检索结果-内蒙古大学图书馆

2023 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2023

作者： Zhang, Pengcheng Yu, Xiaohan Bai, Xiao Zheng, Jin Wu, Xiaoyu Gao, Yongsheng Beihang University School of Computer Science and Engineering State Key Laboratory of Software Development Environment Jiangxi Research Institute Beijing China Griffith University Institute for Integrated and Intelligent Systems Nathan4111 Australia

ISBN: (纸本)9798350382204

Recent advance in ultra-fine-grained visual categorization (ultra-FGVC) has significantly boosted the capability of deep neural networks for ultra-FGVC tasks. However, building models for continually learning to recognize increasing ultra-fine-grained categories is still under-explored. This limits the application of ultra-FGVC techniques in real-world production. To this, we take the first attempt for continual ultra-FGVC. By evaluating existing continual learning methods on the constructed continual ultra-FGVC benchmark, we observe that the main bottleneck lies in the limited model plasticity for incrementally adapting to new tasks. This can be caused by excessive anti-forgetting constraints as the difficult ultra-FGVC task requires substantial update of parameters, and over-fitting on early tasks given that the ultra-fine-grained categories are with very few training samples. To tackle these problems, we propose a joint self-supervised learning and prompting model. The prompt-based continual learning framework offers proper anti-forgetting operation by fixed pretrained vision transformer and adaptive prompt selection. By jointly optimizing the learnable prompts with an adversarial self-supervised loss, the over-fitting on each continual learning task is mitigated. Extensive experiments demonstrate that the proposed method outperforms existing continual learning methods on the challenging continual ultra-FGVC problem. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Understanding Heterophily for Graph Neural Networks 41

Understanding Heterophily for Graph Neural Networks

引用

41st International Conference on Machine Learning, ICML 2024

作者： Wang, Junfu Guo, Yuanfang Yang, Liang Wang, Yunhong State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China Shen Yuan Honors College Beihang University Beijing China School of Artificial Intelligence Hebei University of Technology Tianjin China

Graphs with heterophily have been regarded as challenging scenarios for Graph Neural Networks (GNNs), where nodes are connected with dissimilar neighbors through various patterns. In this paper, we present theoretical understandings of heterophily for GNNs by incorporating the graph convolution (GC) operations into fully connected networks via the proposed Heterophilous Stochastic Block Models (HSBM), a general random graph model that can accommodate diverse heterophily patterns. Our theoretical investigation comprehensively analyze the impact of heterophily from three critical aspects. Firstly, for the impact of different heterophily patterns, we show that the separability gains are determined by two factors, i.e., the Euclidean distance of the neighborhood distributions and pE [deg], where E [deg] is the averaged node degree. Secondly, we show that the neighborhood inconsistency has a detrimental impact on separability, which is similar to degrading E [deg] by a specific factor. Finally, for the impact of stacking multiple layers, we show that the separability gains are determined by the normalized distance of the lpowered neighborhood distributions, indicating that nodes still possess separability in various regimes, even when over-smoothing occurs. Extensive experiments on both synthetic and real-world data verify the effectiveness of our theory. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

CLGT: A Graph Transformer for Student Performance Prediction in Collab.rative Learning 37

CLGT: A Graph Transformer for Student Performance Prediction...

引用

37th AAAI Conference on Artificial Intelligence, AAAI 2023

作者： Peng, Tianhao Liang, Yu Wu, Wenjun Ren, Jian Pengrui, Zhao Pu, Yanjun State Key Laboratory of Software Development Environment Beihang University China School of Computer Science and Engineering Beihang University China Beijing Engineering Research Center for IoT Software and Systems Beijing University of Technology China Institute of Artificial Intelligence Beihang University China

