检索结果-内蒙古大学图书馆

Rethinking Propagation for Unsupervised Graph Domain Adaptation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Meihan Fang, Zeyu Zhang, Zhen Gu, Ming Zhou, Sheng Wang, Xin Bu, Jiajun Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University China School of Software Technology Zhejiang University China Department of Computer Science National University of Singapore Singapore Department of Computer Science and Technology Tsinghua University China

Unsupervised Graph Domain Adaptation (UGDA) aims to transfer knowledge from a labelled source graph to an unlabelled target graph in order to address the distribution shifts between graph domains. Previous works have primarily focused on aligning data from the source and target graph in the representation space learned by graph neural networks (GNNs). However, the inherent generalization capability of GNNs has been largely overlooked. Motivated by our empirical analysis, we reevaluate the role of GNNs in graph domain adaptation and uncover the pivotal role of the propagation process in GNNs for adapting to different graph domains. We provide a comprehensive theoretical analysis of UGDA and derive a generalization bound for multi-layer GNNs. By formulating GNN Lipschitz for k-layer GNNs, we show that the target risk bound can be tighter by removing propagation layers in source graph and stacking multiple propagation layers in target graph. Based on the empirical and theoretical analysis mentioned above, we propose a simple yet effective approach called A2GNN for graph domain adaptation. Through extensive experiments on real-world datasets, we demonstrate the effectiveness of our proposed A2GNN framework. © 2024, CC BY.

关键词： Graph neural networks

CPDG: A Contrastive Pre-Training Method for Dynamic Graph Neural Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Bei, Yuanchen Xu, Hao Zhou, Sheng Chi, Huixuan Wang, Haishuai Zhang, Mengdi Li, Zhao Bu, Jiajun Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science and Technology Zhejiang University China Meituan China School of Software Technology Zhejiang University China Institute of Computing Technology Chinese Academy of Science China

Dynamic graph data mining has gained popularity in recent years due to the rich information contained in dynamic graphs and their widespread use in the real world. Despite the advances in dynamic graph neural networks (DGNNs), the rich information and diverse downstream tasks have posed significant difficulties for the practical application of DGNNs in industrial scenarios. To this end, in this paper, we propose to address them by pre-training and present the Contrastive Pre-Training Method for Dynamic Graph Neural Networks (CPDG). CPDG tackles the challenges of pre-training for DGNNs, including generalization capability and long-short term modeling capability, through a flexible structural-temporal subgraph sampler along with structural-temporal contrastive pre-training schemes. Extensive experiments conducted on both large-scale research and industrial dynamic graph datasets show that CPDG outperforms existing methods in dynamic graph pre-training for various downstream tasks under three transfer settings. Copyright © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

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

Hilbert distillation for cross-dimensionality networks 22

学校读者我要写书评

暂无评论

Hilbert distillation for cross-dimensionality networks

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

作者： Dian Qin Haishuai Wang Zhe Liu Hongjia Xu Sheng Zhou Jiajun Bu Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University Hangzhou China Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University Hangzhou China and School of Software Technology Zhejiang University Ningbo China

ISBN: (纸本)9781713871088

3D convolutional neural networks have revealed superior performance in processing volumetric data such as video and medical imaging. However, the competitive performance by leveraging 3D networks results in huge computational costs, which are far beyond that of 2D networks. In this paper, we propose a novel Hilbert curve-based cross-dimensionality distillation approach that facilitates the knowledge of 3D networks to improve the performance of 2D networks. The proposed Hilbert Distillation (HD) method preserves the structural information via the Hilbert curve, which maps high-dimensional (>=2) representations to one-dimensional continuous space-filling curves. Since the distilled 2D networks are supervised by the curves converted from dimensionally heterogeneous 3D features, the 2D networks are given an informative view in terms of learning structural information embedded in well-trained high-dimensional representations. We further propose a Variable-length Hilbert Distillation (VHD) method to dynamically shorten the walking stride of the Hilbert curve in activation feature areas and lengthen the stride in context feature areas, forcing the 2D networks to pay more attention to learning from activation features. The proposed algorithm outperforms the current state-of-the-art distillation techniques adapted to cross-dimensionality distillation on two classification tasks. Moreover, the distilled 2D networks by the proposed method achieve competitive performance with the original 3D networks, indicating the lightweight distilled 2D networks could potentially be the substitution of cumbersome 3D networks in the real-world scenario.

关键词：

Image Search with Text Feedback by Deep Hierarchical Attention Mutual Information Maximization 21

学校读者我要写书评

暂无评论

Image Search with Text Feedback by Deep Hierarchical Attenti...

