Graph Partition Neural Networks for Semi-Supervised Classification

We present graph partition neural networks (GPNN), an extension of graph neural networks (GNNs) able to handle extremely large graphs. GPNNs alternate between locally propagating information between nodes in small subgraphs and globally propagating information between the subgraphs. To efficiently partition graphs, we experiment with several partitioning algorithms and also propose a novel variant for fast processing of large scale graphs. We extensively test our model on a variety of semi-supervised node classification tasks. Experimental results indicate that GPNNs are either superior or comparable to state-of-the-art methods on a wide variety of datasets for graph-based semi-supervised classification. We also show that GPNNs can achieve similar performance as standard GNNs with fewer propagation steps.

• Publication year

  2018

• Venue

  International Conference on Learning Representations

• Publication date

  2018-02-11

• Fields of study

  Mathematics, Computer Science

• Identifiers
  arXiv 1803.06272
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Few-Shot Learning

  2020cited by this paper
• NerveNet: Learning Structured Policy with Graph Neural Networks

  2018cited by this paper
• Situation Recognition with Graph Neural Networks

  2017cited by this paper
• Neural Message Passing for Quantum Chemistry

  2017influential reference
• 3D Graph Neural Networks for RGBD Semantic Segmentation

  2017cited by this paper
• Few-Shot Learning with Graph Neural Networks

  2017cited by this paper
• Learning to Represent Programs with Graphs

  2017cited by this paper
• Inductive Representation Learning on Large Graphs

  2017cited by this paper
• Modeling Relational Data with Graph Convolutional Networks

  2017cited by this paper
• The More You Know: Using Knowledge Graphs for Image Classification

  2016cited by this paper
• Graph-Structured Representations for Visual Question Answering

  2016cited by this paper
• Learning Multiagent Communication with Backpropagation

  2016cited by this paper
• node2vec: Scalable Feature Learning for Networks

  2016cited by this paper
• Revisiting Semi-Supervised Learning with Graph Embeddings

  2016influential reference
• Semi-Supervised Classification with Graph Convolutional Networks

  2016influential reference
• Convolutional Networks on Graphs for Learning Molecular Fingerprints

  2015cited by this paper
• Gated Graph Sequence Neural Networks

  2015influential reference
• Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks

  2015cited by this paper
• Improving Distant Supervision for Information Extraction Using Label Propagation Through Lists

  2015influential reference
• Message Passing Inference for Large Scale Graphical Models with High Order Potentials

  2014cited by this paper
• Adam: A Method for Stochastic Optimization

  2014cited by this paper
• DeepWalk: online learning of social representations

  2014influential reference
• Spectral Networks and Locally Connected Networks on Graphs

  2013cited by this paper
• Graph Cuts is a Max-Product Algorithm

  2011cited by this paper
• Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection

  2011cited by this paper
• MRF Energy Minimization and Beyond via Dual Decomposition

  2011cited by this paper
• Parsing Natural Scenes and Natural Language with Recursive Neural Networks

  2011cited by this paper
• Toward an Architecture for Never-Ending Language Learning

  2010cited by this paper
• The Graph Neural Network Model

  2009cited by this paper
• Collective Classi!cation in Network Data

  2008cited by this paper
• Collective Classification in Network Data

  2008influential reference
• Visualizing Data using t-SNE

  2008cited by this paper
• Deep learning via semi-supervised embedding

  2008influential reference
• A tutorial on spectral clustering

  2007cited by this paper
• Improved Dynamic Schedules for Belief Propagation

  2007cited by this paper
• Residual Belief Propagation: Informed Scheduling for Asynchronous Message Passing

  2006cited by this paper
• Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples

  2006influential reference
• A new model for learning in graph domains

  2005cited by this paper
• On the Choice of Regions for Generalized Belief Propagation

  2004cited by this paper
• Graph Partition Strategies for Generalized Mean Field Inference

  2004cited by this paper
• Combining active learning and semi-supervised learning using Gaussian fields and harmonic functions

  2003cited by this paper
• Understanding belief propagation and its generalizations

  2003cited by this paper
• Link-Based Classification

  2003cited by this paper
• A generalized mean field algorithm for variational inference in exponential families

  2002cited by this paper
• Tree-based reparameterization for approximate inference on loopy graphs

