Are Graph Convolutional Networks With Random Weights Feasible?
デジタルデータあり（Crossref）
すぐに読む
CiNii Research
全国の図書館の所蔵
国立国会図書館以外の全国の図書館の所蔵状況を表示します。
所蔵のある図書館から取寄せることが可能かなど、資料の利用方法は、ご自身が利用されるお近くの図書館へご相談ください
書誌情報
この資料の詳細や典拠（同じ主題の資料を指すキーワード、著者名）等を確認できます。
- 資料種別
- 記事
- 出版年月日等
- 2023-03-01
- 出版年（W3CDTF）
- 2023-03-01
- タイトル（掲載誌）
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- 巻号年月日等（掲載誌）
- 45 3
- 掲載巻
- 45
- 掲載号
- 3
- 掲載ページ
- 2751-2768
- 掲載年月日（W3CDTF）
- 2023-03-01
- ISSN（掲載誌）
- 01628828
- 出版事項（掲載誌）
- Institute of Electrical and Electronics Engineers (IEEE)
- 対象利用者
- 一般
- DOI
- 10.1109/tpami.2022.3183143
- 作成日（W3CDTF）
- 2022-06-15
- 著作権情報
- https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.htmlhttps://doi.org/10.15223/policy-029https://doi.org/10.15223/policy-037
- 参照
- Distributed Multi-Agent Reinforcement Learning for Cooperative Low-Carbon Control of Traffic Network Flow Using Cloud-Based Parallel Optimization
- 参照
- Stochastic choice of basis functions in adaptive function approximation and the functional-link netToward an Architecture for Never-Ending Language LearningDeep Learning on Graphs: A SurveyL2-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional NetworksStability and Generalization of Graph Convolutional Neural NetworksRandom Vector Functional Link (RVFL) NetworksInsights into randomized algorithms for neural networks: Practical issues and common pitfallsRobust Spatial Filtering With Graph Convolutional Neural NetworksOn the evolution of random graphsBag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark StudyThe Graph Neural Network ModelA Comprehensive Survey on Graph Neural NetworksGraph neural networks: A review of methods and applicationsGeometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNsDeeper Insights Into Graph Convolutional Networks for Semi-Supervised LearningScaling Graph Neural Networks with Approximate PageRankGraph Convolutional Network HashingAn iterative learning algorithm for feedforward neural networks with random weightsSecond-Order Pooling for Graph Neural NetworksStrong and weak stability of randomized learning algorithmsGeometric Deep Learning: Going beyond Euclidean dataUnderstanding Machine LearningA review on neural networks with random weightsRandomness in neural networks: an overviewLearning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph ClassificationTowards Deeper Graph Neural NetworksHpLapGCN: Hypergraph p-Laplacian graph convolutional networks2-D Stochastic Configuration Networks for Image Data AnalyticsSPAGAN: Shortest Path Graph Attention NetworkAn Integral Representation of Functions Using Three-layered Networks and Their Approximation BoundsCo-Embedding of Nodes and Edges With Graph Neural NetworksStochastic Configuration Networks: Fundamentals and AlgorithmsDeepGCNs: Can GCNs Go As Deep As CNNs?Fast Haar Transforms for Graph Neural NetworksHeterogeneous Graph Attention Network for Unsupervised Multiple-Target Domain AdaptationGraph convolutional networks with multi-level coarsening for graph classificationLearning on Attribute-Missing GraphsDeep Stochastic Configuration Networks with Universal Approximation PropertyImage Super-Resolution via Adaptive <inline-formula> <tex-math notation="LaTeX">$\ell _{p} (0<p<1)$ </tex-math> </inline-formula> Regularization and Sparse RepresentationGraphs, Convolutions, and Neural Networks: From Graph Filters to Graph Neural NetworksMulti-dimensional Graph Convolutional NetworksRidge Regression: Applications to Nonorthogonal ProblemsCluster-GCNDeep Learning via Semi-supervised Embeddingnode2vecSupport-vector networksDeepWalkAn iterative thresholding algorithm for linear inverse problems with a sparsity constraintNeural message passing for quantum chemistryDimensional reweighting graph convolutional networksManifold regularization: A geometric framework for learning from labeled and unlabeled examplesGraphSAINT: Graph sampling based inductive learning methodSimple and deep graph convolutional networksDropEdge: Towards deep graph convolutional networks on node classificationRegularized least-squares classificationGraphTSNE: A visualization technique for graph-structured dataLanczosNet: Multi-scale deep graph convolutional networksLink-based classificationStability and generalizationSimplifying graph convolutional networksGraph attention networksUnderstanding the representation power of graph neural networks in learning graph topologySpectral networks and locally connected networks on graphsFast graph representation learning with PyTorch geometricDiffusion-convolutional neural networksAdaptive graph diffusion networks with hop-wise attentionInductive representation learning on large graphsStability of randomized learning algorithmsGraph wavelet neural networkSIGN: Scalable inception graph neural networksVisualizing data using t-SNEConvolutional neural networks on graphs with fast localized spectral filteringHow powerful are graph neural networks?Training graph neural networks with 1000 layersLayer-dependent importance sampling for training deep and large graph convolutional networksRepresentation learning on graphs with jumping knowledge networksAlmost-everywhere algorithmic stability and generalization errorOpen graph benchmark: Datasets for machine learning on graphsTransferability of spectral graph convolutional neural networksGNNAutoScale: Scalable and expressive graph neural networks via historical embeddingsFastGCN: Fast learning with graph convolutional networks via importance samplingGraphon neural networks and the transferability of graph neural networksRevisiting semi-supervised learning with graph embeddingsVQ-GNN: A universal framework to scale up graph neural networks using vector quantizationLazySVD: Even faster SVD decomposition yet without agonizing painSemi-supervised learning using gaussian fields and harmonic functionsWeighted sums of random kitchen sinks: Replacing minimization with randomization in learningBandit samplers for training graph neural networksSemi-supervised classification with graph convolutional networksStochastic training of graph convolutional networks with variance reductionExtensions to McDiarmids inequality when differences are bounded with high probability
- 連携機関・データベース
- 国立情報学研究所 : CiNii Research
- 提供元機関・データベース
- Crossref科学研究費助成事業データベースCrossref