检索结果-内蒙古大学图书馆

The Dataflow Runtime Environment of DFC 1

学校读者我要写书评

暂无评论

21st International Conference on Parallel and Distributed Computing, Applications, and Technologies, PDCAT 2020

作者： Zhang, Jing Li, Jinrong Du, Zheng Shu, Jiwu Luo, Qiuming NHPCC/Guangdong Key Laboratory of Popular HPC College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (数字)9783030692445

ISBN: (纸本)9783030692438

In this paper, we introduce the DFC dataflow language and its runtime environment. DFC runtime library is in charge of constructing the DAG of the dataflow graph, firing the DFC tasks and the synchronizations between the tasks of successive passes. Basing on an elaborately implemented thread pool and queued Active Data, DFC runtime shows an ideal performance comparing with DSPatch. The experiment of a simple dataflow graph shows that DFC has better performance for the cases that the parallelism beneath the core number, while DSPatch shows a better scalability for the cases of the parallelism exceed the core number. As DFC is still a prototype language, it lacks the ability to construct the DAG dynamically, which leads to low efficiency when coding for a well-structured dataflow graph. © 2021, Springer Nature Switzerland AG.

关键词： Data flow analysis

FastVDT: Fast Transformer With Optimised Attention Masks and Positional Encoding for Visual Dialogue

学校读者我要写书评

暂无评论

IET computer Vision 2025年第1期19卷

作者： He, Qiangqiang Qian, Shuwei Wang, Chongjun State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science and Technology Nanjing University Nanjing China

The visual dialogue task requires computers to comprehend image content and preceding question-and-answer history to accurately answer related questions, with each round of dialogue providing the necessary historical context for subsequent interactions. Existing research typically processes multiple questions related to a single image as independent samples, which results in redundant modelling of the images and their captions and substantially increases computational costs. To address the challenges above, we introduce a fast transformer for visual dialogue, termed FastVDT, which utilises novel attention masks and continuous positional encoding. FastVDT models multiple image-related questions as an integrated entity, accurately processing prior conversation history in each dialogue round while predicting answers to multiple questions. Our method effectively captures the interrelations among questions and significantly reduces computational overhead. Experimental results demonstrate that our method delivers outstanding performance on the VisDial v0.9 and v1.0 datasets. FastVDT achieves comparable performance to VD-BERT and VU-BERT while reducing computational costs by 80% and 56%, respectively. © 2025 The Author(s). IET computer Vision published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and technology.

关键词： Natural language processing systems

The Compiler of DFC: A Source Code Converter that Transform the Dataflow Code to the Multi-threaded C Code 1

学校读者我要写书评

暂无评论

21st International Conference on Parallel and Distributed Computing, Applications, and Technologies, PDCAT 2020

作者： Du, Zheng Zhang, Jing Li, Jinrong Du, Haixin Shu, Jiwu Luo, Qiuming Department of Computer Science and Technology Tsinghua University Beijing China NHPCC/Guangdong Key Laboratory of Popular HPC College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (数字)9783030692445

ISBN: (纸本)9783030692438

The working principle of DFC compiler is introduced in this article. DFC is a grammatical extension of standard C language, with special DF function which describe the dependence of computing DAG. DFC compiler, dfcc, is used to convert the DFC source codes to standard C codes with the assistance of multi-threaded library. The lexical rules and grammatical rules are used to setup the AST of DFC codes, and then it is converted to the AST of standard C without DF function nodes. The derived AST is printed into a text file, a normal C file, and finally is processed by GCC to obtain the executable file. The experiment gives some demonstration of that converting details, and the memory footprint is studied to show an ideal scalability. © 2021, Springer Nature Switzerland AG.

关键词： Program compilers

Multi-Agent Policy Transfer via Task Relationship Modeling

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Qin, Rongjun Chen, Feng Wang, Tonghan Yuan, Lei Wu, Xiaoran Zhang, Zongzhang Zhang, Chongjie Yu, Yang National Key Laboratory of Novel Software Technology Nanjing China Polixir Technologies Nanjing China IIIS Tsinghua University Beijing China Department of Computer Science and Technology Tsinghua University Beijing China

Team adaptation to new cooperative tasks is a hallmark of human intelligence, which has yet to be fully realized in learning agents. Previous work on multi-agent transfer learning accommodate teams of different sizes, heavily relying on the generalization ability of neural networks for adapting to unseen tasks. We believe that the relationship among tasks provides the key information for policy adaptation. In this paper, we try to discover and exploit common structures among tasks for more efficient transfer, and propose to learn effect-based task representations as a common space of tasks, using an alternatively fixed training scheme. We demonstrate that the task representation can capture the relationship among tasks, and can generalize to unseen tasks. As a result, the proposed method can help transfer learned cooperation knowledge to new tasks after training on a few source tasks. We also find that fine-tuning the transferred policies help solve tasks that are hard to learn from scratch. Copyright © 2022, The Authors. All rights reserved.

