检索结果-内蒙古大学图书馆

ROD: Reception-aware online distillation for sparse graphs

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Wentao Jiang, Yuezihan Li, Yang Sheng, Zeang Shen, Yu Miao, Xupeng Wang, Liang Yang, Zhi Cui, Bin School of EECS Key Laboratory of High Confidence Software Technologies Peking University Center for Data Science Peking University National Engineering Laboratory for Big Data Analysis and Applications Alibaba Group

Graph neural networks (GNNs) have been widely used in many graph-based tasks such as node classification, link prediction, and node clustering. However, GNNs gain their performance benefits mainly from performing the feature propagation and smoothing across the edges of the graph, thus requiring sufficient connectivity and label information for effective propagation. Unfortunately, many real-world networks are sparse in terms of both edges and labels, leading to sub-optimal performance of GNNs. Recent interest in this sparse problem has focused on the self-training approach, which expands supervised signals with pseudo labels. Nevertheless, the self-training approach inherently cannot realize the full potential of refining the learning performance on sparse graphs due to the unsatisfactory quality and quantity of pseudo labels. In this paper, we propose ROD, a novel reception-aware online knowledge distillation approach for sparse graph learning. We design three supervision signals for ROD: multi-scale reception-aware graph knowledge, task-based supervision, and rich distilled knowledge, allowing online knowledge transfer in a peer-teaching manner. To extract knowledge concealed in the multi-scale reception fields, ROD explicitly requires individual student models to preserve different levels of locality information. For a given task, each student would predict based on its reception-scale knowledge, while simultaneously a strong teacher is established on-the-fly by combining multi-scale knowledge. Our approach has been extensively evaluated on 9 datasets and a variety of graph-based tasks, including node classification, link prediction, and node clustering. The result demonstrates that ROD achieves state-of-art performance and is more robust for the graph sparsity. Copyright © 2021, The Authors. All rights reserved.

关键词： Graphic methods

Grain: Improving data efficiency of graph neural networks via diversified influence maximization

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Wentao Yang, Zhi Wang, Yexin Shen, Yu Li, Yang Wang, Liang Cui, Bin School of EECS Key Laboratory of High Confidence Software Technologies Peking University Tencent Inc Center for Data Science Peking University National Engineering Laboratory for Big Data Analysis and Applications

data selection methods, such as active learning and core-set selection, are useful tools for improving the data efficiency of deep learning models on large-scale datasets. However, recent deep learning models have moved forward from independent and identically distributed data to graph-structured data, such as social networks, e-commerce user-item graphs, and knowledge graphs. This evolution has led to the emergence of Graph Neural Networks (GNNs) that go beyond the models existing data selection methods are designed for. Therefore, we present Grain, an efficient framework that opens up a new perspective through connecting data selection in GNNs with social influence maximization. By exploiting the common patterns of GNNs, Grain introduces a novel feature propagation concept, a diversified influence maximization objective with novel influence and diversity functions, and a greedy algorithm with an approximation guarantee into a unified framework. Empirical studies on public datasets demonstrate that Grain significantly improves both the performance and efficiency of data selection (including active learning and core-set selection) for GNNs. To the best of our knowledge, this is the first attempt to bridge two largely parallel threads of research, data selection, and social influence maximization, in the setting of GNNs, paving new ways for improving data efficiency. Copyright © 2021, The Authors. All rights reserved.

关键词： data reduction

Optimization analysis of online marketing strategy based on the regression prediction model 2

学校读者我要写书评

暂无评论

Optimization analysis of online marketing strategy based on ...

2020 2nd International Conference on Advances in Civil engineering, Energy Resources and Environment engineering, ACCESE 2020

作者： Yang, Jingya Xiao, Xiwang Zhang, Xianfeng Wen, Bin Zhang, Yuehua Guan, Jinqiu Li, Lan College of Science and Mechanical Engineering Jiamusi University Jiamusi City Heilongjiang Province154007 China College of Big Data and Software Engineering Wuzhou University Wuzhou City Guangxi Province543000 China

In response to the three new product sales recommendations of the Amazon online market "Sunshine", based on the data set provided by the enterprise data center, the data in the NLP feature package is preprocessed in Python, and the AHP model is established to measure and establish the data. This experiment according to the quarterly time series ARIMA model to forecast the product sales, and then through the standardization of OLS regression model to predict the trend of the development of products. The results showed that customer text reviews were an important reference for the sunshine company and found that microwave oven sales increased by an average of 6.28%, while sales of baby pacifiers and hair dryers increased by an average of 1.02%. This experiment based on this, puts forward the corresponding marketing strategy. Online marketing strategy can pay more attention to the customer's comments, make updates on the features of the product, the use of to meet customer demand. The study enriches the existing research results, and the sun of the company's sales strategy provides feasibility suggestions, thus has important theoretical significance and practical value. © Published under licence by IOP Publishing Ltd.

