Graph 相关学术速递

2022-05-29
[ 1 ] How Powerful are K-hop Message Passing Graph Neural Networks
标题：K跳消息传递图神经网络的能力有多强
链接：https://arxiv.org/abs/2205.13328
作者：Jiarui Feng,Yixin Chen,Fuhai Li,Anindya Sarkar,Muhan Zhang

[ 2 ] Recipe for a General, Powerful, Scalable Graph Transformer
标题：通用、功能强大、可扩展的图形转换器的诀窍
链接：https://arxiv.org/abs/2205.12454
作者：Ladislav Rampášek,Mikhail Galkin,Vijay Prakash Dwivedi,Anh Tuan Luu,Guy Wolf,Dominique Beaini

[ 3 ] Asynchronous Neural Networks for Learning in Graphs
标题：用于图学习的异步神经网络
链接：https://arxiv.org/abs/2205.12245
作者：Lukas Faber,Roger Wattenhofer

[ 4 ] Ensemble Multi-Relational Graph Neural Networks
标题：集成多关系图神经网络
链接：https://arxiv.org/abs/2205.12076
作者：Yuling Wang,Hao Xu,Yanhua Yu,Mengdi Zhang,Zhenhao Li,Yuji Yang,Wei Wu

[ 5 ] Faithful Explanations for Deep Graph Models
标题：关于深图模型的忠实解释
链接：https://arxiv.org/abs/2205.11850
作者：Zifan Wang,Yuhang Yao,Chaoran Zhang,Han Zhang,Youjie Kang,Carlee Joe-Wong,Matt Fredrikson,Anupam Datta

[ 6 ] Not too little, not too much: a theoretical analysis of graph (over)smoothing
标题：不是太少，不是太多：关于图形(过)平滑的理论分析
链接：https://arxiv.org/abs/2205.12156

[ 7 ] Semi-Supervised Clustering of Sparse Graphs: Crossing the Information-Theoretic Threshold
标题：稀疏图的半监督聚类：跨越信息论阈值
链接：https://arxiv.org/abs/2205.11677

[ 8 ] ImGCL: Revisiting Graph Contrastive Learning on Imbalanced Node Classification
标题：ImGCL：基于不平衡节点分类的重访图对比学习
链接：https://arxiv.org/abs/2205.11332

[ 9 ] Learning heterophilious edge to drop: A general framework for boosting graph neural networks
标题：学习异嗜性边下降：一种增强图神经网络的通用框架
链接：https://arxiv.org/abs/2205.11322

[ 10 ] How Powerful are Spectral Graph Neural Networks
标题：谱图神经网络的功能有多强
链接：https://arxiv.org/abs/2205.11172
作者：Xiyuan Wang,Muhan Zhang

[ 11 ] GraphMAE: Self-Supervised Masked Graph Autoencoders
标题：GraphMAE：自监督掩码图自动编码器
链接：https://arxiv.org/abs/2205.10803

[ 12 ] Tackling Provably Hard Representative Selection via Graph Neural Networks
标题：用图神经网络解决可证明困难的代表选择问题
链接：https://arxiv.org/abs/2205.10403

[ 13 ] On the Prediction Instability of Graph Neural Networks
标题：关于图神经网络的预测不稳定性
链接：https://arxiv.org/abs/2205.10070

[ 14 ] MaskGAE: Masked Graph Modeling Meets Graph Autoencoders
标题：MaskGAE：屏蔽图建模与图自动编码器的结合
链接：https://arxiv.org/abs/2205.10053

[ 15 ] A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection
标题：可信图学习综述：可靠性、可解释性和隐私保护
链接：https://arxiv.org/abs/2205.10014
作者：Bingzhe Wu,Jintang Li,Junchi Yu,Yatao Bian,Hengtong Zhang,CHaochao Chen,Chengbin Hou,Guoji Fu,Liang Chen,Tingyang Xu,Yu Rong,Xiaolin Zheng,Junzhou Huang,Ran He,Baoyuan Wu,GUangyu Sun,Peng Cui,Zibin Zheng,Zhe Liu,Peilin Zhao

[ 16 ] A General Framework for quantifying Aleatoric and Epistemic uncertainty in Graph Neural Networks
标题：图神经网络中任意不确定性和认知不确定性量化的通用框架
链接：https://arxiv.org/abs/2205.09968
作者：Sai Munikoti,Deepesh Agarwal,Laya Das,Balasubramaniam Natarajan