29th ACM International Conference on Multimedia, MM 2021

作者： Gu, Chunbin Bu, Jiajun Zhang, Zhen Yu, Zhi Ma, Dongfang Wang, Wei Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University China Alibaba- Zhejiang University Joint Institute of Frontier Technologies China Zhejiang Provincial Key Laboratory of Service Robot School of Software Technology Ningbo Research Institute Zhejiang University China Institute of Marine Sensing and Networking Key Laboratory of Ocean Observation-Imaging Testbed of Zhejiang Province Zhejiang University China

ISBN: (纸本)9781450386517

Image retrieval with text feedback is an emerging research topic with the objective of integrating inputs from multiple modalities as queries. In this paper, queries contain a reference image plus text feedback that describes modifications between this image and the desired image. The existing work for this task mainly focuses on designing a new fusion network to compose the image and text. Still, little research pays attention to the modality gap caused by the inconsistent distribution of features from different modalities, which dramatically influences the feature fusion and similarity learning between queries and the desired image. We propose a Distribution-Aligned Text-based Image Retrieval (DATIR) model, which consists of attention mutual information maximization and hierarchical mutual information maximization, to bridge this gap by increasing non-linear statistic dependencies between representations of different modalities. More specifically, attention mutual information maximization narrows the modality gap between different input modalities by maximizing mutual information between the text representation and its semantically consistent representation captured from the reference image and the desired image by the difference transformer. For hierarchical mutual information maximization, it aligns distributions of features from the image modality and the fusion modality by estimating mutual information between a single-layer representation in the fusion network and the multi-level representations in the desired image encoder. Extensive experiments on three large-scale benchmark datasets demonstrate that we can bridge the modality gap between different modalities and achieve state-of-the-art retrieval performance. © 2021 ACM.

关键词： Image fusion

A Traffic Light Recognition Method Based on Image Super Resolution in Intelligent Blind Glasses System

学校读者我要写书评

暂无评论

A Traffic Light Recognition Method Based on Image Super Reso...

Advances in Informatics, Electronics and Education (ISAIEE), International Symposium on

作者： Yueqing Zhang Zhi Yu Wei Wang Jiajun Bu Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University Hangzhou China School of Software Technology Zhejiang University Hangzhou Zhejiang China

One kind of traffic light recognition method based on super resolution technology applied in intelligent eyeglasses system is proposed in this paper. Take advantage of the high recognition accuracy of the latest hot target detectors and the ability of super-resolution technology which can increase image resolution dramatically, so as to achieve the accurate identification of pedestrian traffic lights. The lightweight adjustment operation can ensure the real-time performance of the model on the mobile terminal and correctly assist the safe passage of visually impaired people at traffic intersections.

关键词： Image recognition Target recognition Image color analysis Superresolution Education Glass Detectors

Hilbert Distillation for Cross-Dimensionality Networks

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Qin, Dian Wang, Haishuai Liu, Zhe Xu, Hongjia Zhou, Sheng Bu, Jiajun Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University Hangzhou China School of Software Technology Zhejiang University Ningbo China

关键词： Distillation

An Intelligent Blind Glasses System Based on Stair & Step Recognition Function

学校读者我要写书评

暂无评论

An Intelligent Blind Glasses System Based on Stair & Step Re...

Signal Processing, Communications and Engineering Management Conference (ISPCEM), International

In this paper, an intelligent blind glasses system based on stair & step recognition is proposed, which combines the innovative appearance of the product and the high performance advantages of functional modules to effectively assist visually impaired users to safely avoid obstacles when they encounter stairs or steps in indoor environments.

关键词： Headphones Engineering management Lighting Glass Stairs Signal processing Bones

Heterophilous Distribution Propagation for Graph Neural Networks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zheng, Zhuonan Zhou, Sheng Xu, Hongjia Gu, Ming Xu, Yilun Li, Ao Li, Yuhong Gu, Jingjun Bu, Jiajun College of Computer Science Zhejiang University Hangzhou310027 China Zhejiang Provincial Key Laboratory of Service Robot Zhejiang University Hangzhou310027 China School of Software Technology Zhejiang University Ningbo315048 China Bytedance Inc. Hangzhou311113 China Alibaba Group Hangzhou310052 China

Graph Neural Networks (GNNs) have achieved remarkable success in various graph mining tasks by aggregating information from neighborhoods for representation learning. The success relies on the homophily assumption that nearby nodes exhibit similar behaviors, while it may be violated in many real-world graphs. Recently, heterophilous graph neural networks (HeterGNNs) have attracted increasing attention by modifying the neural message passing schema for heterophilous neighborhoods. However, they suffer from insufficient neighborhood partition and heterophily modeling, both of which are critical but challenging to break through. To tackle these challenges, in this paper, we propose heterophilous distribution propagation (HDP) for graph neural networks. Instead of aggregating information from all neighborhoods, HDP adaptively separates the neighbors into homophilous and heterphilous parts based on the pseudo assignments during training. The heterophilous neighborhood distribution is learned with orthogonality-oriented constraint via a trusted prototype contrastive learning paradigm. Both the homophilous and heterophilous patterns are propagated with a novel semantic-aware message passing mechanism. We conduct extensive experiments on 9 benchmark datasets with different levels of homophily. Experimental results show that our method outperforms representative baselines on heterophilous datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks