework, which is featured with three special designs: 1) We jointly model student-exercise responses and group-exercise responses in a multi-task manner to alleviate the sparsity of group-exercise responses; 2) We design a context-aware attention network to model the relationship between student knowledge state and group knowledge state in different contexts; 3) We model an interpretable cognitive layer to obtain student ability, group ability and exercise factors (e.g., difficulty), and then we leverage neural networks to learn complex interaction functions among them. Extensive experiments on real-world datasets demonstrate the generality of MGCD and the effectiveness of our attention design and multi-task learning.

关键词： Knowledge engineering Conferences Education Neural networks Multitasking data models data mining

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：