ISBN: (纸本)9781577358800

Modeling and predicting the performance of students in collab.rative learning paradigms is an important task. Most of the research presented in literature regarding collab.rative learning focuses on the discussion forums and social learning networks. There are only a few works that investigate how students interact with each other in team projects and how such interactions affect their academic performance. In order to bridge this gap, we choose a software engineering course as the study subject. The students who participate in a software engineering course are required to team up and complete a software project together. In this work, we construct an interaction graph based on the activities of students grouped in various teams. Based on this student interaction graph, we present an extended graph transformer framework for collab.rative learning (CLGT) for evaluating and predicting the performance of students. Moreover, the proposed CLGT contains an interpretation module that explains the prediction results and visualizes the student interaction patterns. The experimental results confirm that the proposed CLGT outperforms the baseline models in terms of performing predictions based on the real-world datasets. Moreover, the proposed CLGT differentiates the students with poor performance in the collab.rative learning paradigm and gives teachers early warnings, so that appropriate assistance can be provided. Copyright © 2023, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

The Power of Age-based Reward in Fresh Information Acquisition 42

The Power of Age-based Reward in Fresh Information Acquisiti...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Wang, Zhiyuan Meng, Qingkai Zhang, Shan Luo, Hongbin Beihang University School of Computer Science and Engineering Beijing China Beihang University State Key Laboratory of Virtual Reality Technology and Systems China Beihang University Institute of Artificial Intelligence Beijing China State Key Laboratory of Software Development Environment China

ISBN: (纸本)9798350334142

Many Internet platforms collect fresh information of various points of interest (PoIs) relying on users who happen to be nearby the PoIs. The platform will offer reward to incentivize users and compensate their costs incurred from information acquisition. In practice, the user cost (and its distribution) is hidden to the platform, thus it is challenging to determine the optimal reward. In this paper, we investigate how the platform dynamically rewards the users, aiming to jointly reduce the age of information (AoI) and the operational expenditure (OpEx). Due to the hidden cost distribution, this is an online non-convex learning problem with partial feedback. To overcome the challenge, we first design an age-based rewarding scheme, which decouples the OpEx from the unknown cost distribution and enables the platform to accurately control its OpEx. We then take advantage of the age-based rewarding scheme and propose an exponentially discretizing and learning (EDAL) policy for platform operation. We prove that the EDAL policy performs asymptotically as well as the optimal decision (derived based on the cost distribution). Simulation results show that the age-based rewarding scheme protects the platform's OpEx from the influence of the user characteristics, and verify the asymptotic optimality of the EDAL policy. © 2023 IEEE.

关键词： Simulation platform

来源：评论

学校读者我要写书评

暂无评论

Towards better dynamic graph learning: new architecture and unified library 23

Towards better dynamic graph learning: new architecture and ...

引用

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

作者： Le Yu Leilei Sun Bowen Du Weifeng Lv State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University

We propose DyGFormer, a new Transformer-based architecture for dynamic graph learning. DyGFormer is conceptually simple and only needs to learn from nodes' historical first-hop interactions by: (i) a neighbor co-occurrence encoding scheme that explores the correlations of the source node and destination node based on their historical sequences; (ii) a patching technique that divides each sequence into multiple patches and feeds them to Transformer, allowing the model to effectively and efficiently benefit from longer histories. We also introduce DyGLib, a unified library with standard training pipelines, extensible coding interfaces, and comprehensive evaluating protocols to promote reproducible, scalab.e, and credible dynamic graph learning research. By performing exhaustive experiments on thirteen datasets for dynamic link prediction and dynamic node classification tasks, we find that DyGFormer achieves state-of-the-art performance on most of the datasets, demonstrating its effectiveness in capturing nodes' correlations and long-term temporal dependencies. Moreover, some results of baselines are inconsistent with previous reports, which may be caused by their diverse but less rigorous implementations, showing the importance of DyGLib. All the used resources are publicly availab.e at https://***/yule-BUAA/DyGLib.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Permutation Invariant Training for Paraphrase Identification 48

