graph2vec: Learning Distributed Representations of Graphs
arXiv:1707.05005
Abstract
Recent works on representation learning for graph structured data predominantly focus on learning distributed representations of graph substructures such as nodes and subgraphs. However, many graph analytics tasks such as graph classification and clustering require representing entire graphs as fixed length feature vectors. While the aforementioned approaches are naturally unequipped to learn such representations, graph kernels remain as the most effective way of obtaining them. However, these graph kernels use handcrafted features (e.g., shortest paths, graphlets, etc.) and hence are hampered by problems such as poor generalization. To address this limitation, in this work, we propose a neural embedding framework named graph2vec to learn data-driven distributed representations of arbitrary sized graphs. graph2vec's embeddings are learnt in an unsupervised manner and are task agnostic. Hence, they could be used for any downstream task such as graph classification, clustering and even seeding supervised representation learning approaches. Our experiments on several benchmark and large real-world datasets show that graph2vec achieves significant improvements in classification and clustering accuracies over substructure representation learning approaches and are competitive with state-of-the-art graph kernels.
References in corpus (3)
Cited by in corpus (103)
- Graph Contrastive Learning with Augmentations
- A Comprehensive Survey on Graph Anomaly Detection with Deep Learning
- Contrastive Multi-View Representation Learning on Graphs
- UNICORN: Runtime Provenance-Based Detector for Advanced Persistent Threats
- SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentation
- Geometric deep learning for computational mechanics Part I: Anisotropic Hyperelasticity
- InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization
- Adversarial Graph Augmentation to Improve Graph Contrastive Learning
- Anonymous Walk Embeddings
- Behavior-aware Account De-anonymization on Ethereum Interaction Graph
- Deep Graph-level Anomaly Detection by Glocal Knowledge Distillation
- On Proximity and Structural Role-based Embeddings in Networks: Misconceptions, Techniques, and Applications
- DDGK: Learning Graph Representations for Deep Divergence Graph Kernels
- Identity Inference on Blockchain using Graph Neural Network
- Recommender systems based on graph embedding techniques: A comprehensive review
- Artificial Intelligence for Quantum Computing
- Semi-Supervised Hierarchical Graph Classification
- KGNN: Harnessing Kernel-based Networks for Semi-supervised Graph Classification
- InfoGCL: Information-Aware Graph Contrastive Learning
- M-Evolve: Structural-Mapping-Based Data Augmentation for Graph Classification
- Graph Mining for Cybersecurity: A Survey
- CLPVG: Circular limited penetrable visibility graph as a new network model for time series
- Network representation learning systematic review: ancestors and current development state
- A Survey of Source Code Representations for Machine Learning-Based Cybersecurity Tasks
- Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity
- Few-Shot Learning on Graphs via Super-Classes based on Graph Spectral Measures
- GRETEL: A unified framework for Graph Counterfactual Explanation Evaluation
- Video Source Characterization Using Encoding and Encapsulation Characteristics
- A Large-Scale Database for Graph Representation Learning
- Distance Metric Learning for Graph Structured Data
- Modeling Multiple Views via Implicitly Preserving Global Consistency and Local Complementarity
- MAPFAST: A Deep Algorithm Selector for Multi Agent Path Finding using Shortest Path Embeddings
- Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs
- Deep Graph Similarity Learning: A Survey
- Semi-supervised learning of hierarchical representations of molecules using neural message passing
- IsoNN: Isomorphic Neural Network for Graph Representation Learning and Classification
- Combining Graph Neural Networks and Spatio-temporal Disease Models to Predict COVID-19 Cases in Germany
- Iterative Graph Self-Distillation
- Incorporating Relational Background Knowledge into Reinforcement Learning via Differentiable Inductive Logic Programming
- InferCode: Self-Supervised Learning of Code Representations by Predicting Subtrees
- Simplicial Complex Representation Learning
- Intelligent Vector-based Customer Segmentation in the Banking Industry
- Hyperparameter-free and Explainable Whole Graph Embedding