关键词： Sales

FlagVNE: A Flexible and Generalizable Reinforcement Learning Framework for Network Resource Allocation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Tianfu Fan, Qilin Wang, Chao Yang, Long Ding, Leilei Yuan, Nicholas Jing Xiong, Hui School of Computer Science and Technology University of Science and Technology of China China School of Big Data and Software Engineering Chongqing University China Guangzhou HKUST Fok Ying Tung Research Institute China School of Artificial Intelligence Peking University China Thrust of Artificial Intelligence The Hong Kong University of Science and Technology Guangzhou China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Hong Kong

Virtual network embedding (VNE) is an essential resource allocation task in network virtualization, aiming to map virtual network requests (VNRs) onto physical infrastructure. Reinforcement learning (RL) has recently emerged as a promising solution to this problem. However, existing RL-based VNE methods are limited by the unidirectional action design and one-size-fits-all training strategy, resulting in restricted searchability and generalizability. In this paper, we propose a FLexible And Generalizable RL framework for VNE, named FlagVNE. Specifically, we design a bidirectional action-based Markov decision process model that enables the joint selection of virtual and physical nodes, thus improving the exploration flexibility of solution space. To tackle the expansive and dynamic action space, we design a hierarchical decoder to generate adaptive action probability distributions and ensure high training efficiency. Furthermore, to overcome the generalization issue for varying VNR sizes, we propose a meta-RL-based training method with a curriculum scheduling strategy, facilitating specialized policy training for each VNR size. Finally, extensive experimental results show the effectiveness of FlagVNE across multiple key metrics. Our code is available at GitHub1 Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

Motif Channel Opened in a White-Box: Stereo Matching via Motif Correlation Graph

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Ziyang Zhang, Yongjun Li, Wenting Wang, Bingshu Zhao, Yong Chen, C.L. Philip College of Computer Science the State Key Laboratory of Public Big Data Guizhou University Guiyang550025 China School of Information Engineering Guizhou University of Commerce Guiyang550021 China School of Software Northwestern Polytechnical University Xi’an710129 China Key Laboratory of Integrated Microsystems Shenzhen Graduate School Peking University Shenzhen518055 China School of Computer Science and Engineering South China University of Technology Guangzhou510641 China

Real-world applications of stereo matching, such as autonomous driving, place stringent demands on both safety and accuracy. However, learning-based stereo matching methods inherently suffer from the loss of geometric structures in certain feature channels, creating a bottleneck in achieving precise detail matching. Additionally, these methods lack interpretability due to the black-box nature of deep learning. In this paper, we propose MoCha-V2, a novel learning-based paradigm for stereo matching. MoCha-V2 introduces the Motif Correlation Graph (MCG) to capture recurring textures, which are referred to as "motifs" within feature channels. These motifs reconstruct geometric structures and are learned in a more interpretable way. Subsequently, we integrate features from multiple frequency domains through wavelet inverse transformation. The resulting motif features are utilized to restore geometric structures in the stereo matching process. Experimental results demonstrate the effectiveness of MoCha-V2. MoCha-V2 achieved 1st place on the Middlebury benchmark at the time of its release. Code is available at here. Copyright © 2024, The Authors. All rights reserved.

关键词： Stereocenters

Connecting latent relationships over heterogeneous attributed network for recommendation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Duan, Ziheng Wang, Yueyang Ye, Weihao Feng, Zixuan Fan, Qilin Li, Xiuhua School of Big Data and Software Engineering Chongqing University Chongqing401331 China Department of Control Science and Technology Zhejiang University Hangzhou310027 China

Recently, deep neural network models for graph-structured data have been demonstrating to be influential in recommendation systems. Graph Neural Network (GNN), which can generate high-quality embeddings by capturing graph-structured information, is convenient for the recommendation. However, most existing GNN models mainly focus on the homogeneous graph. They cannot characterize heterogeneous and complex data in the recommendation system. Meanwhile, it is challenging to develop effective methods to mine the heterogeneity and latent correlations in the graph. In this paper, we adopt Heterogeneous Attributed Network (HAN), which involves different node types as well as rich node attributes, to model data in the recommendation system. Furthermore, we propose a novel graph neural network-based model to deal with HAN for Recommendation, called HANRec. In particular, we design a component connecting potential neighbors to explore the influence between neighbors and provide two different strategies with the attention mechanism to aggregate neighbors’ information. The experimental results on two real-world datasets prove that HANRec outperforms other state-of-the-arts methods1 Copyright © 2021, The Authors. All rights reserved.