[ 17 ] Towards Explanation for Unsupervised Graph-Level Representation Learning
标题：关于无监督图级表示学习的解释
链接：https://arxiv.org/abs/2205.09934
作者：Qinghua Zheng,Jihong Wang,Minnan Luo,Yaoliang Yu,Jundong Li,Lina Yao,Xiaojun Chang

[ 18 ] Label-invariant Augmentation for Semi-Supervised Graph Classification
标题：半监督图分类中的标签不变增强算法
链接：https://arxiv.org/abs/2205.09802
作者：Han Yue,Chunhui Zhang,Chuxu Zhang,Hongfu Liu

[ 19 ] Graph Neural Networks Are More Powerful Than we Think
标题：图形神经网络比我们想象的更强大
链接：https://arxiv.org/abs/2205.09801
作者：Charilaos I. Kanatsoulis,Alejandro Ribeiro

[ 20 ] Are Graph Representation Learning Methods Robust to Graph Sparsity and Asymmetric Node Information?
标题：图表示学习方法对图稀疏性和节点信息不对称具有稳健性吗？
链接：https://arxiv.org/abs/2205.09648
作者：Pierre Sevestre,Marine Neyret

[ 21 ] Learning Graph Structure from Convolutional Mixtures
标题：从卷积混合中学习图的结构
链接：https://arxiv.org/abs/2205.09575
作者：Max Wasserman,Saurabh Sihag,Gonzalo Mateos,Alejandro Ribeiro

[ 22 ] Constraint-Based Causal Structure Learning from Undersampled Graphs
标题：基于约束的欠采样图因果结构学习
链接：https://arxiv.org/abs/2205.09235
作者：Mohammadsajad Abavisani,David Danks,Sergey Plis

[ 13 ] Simple Contrastive Graph Clustering
标题：简单对比图聚类
链接：https://arxiv.org/abs/2205.07865

[ 14 ] Discovering the Representation Bottleneck of Graph Neural Networks from Multi-order Interactions
标题：从多阶交互中发现图神经网络的表示瓶颈
链接：https://arxiv.org/abs/2205.07266

[ 15 ] GPN: A Joint Structural Learning Framework for Graph Neural Networks
标题：GPN：一种图神经网络的联合结构学习框架
链接：https://arxiv.org/abs/2205.05964
作者：Qianggang Ding,Deheng Ye,Tingyang Xu,Peilin Zhao

[ 16 ] A Survey on Fairness for Machine Learning on Graphs
标题：基于图的机器学习公平性研究综述
链接：https://arxiv.org/abs/2205.05396
作者：Manvi Choudhary,Charlotte Laclau,Christine Largeron

[ 17 ] NDGGNET-A Node Independent Gate based Graph Neural Networks
标题：NDGGNET--一种基于节点无关门的图神经网络
链接：https://arxiv.org/abs/2205.05348
作者：Ye Tang,Xuesong Yang,Xinrui Liu,Xiwei Zhao,Zhangang Lin,Changping Peng

[ 18 ] Deep Embedded Multi-View Clustering via Jointly Learning Latent Representations and Graphs
标题：基于联合学习潜在表示和图的深度嵌入式多视点聚类
链接：https://arxiv.org/abs/2205.03803
作者：Zongmo Huang,Yazhou Ren,Xiaorong Pu,Lifang He

[ 19 ] Select and Calibrate the Low-confidence: Dual-Channel Consistency based Graph Convolutional Networks
标题：选择和校正低置信度：基于双通道一致性的图卷积网络
链接：https://arxiv.org/abs/2205.03753
作者：Shuhao Shi,Jian Chen,Kai Qiao,Shuai Yang,Linyuan Wang,Bin Yan

[ 20 ] Bandits for Structure Perturbation-based Black-box Attacks to Graph Neural Networks with Theoretical Guarantees
标题：基于结构扰动的图神经网络黑盒攻击的强盗行为
链接：https://arxiv.org/abs/2205.03546
作者：Binghui Wang,Youqi Li,Pan Zhou

[ 21 ] Clustered Graph Matching for Label Recovery and Graph Classification
标题：用于标签恢复和图分类的聚类图匹配
链接：https://arxiv.org/abs/2205.03486
作者：Zhirui Li,Jesus Arroyo,Konstantinos Pantazis,Vince Lyzinski