关键词： Multi agent systems

Homophily-enhanced Structure Learning for Graph Clustering

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Gu, Ming Yang, Gaoming Zhou, Sheng Ma, Ning Chen, Jiawei Tan, Qiaoyu Liu, Meihan Bu, Jiajun College of Computer Science and Technology Zhejiang University China School of Software Technology Zhejiang University China Zhejiang Provincial Key Laboratory of Service Robot Zhejiang University China Department of Computer Science New York University Shanghai China

Graph clustering is a fundamental task in graph analysis, and recent advances in utilizing graph neural networks (GNNs) have shown impressive results. Despite the success of existing GNN-based graph clustering methods, they often overlook the quality of graph structure, which is inherent in real-world graphs due to their sparse and multifarious nature, leading to subpar performance. Graph structure learning allows refining the input graph by adding missing links and removing spurious connections. However, previous endeavors in graph structure learning have predominantly centered around supervised settings, and cannot be directly applied to our specific clustering tasks due to the absence of ground-truth labels. To bridge the gap, we propose a novel method called homophily-enhanced structure learning for graph clustering (HoLe). Our motivation stems from the observation that subtly enhancing the degree of homophily within the graph structure can significantly improve GNNs and clustering outcomes. To realize this objective, we develop two clustering-oriented structure learning modules, i.e., hierarchical correlation estimation and cluster-aware sparsification. The former module enables a more accurate estimation of pairwise node relationships by leveraging guidance from latent and clustering spaces, while the latter one generates a sparsified structure based on the similarity matrix and clustering assignments. Additionally, we devise a joint optimization approach alternating between training the homophily-enhanced structure learning and GNN-based clustering, thereby enforcing their reciprocal effects. Extensive experiments on seven benchmark datasets of various types and scales, across a range of clustering metrics, demonstrate the superiority of HoLe against state-of-the-art baselines. Copyright © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

Linear uncertainty quantification of graphical model inference 24

学校读者我要写书评

暂无评论

Linear uncertainty quantification of graphical model inferen...

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Chenghua Guo Han Yu Jiaxin Liu Chao Chen Qi Li Sihong Xie Xi Zhang Key Laboratory of Trustworthy Distributed Computing and Service (MoE) Beijing University of Posts and Telecommunications China College of Artificial Intelligence Beijing University of Posts and Telecommunications China Department of Computer Science and Engineering Lehigh University School of Computer Science and Technology Harbin Institute of Technology (Shenzhen) China Department of Computer Science Iowa State University AI Thrust The Hong Kong University of Science and Technology (Guangzhou) China

ISBN: (纸本)9798331314385

Uncertainty Quantification (UQ) is vital for decision makers as it offers insights into the potential reliability of data and model, enabling more informed and risk-aware decision-making. Graphical models, capable of representing data with complex dependencies, are widely used across domains. Existing sampling-based UQ methods are unbiased but cannot guarantee convergence and are time-consuming on large-scale graphs. There are fast UQ methods for graphical models with closed-form solutions and convergence guarantee but with uncertainty underestimation. We propose LinUProp, a UQ method that utilizes a novel linear propagation of uncertainty to model uncertainty among related nodes additively instead of multiplicatively, to offer linear scalability, guaranteed convergence, and closed-form solutions without underestimating uncertainty. Theoretically, we decompose the expected prediction error of the graphical model and prove that the uncertainty computed by LinUProp is the generalized variance component of the decomposition. Experimentally, we demonstrate that LinUProp is consistent with the sampling-based method but with linear scalability and fast convergence. Moreover, LinUProp outperforms competitors in uncertainty-based active learning on four real-world graph datasets, achieving higher accuracy with a lower labeling budget.

关键词：

Segmentation Guided Sparse Transformer for Under-Display Camera Image Restoration

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xue, Jingyun Wang, Tao Wang, Jun Zhang, Kaihao Luo, Wenhan Ren, Wenqi Liu, Zikun Park, Hyunhee Cao, Xiaochun Shenzhen Campus of Sun Yat-Sen University Shenzhen China The Hong Kong University of Science and Technology Hong Kong Hong Kong The State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Beijing China The Harbin Institute of Technology Shenzhen China The Department of Camera Innovation Group Samsung Electronics Suwon16677 Korea Republic of