关键词： Graph neural networks

Decoupled Prototype Learning for Reliable Test-Time Adaptation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Guowei Ding, Changxing Tan, Wentao Tan, Mingkui the School of Electronic and Information Engineering South China University of Technology 381 Wushan Road Tianhe District Guangzhou510000 China the Pazhou Lab Guangzhou510330 China the School of Future Technology South China University of Technology 381 Wushan Road Tianhe District Guangzhou510000 China the School of Software Engineering the Key Laboratory of Big Data and Intelligent Robot Ministry of Education South China University of Technology Guangzhou510006 China

Test-time adaptation (TTA) is a task that continually adapts a pre-trained source model to the target domain during inference. One popular approach involves fine-tuning model with cross-entropy loss according to estimated pseudo-labels. However, its performance is significantly affected by noisy pseudo-labels. This study reveals that minimizing the classification error of each sample causes the cross-entropy loss’s vulnerability to label noise. To address this issue, we propose a novel Decoupled Prototype Learning (DPL) method that features prototype-centric loss computation. First, we decouple the optimization of class prototypes. For each class prototype, we reduce its distance with positive samples and enlarge its distance with negative samples in a contrastive manner. This strategy prevents the model from overfitting to noisy pseudo-labels. Second, we propose a memory-based strategy to enhance DPL’s robustness for the small batch sizes often encountered in TTA. We update each class’s pseudo-feature from a memory in a momentum manner and insert an additional DPL loss. Finally, we introduce a consistency regularization-based approach to leverage samples with unconfident pseudo-labels. This approach transfers feature styles of samples with unconfident pseudo-labels to those with confident pseudo-labels. Thus, more reliable samples for TTA are created. The experimental results demonstrate that our methods achieve state-of-the-art performance on domain generalization benchmarks, and reliably improve the performance of self-training-based methods on image corruption benchmarks. The code will be released. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

Semi-Supervised Learning For Signal Recognition With Sparsity And Robust Promotion

学校读者我要写书评

暂无评论

Semi-Supervised Learning For Signal Recognition With Sparsit...

IEEE Conference on Wireless Communications and Networking

作者： Yihong Dong Xiaohan Jiang Lei Cheng Qingjiang Shi School of Software Engineering Tongji University Shanghai China Shenzhen Research Institute of Big Data Shenzhen Guangdong P. R. China

Due to the emergence of deep learning, signal recognition has made great strides in performance improvement. The success of most deep learning methods relies on the accessibility of abundant labelled training data. However, the annotation of signals is quite expensive, making it challenging to train deep learning models substantially. This calls for the development of semi-supervised learning (SSL) method to fully utilize the unlabelled data to assist the training of deep learning models. To achieve this goal, three types of loss function tailored to the task of signal recognition are carefully designed in this paper. Together with the novel design of neural network structure, the proposed SSL method can effectively extract the information from unlabelled training data and thus overcome the difficulty of insufficient training. Extensive numerical results using real-world signal datasets are presented to show the remarkable performance of the proposed SSL method.

关键词： Deep learning Training Knowledge engineering Neural networks Training data Pattern classification Semisupervised learning

Code-Aware Fault Localization with Pre-Training and Interpretable Machine Learning

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Zhang, Zhuo Li, Ya Yang, Sha Zhang, Zhanjun Lei, Yan School of Information Technology and Engineering Guangzhou College of Commerce Guangzhou China Ningbo Artificial Intelligence Institute Shanghai Jiaotong University Ningbo China College of Computer National University of Defense Technology Changsha China School of Big Data and Software Engineering Chongqing University Chongqing China

Following the rapid development of deep learning, many studies in the field of fault localization (FL) have utilized deep learning to analyze statements coverage information (i.e., executed or not executed) and test cases' results (i.e., failing or passing), which have shown dramatic ability in identifying suspicious statements potentially responsible for failures. However, they mainly pay attention to the binary information of executing test cases but ignore incorporating code snippets and their inner relationships into the learning process. Furthermore, how a complex deep learning model for FL achieves a particular decision is not transparent. These drawbacks may limit the effectiveness of FL. Recently, graph-based pre-training techniques have dramatically improved the state-of-the-art in a variety of code-related tasks such as natural language code search, clone detection, code translation, code refinement, etc. And interpretable machine learning tackles the problem of non-transparency and enables learning models to explain or present their behaviours to humans in an understandable *** this paper, our insight is to select a candidate solution that leverages the promising learning ability of graph-based pre-training techniques to learn a feasible model for incorporating code snippets as well as their inner relationships into fault localization, and then uses interpretable machine learning to localize faulty statements. Thus, we propose CodeAwareFL, a code-aware fault localization technique with pre-training and interpretable machine learning. Concretely, CodeAwareFL constructs a variety of code snippets through executing test cases. Next, CodeAwareFL utilizes the code snippets to extract propagation chains which could show a set of variables interact with each other to cause a failure. After that, a graph-based pre-trained model is customized for fault localization. CodeAwareFL takes the code snippets and their corresponding propagation chains as inputs with te

关键词： Deep learning