[ 22 ] OOD Link Prediction Generalization Capabilities of Message-Passing GNNs in Larger Test Graphs
标题：消息传递GNN在较大测试图中的OOD链路预测泛化能力
链接：https://arxiv.org/abs/2205.15117

[ 23 ] CGMN: A Contrastive Graph Matching Network for Self-Supervised Graph Similarity Learning
标题：CGMN：一种用于自监督图相似性学习的对比图匹配网络
链接：https://arxiv.org/abs/2205.15083

[ 24] Embedding Graphs on Grassmann Manifold
标题：Grassmann流形上的嵌入图
链接：https://arxiv.org/abs/2205.15068

[ 25 ] GraMeR: Graph Meta Reinforcement Learning for Multi-Objective Influence Maximization
标题：Gramer：多目标影响最大化的图元强化学习
链接：https://arxiv.org/abs/2205.14834

[ 26 ] Graph Structure Based Data Augmentation Method
标题：一种基于图结构的数据增强方法
链接：https://arxiv.org/abs/2205.14619

[ 27 ] Rethinking the Setting of Semi-supervised Learning on Graphs
标题：关于图的半监督学习设置的再思考
链接：https://arxiv.org/abs/2205.14403

[ 28 ] Going Deeper into Permutation-Sensitive Graph Neural Networks
标题：更深入地研究排列敏感的图神经网络
链接：https://arxiv.org/abs/2205.14368

[ 29 ] Personalized PageRank Graph Attention Networks
标题：个性化PageRank图关注网络
链接：https://arxiv.org/abs/2205.14259

[ 30 ] Collaborative likelihood-ratio estimation over graphs
标题：图上的协作似然比估计
链接：https://arxiv.org/abs/2205.14461

2022-05-31
[ 31 ] Bayesian Robust Graph Contrastive Learning
标题：贝叶斯稳健图对比学习
链接：https://arxiv.org/abs/2205.14109

[ 32 ] Learning to Solve Combinatorial Graph Partitioning Problems via Efficient Exploration
标题：通过有效探索学习解决组合图划分问题
链接：https://arxiv.org/abs/2205.14105

[ 33 ] What Dense Graph Do You Need for Self-Attention?
标题：你需要什么样的密集图表来集中注意力？
链接：https://arxiv.org/abs/2205.14014

[ 34 ] EvenNet: Ignoring Odd-Hop Neighbors Improves Robustness of Graph Neural Networks
标题：EvenNet：忽略奇跳邻居提高图神经网络的健壮性
链接：https://arxiv.org/abs/2205.13892

[ 35 ] On Consistency in Graph Neural Network Interpretation
标题：关于图神经网络解释中的一致性问题
链接：https://arxiv.org/abs/2205.13733

[ 36 ] Faster Optimization on Sparse Graphs via Neural Reparametrization
标题：基于神经重构的稀疏图快速优化
链接：https://arxiv.org/abs/2205.13624

[ 37 ] Strategic Classification with Graph Neural Networks
标题：基于图神经网络的战略分类
链接：https://arxiv.org/abs/2205.15765

[ 38 ] Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning
标题：用于自监督图表示学习的全粒度自我语义传播
链接：https://arxiv.org/abs/2205.15746

[ 39 ] Template based Graph Neural Network with Optimal Transport Distances
标题：基于模板的最优传输距离图神经网络
链接：https://arxiv.org/abs/2205.15733

[ 40 ] Automatic Relation-aware Graph Network Proliferation
标题：自动关系感知图网络扩散
链接：https://arxiv.org/abs/2205.15678

[ 41 ] Label-Enhanced Graph Neural Network for Semi-supervised Node Classification
标题：基于标签增强型图神经网络的半监督节点分类
链接：https://arxiv.org/abs/2205.15653

[ 42 ] Graph-level Neural Networks: Current Progress and Future Directions
标题：图级神经网络：现状与发展方向
链接：https://arxiv.org/abs/2205.15555

[ 43 ] Graph Neural Networks with Precomputed Node Features
标题：具有预计算节点特征的图神经网络
链接：https://arxiv.org/abs/2206.00637

[ 44 ] Calibrate and Debias Layer-wise Sampling for Graph Convolutional Networks
标题：图卷积网络的逐层采样校正与去偏
链接：https://arxiv.org/abs/2206.00583

[ 45 ] Augmenting Message Passing by Retrieving Similar Graphs
标题：通过检索相似图来增强消息传递
链接：https://arxiv.org/abs/2206.00362

[ 46 ] Lower and Upper Bounds for Numbers of Linear Regions of Graph Convolutional Networks
标题：图卷积网络线性区域个数的上下界
链接：https://arxiv.org/abs/2206.00228

[ 47 ] Principle of Relevant Information for Graph Sparsification
标题：图的相关信息稀疏化原理
链接：https://arxiv.org/abs/2206.00118

[ 48 ] A Simple yet Effective Method for Graph Classification
标题：一种简单有效的图形分类方法
链接：https://arxiv.org/abs/2206.02404

[ 49 ] Restructuring Graph for Higher Homophily via Learnable Spectral Clustering
标题：基于可学习谱聚类的同质性较高重构图
链接：https://arxiv.org/abs/2206.02386

[ 50 ] Your Neighbors Are Communicating: Towards Powerful and Scalable Graph Neural Networks
标题：您的邻居正在交流：迈向功能强大且可扩展的图形神经网络
链接：https://arxiv.org/abs/2206.02059

[ 51 ] An Unpooling Layer for Graph Generation
标题：一种用于图形生成的解池层
链接：https://arxiv.org/abs/2206.01874

[ 52 ] Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
标题：图神经网络中异质性相遇时的全局同质性
链接：https://arxiv.org/abs/2205.07308

[ 53 ] Discovering the Representation Bottleneck of Graph Neural Networks from Multi-order Interactions
标题：从多阶交互中发现图神经网络的表示瓶颈
链接：https://arxiv.org/abs/2205.07266

[ 54]  A Survey on Fairness for Machine Learning on Graphs
标题：基于图的机器学习公平性研究综述
链接：https://arxiv.org/abs/2205.05396

[ 55] Deep Graph Clustering via Mutual Information Maximization and Mixture Model
标题：基于互信息最大化和混合模型的深度图聚类
链接：https://arxiv.org/abs/2205.05168

[ 56 ] Deep Embedded Multi-View Clustering via Jointly Learning Latent Representations and Graphs
标题：基于联合学习潜在表示和图的深度嵌入式多视点聚类
链接：https://arxiv.org/abs/2205.03803

[ 57 ] Bandits for Structure Perturbation-based Black-box Attacks to Graph Neural Networks with Theoretical Guarantees
标题：基于结构扰动的图神经网络黑盒攻击的强盗行为
链接：https://arxiv.org/abs/2205.03546

[ 58 ] Clustered Graph Matching for Label Recovery and Graph Classification
标题：用于标签恢复和图分类的聚类图匹配
链接：https://arxiv.org/abs/2205.03486

[ 59 ] FastGCL: Fast Self-Supervised Learning on Graphs via Contrastive Neighborhood Aggregation
标题：FastGCL：基于对比邻域聚集的快速图自监督学习
链接：https://arxiv.org/abs/2205.00905

[ 60 ] Positive-Unlabeled Learning with Adversarial Data Augmentation for Knowledge Graph Completion
标题：基于对抗性数据增强的知识图补全正向无标记学习
链接：https://arxiv.org/abs/2205.00904

[ 61]  Graph Anisotropic Diffusion
标题：图的各向异性扩散
链接：https://arxiv.org/abs/2205.00354

[ 62 ] Heterogeneous Graph Neural Networks using Self-supervised Reciprocally Contrastive Learning
标题：基于自监督反向对比学习的异构图神经网络
链接：https://arxiv.org/abs/2205.00256

[ 63] Reducing Neural Architecture Search Spaces with Training-Free Statistics and Computational Graph Clustering
标题：利用免训练统计和计算图聚类减少神经结构搜索空间
链接：https://arxiv.org/abs/2204.14103

[ 64 ] RoSA: A Robust Self-Aligned Framework for Node-Node Graph Contrastive Learning
标题：ROSA：一种健壮的节点-节点图对比学习自对齐框架
链接：https://arxiv.org/abs/2204.13846

[ 65 ] SmartGD: A Self-Challenging Generative Adversarial Network for Graph Drawing
标题：SmartGD：一种自挑战的图形生成对抗性网络
链接：https://arxiv.org/abs/2206.06434