  2001cited by this paper
• Distributed Computing: Fundamentals, Simulations and Advanced Topics

  2001cited by this paper
• Distributed Computing: Fundamentals, Simulations and Advanced Topics

  1998cited by this paper
• Normalized cuts and image segmentation

  1997cited by this paper
• Probabilistic reasoning in intelligent systems: Networks of plausible inference

  1991cited by this paper
• Local computations with probabilities on graphical structures and their application to expert systems

  1990cited by this paper

• CNEKA: An Algorithm for SDN Controller Placement Based on Graph Convolutional Networks

  2026cites this paper
• DDL: Dynamic Direction Learning for Semi-Supervised Facial Expression Recognition

  2025cites this paper
• Distributed framework for high-quality graph partitioning

  2025cites this paper
• Using graph convolutional networks to improve accuracy of image retrieval with relevance feedback method

  2025cites this paper
• Beyond the Known: Novel Class Discovery for Open-world Graph Learning

  2024cites this paper
• Cross-Modal Learning for Chemistry Property Prediction: Large Language Models Meet Graph Machine Learning

  2024cites this paper
• Partitioned neural network training via synthetic intermediate labels

  2024cites this paper
• Similarity graph-based max-flow and duality approaches for semi-supervised data classification and image segmentation

  2023cites this paper
• Efficient graph-based spectral techniques for data with few labeled samples

  2023cites this paper
• Fast and Effective GNN Training through Sequences of Random Path Graphs

  2023cites this paper
• Self-Supervised Nodes-Hyperedges Embedding for Heterogeneous Information Network Learning

  2023cites this paper
• Lasagne: A Multi-Layer Graph Convolutional Network Framework via Node-Aware Deep Architecture

  2023cites this paper
• Uplifting the Expressive Power of Graph Neural Networks through Graph Partitioning

  2023cites this paper
• Large Scale Training of Graph Neural Networks for Optimal Markov-Chain Partitioning Using the Kemeny Constant

  2023influential citation
• Minority-Weighted Graph Neural Network for Imbalanced Node Classification in Social Networks of Internet of People

  2023cites this paper
• An Interpretable Station Delay Prediction Model Based on Graph Community Neural Network and Time-Series Fuzzy Decision Tree

  2023cites this paper
• GraphNAS++: Distributed Architecture Search for Graph Neural Networks

  2023cites this paper
• Kemeny Constant-Based Optimization of Network Clustering Using Graph Neural Networks

  2023cites this paper
• Permutation-Invariant Graph Partitioning:How Graph Neural Networks Capture Structural Interactions?

  2023cites this paper
• PaSca: A Graph Neural Architecture Search System under the Scalable Paradigm

  2022cites this paper
• Path reliability-based graph attention networks

  2022cites this paper
• A Spatiotemporal Graph Attention Network Based on Synchronization for Epileptic Seizure Prediction

  2022cites this paper
• gSuite: A Flexible and Framework Independent Benchmark Suite for Graph Neural Network Inference on GPUs

  2022cites this paper
• Two-step artificial intelligence system for endoscopic gastric biopsy improves the diagnostic accuracy of pathologists

  2022cites this paper
• Adaptive Propagation Graph Convolutional Networks Based on Attention Mechanism

  2022cites this paper
• Deep Portfolio Optimization Modeling based on Conv-Transformers with Graph Attention Mechanism

  2022cites this paper
• Hypergraph Transformer Neural Networks

  2022cites this paper
• Pattern classification based on regional models

  2022cites this paper
• On rough set based fuzzy clustering for graph data

  2022cites this paper
• Semisupervised Graph Neural Networks for Graph Classification

  2022cites this paper
• Graph neural network with feature enhancement of isolated marginal groups

  2022cites this paper
• Active and Semi-Supervised Graph Neural Networks for Graph Classification

  2022cites this paper
• Large-scale graph representation learning with very deep GNNs and self-supervision

  2021cites this paper
• Graph-Based Semi-Supervised Learning: A Comprehensive Review

  2021cites this paper
• A Survey on Deep Semi-Supervised Learning

  2021cites this paper
• GraphTheta: A Distributed Graph Neural Network Learning System With Flexible Training Strategy

  2021influential citation
• L ARGE - SCALE NODE CLASSIFICATION WITH BOOTSTRAPPING

  2021cites this paper
• DeGNN: Improving Graph Neural Networks with Graph Decomposition