Under-Display Camera (UDC) is an emerging technology that achieves full-screen display via hiding the camera under the display panel. However, the current implementation of UDC causes serious degradation. The incident light required for camera imaging undergoes attenuation and diffraction when passing through the display panel, leading to various artifacts in UDC imaging. Presently, the prevailing UDC image restoration methods predominantly utilize convolutional neural network architectures, whereas Transformer-based methods have exhibited superior performance in the majority of image restoration tasks. This is attributed to the Transformer’s capability to sample global features for the local reconstruction of images, thereby achieving high-quality image restoration. In this paper, we observe that when using the Vision Transformer for UDC degraded image restoration, the global attention samples a large amount of redundant information and noise. Furthermore, compared to the ordinary Transformer employing dense attention, the Transformer utilizing sparse attention can alleviate the adverse impact of redundant information and noise. Building upon this discovery, we propose a Segmentation Guided Sparse Transformer method (SGSFormer) for the task of restoring high-quality images from UDC degraded images. Specifically, we utilize sparse self-attention to filter out redundant information and noise, directing the model’s attention to focus on the features more relevant to the degraded regions in need of reconstruction. Moreover, we integrate the instance segmentation map as prior information to guide the sparse self-attention in filtering and focusing on the correct regions. Experimental results on public datasets verify that the proposed method demonstrates positive performance in comparison to state-of-the-art approaches. Copyright © 2024, The Authors. All rights reserved.

关键词： Image reconstruction

Learning a Mini-batch Graph Transformer via Two-stage Interaction Augmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Wenda Chen, Kaixuan Liu, Shunyu Zheng, Tongya Huang, Wenjie Song, Mingli State Key Laboratory of Blockchain and Security Zhejiang University China School of Software Technology Zhejiang University China Institute of Blockchain and Data Security China Big Graph Center School of Computer and Computing Science Hangzhou City University China College of Computer Science and Technology Zhejiang University Hangzhou China

Mini-batch Graph Transformer (MGT), as an emerging graph learning model, has demonstrated significant advantages in semi-supervised node prediction tasks with improved computational efficiency and enhanced model robustness. However, existing methods for processing local information either rely on sampling or simple aggregation, which respectively result in the loss and squashing of critical neighbor information. Moreover, the limited number of nodes in each mini-batch restricts the model’s capacity to capture the global characteristic of the graph. In this paper, we propose LGMformer, a novel MGT model that employs a two-stage augmented interaction strategy, transitioning from local to global perspectives, to address the aforementioned bottlenecks. The local interaction augmentation (LIA) presents a neighbor-target interaction Transformer (NTIformer) to acquire an insightful understanding of the co-interaction patterns between neighbors and the target node, resulting in a locally effective token list that serves as input for the MGT. In contrast, global interaction augmentation (GIA) adopts a cross-attention mechanism to incorporate entire graph prototypes into the target node representation, thereby compensating for the global graph information to ensure a more comprehensive perception. To this end, LGMformer achieves the enhancement of node representations under the MGT paradigm. Experimental results related to node classification on the ten benchmark datasets demonstrate the effectiveness of the proposed method. Our code is available at https://***/l-wd/LGMformer. Copyright © 2024, The Authors. All rights reserved.

关键词： Computational efficiency

NEGAR: Network Embedding Guided Architecture Recovery for software Systems

学校读者我要写书评

暂无评论

NEGAR: Network Embedding Guided Architecture Recovery for So...

Asia-Pacific Conference on software Engineering

作者： Jiayi Chen Zhixing Wang Yuchen Jiang Jun Pang Tian Zhang Minxue Pan Jianwen Sun State Key Lab for Novel Software Technology Nanjing University Nanjing China Department of Computer Science University of Luxembourg Esch-sur-Alzette Luxembourg Huawei Technologies Software Engineering Application Technology Lab Shenzhen China

ISBN: (纸本)9781665455381

With their rapid development, the scale and complexity of software systems are rapidly growing. Identifying and organizing files of similar functionality into the same module, called architecture recovery, contributes to the maintainability of a software system. However, manual architecture recovery on large-sized software requires unbearable costs. Hence a lot of automatic algorithms have been proposed in recent years. However, current algorithms’ accuracy is still insufficient to support practical applications. To improve the accuracy of architecture recovery, this work proposes a novel algorithm, NEGAR, which leverages random walks to extract latent graphic information from the dependency graph of files in the software system and learn the node representation for clustering. The proposed algorithm NEGAR has been comprehensively evaluated on three medium-sized and two large-sized software systems, as well as a super large-sized software system, in terms of four widely-used metrics. The experimental results demonstrate the outstanding accuracy and excellent scalability of NEGAR.

关键词： Measurement Codes Scalability software algorithms Semantics Clustering algorithms computer architecture