Permutation Invariant Training for Paraphrase Identification

引用

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

作者： Bai, Jun Yin, Chuantao Hong, Hanhua Zhang, Jianfei Li, Chen Wang, Yanmeng Rong, Wenge Beihang University State Key Laboratory of Software Development Environment Beijing China Beihang University School of Computer Science and Engineering Beijing China Beihang University Sino-French Engineer School Beijing China Ping An Technology Beijing China

ISBN: (纸本)9781728163277

Identifying sentences sharing similar meanings is crucial to speech and text understandings. Although currently popular cross-encoder solutions with pre-trained language models as backbone have achieved remarkable performance, they suffer from the lack of the permutation invariance or symmetry that is one of the most important inductive biases to such task. To alleviate this issue, in this research we propose a permutation invariant training framework, in which a symmetry regularization is introduced during training that forces the model to produce the same predictions for input sentence pairs in both forward and backward directions. Empirical studies exhibit improved performance over competitive baselines. © 2023 IEEE.

关键词： Paraphrase Identification Permutation Invariance Symmetry Regularization

来源：评论

学校读者我要写书评

暂无评论

WasmFuzzer: A Fuzzer for WebAssembly Virtual Machines 34

WasmFuzzer: A Fuzzer for WebAssembly Virtual Machines

引用

34th International Conference on software engineering and Knowledge engineering, SEKE 2022

作者： Jiang, Bo Li, Zichao Huang, Yuhe Zhang, Zhenyu Chan, W.K. State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China Department of Computer Science City University of Hong Kong Hong Kong

ISBN: (纸本)1891706543

WebAssembly is a fast, safe, and portable low-level language suitable for diverse application scenarios. And The WebAssembly virtual machines are widely used by Web browsers or Blockchain platforms as execution engine. When there is a bug in the implementation of the Wasm virtual machine, the execution of WebAssembly may lead to errors or vulnerability in the application. Due to the grammar checks by WASM VMs, fuzzing at the binary level is ineffective to expose the bugs because most inputs cannot reach the deep logic within the WASM VM. In this work, we propose WasmFuzzer, a bytecode level fuzzing tool for WASM VMs. WasmFuzzer proposes to generate initial seeds for Fuzzing at the Wasm bytecode level and it also designs a systematic set of mutation operators for Wasm bytecode. Furthermore, WasmFuzzer proposes an adaptive mutation strategy to search for the best mutation operators for different fuzzing targets. Our evaluation on 3 real-life Wasm VMs shows that WasmFuzzer can significantly outperform AFL in terms of both code coverage and unique crash. © 2022 Knowledge Systems Institute Graduate school. All rights reserved.

关键词： Web browsers

来源：评论

学校读者我要写书评

暂无评论

SWin: A Set-Window Division Mechanism to Alleviate I/O Jitters of NVMe SSD Drives 24

SWin: A Set-Window Division Mechanism to Alleviate I/O Jitte...

引用

24th IEEE International Conference on High Performance Computing and Communications, 8th IEEE International Conference on Data science and Systems, 20th IEEE International Conference on Smart City and 8th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Application, HPCC/DSS/SmartCity/DependSys 2022

作者： Liu, Yuting Wang, Liang Zhu, Jinbin Shen, Runnan Jiang, Shixuan Xiao, Limin Beihang University State Key Laboratory of Software Development Environment Beijing100191 China School of Computer Science and Engineering Beihang University Beijing100191 China

ISBN: (纸本)9798350319934

NVMe SSDs increase the performance of I/O system significantly, but they still suffer from the problem of performance jitters. Although existing studies adopt optimized GC or schedulers to make up for the vulnerabilities, they cannot provide a near 'GC-free' performance under various scenarios. In this paper, we propose SWin, a Set-Window division mechanism to alleviate I/O jitters of NVMe SSDs, in which we build an optimized scheduler with cache management on sets. First, we first divide NVMe SSD into set level and determine time windows based on sets. Then, an efficient I/O scheduler is designed to process requests of applications. Finally, we develop a host cache management strategy to ensure a stable response time for I/O requests. The experimental results indicate that the OCSSD system integrated with SWin can gain performance improvement by 32%, 34% and 14% in completion time, IOPS and latency performance, respectively. © 2022 IEEE.