- MLQAOA: Graph Learning Accelerated Hybrid Quantum-Classical Multilevel QAOA
- Learning Multi-resolution Graph Edge Embedding for Discovering Brain Network Dysfunction in Neurological Disorders
- From Node Embedding To Community Embedding : A Hyperbolic Approach
- Geometric Scattering for Graph Data Analysis
- CogDL: A Comprehensive Library for Graph Deep Learning
- Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks
- An Interpretable Ensemble of Graph and Language Models for Improving Search Relevance in E-Commerce
- Genome Sequence Classification for Animal Diagnostics with Graph Representations and Deep Neural Networks
- Balancing Graph Embedding Smoothness in Self-Supervised Learning via Information-Theoretic Decomposition
- Segmented Graph-Bert for Graph Instance Modeling
- Subjective Bias in Abstractive Summarization
- Data Curation with Deep Learning [Vision]
- Label Contrastive Coding based Graph Neural Network for Graph Classification
- On the Structural Properties of Social Networks and their Measurement-calibrated Synthetic Counterparts
- Variational Recurrent Neural Networks for Graph Classification
- Generic Neural Architecture Search via Regression
- Unsupervised Joint -node Graph Representations with Compositional Energy-Based Models
- Sampling Subgraph Network with Application to Graph Classification
- Learning distributed representations of graphs with Geo2DR
- Adaptive Visibility Graph Neural Network and its Application in Modulation Classification
- Graph-Level Embedding for Time-Evolving Graphs
- Permutation-Invariant Variational Autoencoder for Graph-Level Representation Learning
- MG-GCN: Fast and Effective Learning with Mix-grained Aggregators for Training Large Graph Convolutional Networks
- Contrastive Embeddings for Neural Architectures
- Automated Cause Analysis of Latency Outliers Using System-Level Dependency Graphs
- A Quotient Space Formulation for Generative Statistical Analysis of Graphical Data
- Robust Hierarchical Graph Classification with Subgraph Attention
- Anomaly Detection in Large Labeled Multi-Graph Databases
- Little Ball of Fur: A Python Library for Graph Sampling
- Attention improves concentration when learning node embeddings
- A Wasserstein Graph Distance Based on Distributions of Probabilistic Node Embeddings
- Semi-Supervised Graph Classification: A Hierarchical Graph Perspective
- CGCL: Collaborative Graph Contrastive Learning without Handcrafted Graph Data Augmentations
- G5: A Universal GRAPH-BERT for Graph-to-Graph Transfer and Apocalypse Learning
- Inductive Subgraph Embedding for Link Prediction
- Unsupervised Hierarchical Graph Representation Learning by Mutual Information Maximization
- EGC2: Enhanced Graph Classification with Easy Graph Compression
- Computing Steiner Trees using Graph Neural Networks
- Methodology for Identifying Social Groups within a Transactional Graph
- Theoretically Improving Graph Neural Networks via Anonymous Walk Graph Kernels
- A Survey on Graph Processing Accelerators: Challenges and Opportunities
- Graphon based Clustering and Testing of Networks: Algorithms and Theory
- Learning Features of Network Structures Using Graphlets
- TGG: Transferable Graph Generation for Zero-shot and Few-shot Learning
- Unsupervised Graph Representation by Periphery and Hierarchical Information Maximization
- A Concept-Centered Hypertext Approach to Case-Based Retrieval
- High Tension Lines: Predicting robustness of high-voltage power-grids to cascading failure using network embedding
- Contributions to Representation Learning with Graph Autoencoders and Applications to Music Recommendation
- Learning Graphon Autoencoders for Generative Graph Modeling
- Low Complexity Recruitment for Collaborative Mobile Crowdsourcing Using Graph Neural Networks
- Interpreting Language Models Through Knowledge Graph Extraction
- Casting graph isomorphism as a point set registration problem using a simplex embedding and sampling
- Pairwise Half-graph Discrimination: A Simple Graph-level Self-supervised Strategy for Pre-training Graph Neural Networks
- Graph Embedding via Diffusion-Wavelets-Based Node Feature Distribution Characterization
- Counterfactual Graphs for Explainable Classification of Brain Networks
- Learning GraphQL Query Costs (Extended Version)
- A Neighborhood-preserving Graph Summarization
- Prob2Vec: Mathematical Semantic Embedding for Problem Retrieval in Adaptive Tutoring
- Column2Vec: Structural Understanding via Distributed Representations of Database Schemas
- cf2vec: Collaborative Filtering algorithm selection using graph distributed representations