[ 66 ] Graph Neural Networks Intersect Probabilistic Graphical Models: A Survey
标题：图神经网络与概率图模型相交：综述
链接：https://arxiv.org/abs/2206.06089

[ 67 ] Local distance preserving auto-encoders using Continuous k-Nearest Neighbours graphs
标题：基于连续k近邻图的局部距离保持自动编码器
链接：https://arxiv.org/abs/2206.05909

[ 68 ] Soft-mask: Adaptive Substructure Extractions for Graph Neural Networks
标题：软掩码：图神经网络的自适应子结构提取
链接：https://arxiv.org/abs/2206.05499

[ 69 ] Semi-Supervised Hierarchical Graph Classification
标题：半监督层次图分类
链接：https://arxiv.org/abs/2206.05416

[ 70 ] Synthetic Over-sampling for Imbalanced Node Classification with Graph Neural Networks
标题：基于图神经网络的非平衡节点分类综合过采样算法
链接：https://arxiv.org/abs/2206.05335

[ 71 ] Evaluating Graph Generative Models with Contrastively Learned Features
标题：用对比学习特征评价图生成模型
链接：https://arxiv.org/abs/2206.06234

[ 72 ] NAGphormer: Neighborhood Aggregation Graph Transformer for Node Classification in Large Graphs
标题：NAGphormer：用于大型图节点分类的邻域聚集图转换器
链接：https://arxiv.org/abs/2206.04910

[ 73 ] COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive Learning
标题：COSTA：图对比学习中的保协方差特征增强
链接：https://arxiv.org/abs/2206.04726

[ 74 ] Scalable Deep Gaussian Markov Random Fields for General Graphs
标题：一般图的可伸缩深度高斯马尔可夫随机场
链接：https://arxiv.org/abs/2206.05032

[ 75 ] ProGNNosis: A Data-driven Model to Predict GNN Computation Time Using Graph Metrics
标题：ProGNNosis：一种基于图度量的数据驱动GNN计算时间预测模型
链接：https://arxiv.org/abs/2206.08258

[ 76 ] ResNorm: Tackling Long-tailed Degree Distribution Issue in Graph Neural Networks via Normalization
标题：ResNorm：用归一化方法解决图神经网络中的长尾度分布问题
链接：https://arxiv.org/abs/2206.08181

[ 77 ] Long Range Graph Benchmark
标题：长程图基准
链接：https://arxiv.org/abs/2206.08164

[ 78 ] Challenges and Opportunities in Deep Reinforcement Learning with Graph Neural Networks: A Comprehensive review of Algorithms and Applications
标题：图神经网络深度强化学习的挑战与机遇：算法与应用综述
链接：https://arxiv.org/abs/2206.07922

[ 79 ] Simultaneously Learning Stochastic and Adversarial Bandits with General Graph Feedback
标题：用广义图反馈同时学习随机和对抗性权标
链接：https://arxiv.org/abs/2206.07908

[ 80 ] Let Invariant Rationale Discovery Inspire Graph Contrastive Learning
标题：让不变的原理发现启发图形对比学习
链接：https://arxiv.org/abs/2206.07869

[ 81 ] Robust Attack Graph Generation
标题：健壮的攻击图生成
链接：https://arxiv.org/abs/2206.07776

[ 82 ] Condensing Graphs via One-Step Gradient Matching
标题：一步梯度匹配法压缩图
链接：https://arxiv.org/abs/2206.07746

[ 83 ] Feature Overcorrelation in Deep Graph Neural Networks: A New Perspective
标题：深度图神经网络中的特征过相关性：一个新视角
链接：https://arxiv.org/abs/2206.07743

[ 84 ] Taxonomy of Benchmarks in Graph Representation Learning
标题：图表示学习中的基准分类
链接：https://arxiv.org/abs/2206.07729

[ 85 ] Large-Scale Differentiable Causal Discovery of Factor Graphs
标题：因子图的大规模可区分因果发现
链接：https://arxiv.org/abs/2206.07824

[ 86 ] NAFS: A Simple yet Tough-to-beat Baseline for Graph Representation Learning
标题：NAFS：一种简单但难以击败的图表示学习基线
链接：https://arxiv.org/abs/2206.08583