关键词： Jitter

来源：评论

学校读者我要写书评

暂无评论

Optimizing Link-Identified Forwarding Framework in LEO Satellite Networks 21

Optimizing Link-Identified Forwarding Framework in LEO Satel...

引用

21st International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks, WiOpt 2023

作者： Zhang, Hefan Wang, Zhiyuan Zhang, Shan Meng, Qingkai Luo, Hongbin School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China Institute of Artificial Intelligence Beihang University Beijing China State Key Laboratory of Software Development Environment China State Key Laboratory of Virtual Reality Technology and Systems China

ISBN: (纸本)9783903176553

Low earth orbit (LEO) satellite networks have the potential to provide low-latency communication with global coverage. To unleash this potential, it is crucial to achieve efficient data delivery. In this paper, we analyze the topology characteristics of LEO satellite networks, and propose a source-route-style forwarding framework. Specifically, we leverage the deterministic neighbor relationship and identify all the unidirectional inter-satellite links (ISLs). Moreover, our framework utilizes the in-packet bloom filter (BF) to store the source-route-style forwarding information. This way, the source satellite could encode multiple ISL identifiers into the BF, which actually specifies the forwarding path. The intermediate satellites only need to check whether the outgoing ISLs are encoded and forward packets accordingly. Due to false positives caused by BF, the more ISLs are encoded at a time, the more redundant forwardings emerge. To reduce forwarding overhead, we take into account segment encoding, allowing the source and intermediate satellites to encode part of ISLs towards the destination. Overall, segment encoding seeks the right balance between forwarding overhead and encoding delay. We characterize a wide range of segment encoding policy in a unified framework, and derive the expected forwarding overhead in a closed-form. The segment encoding design is formulated as a binary non-linear programming, which is NP-hard. To overcome the challenge, we leverage its decomposable structure, and propose an efficient algorithm to solve it optimally. Finally, we validate our analytical results via packet-level experiments. Results also show that our proposed segment encoding policy significantly reduces the queuing delay compared to source encoding. © 2023 IFIP.

关键词： Satellites

来源：评论

学校读者我要写书评

暂无评论

Towards Better Dynamic Graph Learning: New Architecture and Unified Library

arXiv

引用

arXiv 2023年

作者： Yu, Le Sun, Leilei Du, Bowen Lv, Weifeng State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University China

We propose DyGFormer, a new Transformer-based architecture for dynamic graph learning. DyGFormer is conceptually simple and only needs to learn from nodes’ historical first-hop interactions by: (i) a neighbor co-occurrence encoding scheme that explores the correlations of the source node and destination node based on their historical sequences;(ii) a patching technique that divides each sequence into multiple patches and feeds them to Transformer, allowing the model to effectively and efficiently benefit from longer histories. We also introduce DyGLib, a unified library with standard training pipelines, extensible coding interfaces, and comprehensive evaluating protocols to promote reproducible, scalab.e, and credible dynamic graph learning research. By performing exhaustive experiments on thirteen datasets for dynamic link prediction and dynamic node classification tasks, we find that DyGFormer achieves state-of-the-art performance on most of the datasets, demonstrating its effectiveness in capturing nodes’ correlations and long-term temporal dependencies. Moreover, some results of baselines are inconsistent with previous reports, which may be caused by their diverse but less rigorous implementations, showing the importance of DyGLib. All the used resources are publicly availab.e at https://***/yule-BUAA/DyGLib. Copyright © 2023, The Authors. All rights reserved.

关键词： Memory architecture

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：