  2021influential citation
• Deep Dive into Semi-Supervised ELBO for Improving Classification Performance

  2021cites this paper
• Multiscale laplacian learning

  2021cites this paper
• Boosting Few-Shot Hyperspectral Image Classification Using Pseudo-Label Learning

  2021cites this paper
• BotSpot++: A Hierarchical Deep Ensemble Model for Bots Install Fraud Detection in Mobile Advertising

  2021cites this paper
• A NOTE ON APPLICABILITY OF ARTIFICIAL INTELLIGENCE TO CONSTITUTIVE MODELING OF GEOMATERIALS

  2020cites this paper
• Graph Convolution Network with Double Filter for Point Cloud Segmentation

  2020cites this paper
• Hop-Hop Relation-aware Graph Neural Networks

  2020cites this paper
• Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving

  2020cites this paper
• Graph Neural Networks: Taxonomy, Advances, and Trends

  2020cites this paper
• Multi-Channel Temporal Graph Convolutional Network for Stock Return Prediction

  2020cites this paper
• A reinforcement learning approach for optimizing multiple traveling salesman problems over graphs

  2020cites this paper
• Meta-path Free Semi-supervised Learning for Heterogeneous Networks

  2020cites this paper
• Computing Graph Neural Networks: A Survey from Algorithms to Accelerators

  2020influential citation
• Reliable Data Distillation on Graph Convolutional Network

  2020cites this paper
• GuardHealth: Blockchain empowered secure data management and Graph Convolutional Network enabled anomaly detection in smart healthcare

  2020cites this paper
• Uncertainty Aware Graph Gaussian Process for Semi-Supervised Learning

  2020cites this paper
• Nonlinear Equation Solving: A Faster Alternative to Feedforward Computation

  2020cites this paper
• DeGNN : Characterizing and Improving Graph Neural Networks with Graph Decomposition

  2020cites this paper
• CFGAT: A Coarse-to-Fine Graph Attention Network for Semi-supervised Node Classification

  2020cites this paper
• Confidence-based Graph Convolutional Networks for Semi-Supervised Learning

  2019influential citation
• LanczosNet: Multi-Scale Deep Graph Convolutional Networks

  2019cites this paper
• Supervized Segmentation with Graph-Structured Deep Metric Learning

  2019cites this paper
• Label Efficient Semi-Supervised Learning via Graph Filtering

  2019cites this paper
• Graph convolutional networks: analysis, improvements and results

  2019influential citation
• Neural Graph Embedding Methods for Natural Language Processing

  2019cites this paper
• CamDrop: A New Explanation of Dropout and A Guided Regularization Method for Deep Neural Networks

  2019cites this paper
• Message Scheduling for Performant, Many-Core Belief Propagation

  2019cites this paper
• Batch Virtual Adversarial Training for Graph Convolutional Networks

  2019cites this paper
• Belief Propagation Network for Hard Inductive Semi-Supervised Learning

  2019cites this paper
• Solving Graph Flow Problems with Neural Networks: A Lagrangian Duality Approach

  2019cites this paper
• Learning a Static Bug Finder from Data

  2019cites this paper
• Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks

  2019cites this paper
• Reviving and Improving Recurrent Back-Propagation

  2018cites this paper
• Every Node Counts: Self-Ensembling Graph Convolutional Networks for Semi-Supervised Learning

  2018cites this paper
• Hierarchical Graph Representation Learning with Differentiable Pooling

  2018cites this paper
• Lovasz Convolutional Networks

  2018cites this paper
• SaaS: Speed as a Supervisor for Semi-supervised Learning

  2018cites this paper
• LanczosNet : Multi-Scale Deep Graph Convolutional Networks

  2018cites this paper
• Generalized Label Propagation Methods for Semi-Supervised Learning

  2018cites this paper
• Structure-Aware Convolutional Neural Networks

  2018cites this paper
• Bayesian graph convolutional neural networks for semi-supervised classification

  2018cites this paper
• Graph HyperNetworks for Neural Architecture Search

  2018cites this paper
• Structured Neural Summarization

  2018cites this paper
• DeGNN: Improving Graph Neural Networks with Graph Decomposition

  year unknowncites this paper