[ 87 ] DFG-NAS: Deep and Flexible Graph Neural Architecture Search
标题：DFG-NAS：深度灵活的图神经结构搜索
链接：https://arxiv.org/abs/2206.08582

[ 88 ] Boosting Graph Structure Learning with Dummy Nodes
标题：基于虚结点的Boost图结构学习
链接：https://arxiv.org/abs/2206.08561

[ 89 ] A Robust Stacking Framework for Training Deep Graph Models with Multifaceted Node Features
标题：一种用于训练具有多面节点特征的深图模型的健壮堆叠框架
链接：https://arxiv.org/abs/2206.08473

[ 90 ] FINGER: Fast Inference for Graph-based Approximate Nearest Neighbor Search
标题：Finger：基于图的近似最近邻搜索的快速推理
链接：https://arxiv.org/abs/2206.11408

[ 91 ] Graph Neural Networks as Gradient Flows
标题：图神经网络中的梯度流
链接：https://arxiv.org/abs/2206.10991

[ 92 ] On Structural Explanation of Bias in Graph Neural Networks
标题：关于图神经网络中偏差的结构解释
链接：https://arxiv.org/abs/2206.12104

[ 93 ] Similarity-aware Positive Instance Sampling for Graph Contrastive Pre-training
标题：用于图对比预训练的相似性感知正例抽样
链接：https://arxiv.org/abs/2206.11959

[ 94 ] Affinity-Aware Graph Networks
标题：亲和力感知的图网络
链接：https://arxiv.org/abs/2206.11941

[ 95 ] A Representation Learning Framework for Property Graphs
标题：一种面向属性图的表示学习框架
链接：https://arxiv.org/abs/2206.13176

[ 96 ] Measuring and Improving the Use of Graph Information in Graph Neural Networks
标题：图神经网络中图信息使用的度量与改进
链接：https://arxiv.org/abs/2206.13170

[ 97 ] FlowX: Towards Explainable Graph Neural Networks via Message Flows
标题：FlowX：基于消息流的可解释图神经网络
链接：https://arxiv.org/abs/2206.12987

[ 98 ] Latent Augmentation For Better Graph Self-Supervised Learning
标题：用于更好的图自监督学习的潜在增强
链接：https://arxiv.org/abs/2206.12933

[ 99 ] Modeling Teams Performance Using Deep Representational Learning on Graphs
标题：基于图的深度表征学习的团队绩效建模
链接：https://arxiv.org/abs/2206.14741

[ 100 ] Private Graph Extraction via Feature Explanations
标题：基于特征解释的专用图提取
链接：https://arxiv.org/abs/2206.14724

[ 101 ] Multi-scale Physical Representations for Approximating PDE Solutions with Graph Neural Operators
标题：用图神经算子逼近偏微分方程组解的多尺度物理表示
链接：https://arxiv.org/abs/2206.14687

[ 102 ] Optimization-Induced Graph Implicit Nonlinear Diffusion
标题：优化诱导图隐式非线性扩散
链接：https://arxiv.org/abs/2206.14418

[ 103 ] Deformable Graph Transformer
标题：可变形图形转换器
链接：https://arxiv.org/abs/2206.14337

[ 104 ] Generating Counterfactual Hard Negative Samples for Graph Contrastive Learning
标题：用于图对比学习的反事实硬否定样本生成
链接：https://arxiv.org/abs/2207.00148

[ 105 ] Modularity Optimization as a Training Criterion for Graph Neural Networks
标题：模块化优化作为图神经网络的训练准则
链接：https://arxiv.org/abs/2207.00107

[ 106 ] A Safe Semi-supervised Graph Convolution Network
标题：一种安全的半监督图卷积网络
链接：https://arxiv.org/abs/2207.01960

[ 107 ] What Do Graph Convolutional Neural Networks Learn?
标题：图形卷积神经网络学到了什么？
链接：https://arxiv.org/abs/2207.01839

[ 108 ] Features Based Adaptive Augmentation for Graph Contrastive Learning
标题：基于特征的自适应增强图对比学习算法
链接：https://arxiv.org/abs/2207.01792

[ 109 ] Graph Trees with Attention
标题：带注意力的图树
链接：https://arxiv.org/abs/2207.02760

[ 110 ] Simple and Efficient Heterogeneous Graph Neural Network
标题：简单高效的异构图神经网络
链接：https://arxiv.org/abs/2207.02547

[ 111 ] Pure Transformers are Powerful Graph Learners
标题：Pure Transformers是强大的图形学习工具
链接：https://arxiv.org/abs/2207.02505

[ 112 ] Text Enriched Sparse Hyperbolic Graph Convolutional Networks
标题：文本丰富的稀疏双曲图卷积网络
链接：https://arxiv.org/abs/2207.02368

[ 113 ] Unified Embeddings of Structural and Functional Connectome via a Function-Constrained Structural Graph Variational Auto-Encoder
标题：基于函数约束结构图变分自动编码器的结构和功能连接体的统一嵌入
链接：https://arxiv.org/abs/2207.02328

[ 114 ] Label-Only Membership Inference Attack against Node-Level Graph Neural Networks
标题： 基于标签的节点级图神经网络成员推断攻击
链接：https://arxiv.org/abs/2207.13766

[ 115 ] Analyzing Data-Centric Properties for Contrastive Learning on Graphs
标题： 图对比学习中数据中心性质的分析
链接：https://arxiv.org/abs/2208.02810

[ 116 ] GROWN+UP: A Graph Representation Of a Webpage Network Utilizing Pre-training
标题： GROWN+UP：一种利用预训练的网页网络图表示
链接：https://arxiv.org/abs/2208.02252

[ 117 ] Node Copying: A Random Graph Model for Effective Graph Sampling
标题：节点复制：一种有效图抽样的随机图模型
链接：https://arxiv.org/abs/2208.02435

[ 118 ] Robust Graph Neural Networks using Weighted Graph Laplacian
标题：基于加权图拉普拉斯算子的鲁棒图神经网络
链接：https://arxiv.org/abs/2208.01853

[ 119 ] Link Prediction on Heterophilic Graphs via Disentangled Representation Learning
标题：基于解纠缠表示学习的异构图链接预测
链接：https://arxiv.org/abs/2208.01820

[ 120 ] Adversarial Camouflage for Node Injection Attack on Graphs
标题：图上节点注入攻击的对抗性伪装
链接：https://arxiv.org/abs/2208.01819

[ 121 ] Maximal Independent Vertex Set applied to Graph Pooling
标题：最大独立顶点集在图池中的应用
链接：https://arxiv.org/abs/2208.01648

[ 122 ] Path-aware Siamese Graph Neural Network for Link Prediction
标题：用于链路预测的路径感知暹罗图神经网络
链接：https://arxiv.org/abs/2208.05781

[ 123 ] Learning Point Processes using Recurrent Graph Network
标题：基于递归图网络的学习点过程
链接：https://arxiv.org/abs/2208.05736

[ 124 ] Embedding Compression with Hashing for Efficient Representation Learning in Large-Scale Graph
标题：大规模图中高效表示学习的哈希嵌入压缩算法
链接：https://arxiv.org/abs/2208.05648

[ 125 ] Are Gradients on Graph Structure Reliable in Gray-box Attacks?
标题：在灰盒攻击中，图结构上的梯度可靠吗？
链接：https://arxiv.org/abs/2208.05514

[ 126 ] Adaptive incomplete multi-view learning via tensor graph completion
标题：基于张量图补全的自适应不完全多视图学习
链接：https://arxiv.org/abs/2208.03710

[ 127 ] Robust Causal Graph Representation Learning against Confounding Effects
标题：抗混杂影响的鲁棒因果图表示学习
链接：https://arxiv.org/abs/2208.08584

[ 128 ] Evaluating Explainability for Graph Neural Networks
标题：图神经网络的可解释性评价
链接：https://arxiv.org/abs/2208.09339

[ 129 ] Graph Convolutional Networks from the Perspective of Sheaves and the Neural Tangent Kernel
标题：基于层和神经切核的图卷积网络
链接：https://arxiv.org/abs/2208.09309

[ 130 ] GraphTTA: Test Time Adaptation on Graph Neural Networks
标题：GraphTTA：图神经网络的测试时间自适应
链接：https://arxiv.org/abs/2208.09126

[ 131 ] GraTO: Graph Neural Network Framework Tackling Over-smoothing with Neural Architecture Search
标题：GraTO：用神经结构搜索解决过平滑问题的图神经网络框架
链接：https://arxiv.org/abs/2208.09027

 

----------------