Revisiting Semi-Supervised Learning with Graph Embeddings

We present a semi-supervised learning framework based on graph embeddings. Given a graph between instances, we train an embedding for each instance to jointly predict the class label and the neighborhood context in the graph. We develop both transductive and inductive variants of our method. In the transductive variant of our method, the class labels are determined by both the learned embeddings and input feature vectors, while in the inductive variant, the embeddings are defined as a parametric function of the feature vectors, so predictions can be made on instances not seen during training. On a large and diverse set of benchmark tasks, including text classification, distantly supervised entity extraction, and entity classification, we show improved performance over many of the existing models.

• Publication year

  2016

• Venue

  International Conference on Machine Learning

• Publication date

  2016-03-29

• Fields of study

  Mathematics, Computer Science

• Identifiers
  arXiv 1603.08861
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Hierarchical Semi-supervised Classification with Incomplete Class Hierarchies

  2016cited by this paper
• Multi-Task Cross-Lingual Sequence Tagging from Scratch

  2016cited by this paper
• Improving Distant Supervision for Information Extraction Using Label Propagation Through Lists

  2015influential reference
• LINE: Large-scale Information Network Embedding

  2015cited by this paper
• Bidirectional LSTM-CRF Models for Sequence Tagging

  2015cited by this paper
• GloVe: Global Vectors for Word Representation

  2014cited by this paper
• Learning Deep Representations for Graph Clustering

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

  2014influential reference
• PIDGIN: ontology alignment using web text as interlingua

  2013cited by this paper
• Translating Embeddings for Modeling Multi-relational Data

  2013cited by this paper
• Distributed Representations of Words and Phrases and their Compositionality

  2013cited by this paper
• Natural Language Processing (Almost) from Scratch

  2011cited by this paper
• Graph Regularized Transductive Classification on Heterogeneous Information Networks

  2010cited by this paper
• Large-Scale Machine Learning with Stochastic Gradient Descent

  2010cited by this paper
• Toward an Architecture for Never-Ending Language Learning

  2010influential reference
• New Regularized Algorithms for Transductive Learning

  2009influential reference
• Visualizing Data using t-SNE

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

  2008influential reference
• Collective Classi!cation in Network Data

  2008influential reference
• Collective Classification in Network Data

  2008influential reference
• Model‐based clustering for social networks

  2007cited by this paper
• Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples

  2006influential reference
• Learning with Local and Global Consistency

  2003cited by this paper
• Combining active learning and semi-supervised learning using Gaussian fields and harmonic functions

  2003cited by this paper
• Transductive Inference for Text Classification using Support Vector Machines

  1999influential reference
• Estimation and Prediction for Stochastic Blockmodels for Graphs with Latent Block Structure

  1997cited by this paper

• LEDA: Latent Semantic Distribution Alignment for Multi-domain Graph Pre-training

  2026cites this paper
• SG-DGLF: A similarity-guided dual-graph learning framework

  2026cites this paper
• EdgeMask-DG*: Learning Domain-Invariant Graph Structures via Adversarial Edge Masking

  2026cites this paper
• HydroTGNN: Filling missing streamflow data with graph neural network

  2026cites this paper
• UniTrain: A universal iterative semi-supervised training framework for graph representation learning.

  2026cites this paper
• Hyperbolic legendre neural network: Enhancing modeling and generalization capabilities in hyperbolic space

  2026cites this paper
• Graph-constructed adaptive semantic fusion for heterophilic graph contrastive learning

  2026cites this paper
• MAGPrompt: Message-Adaptive Graph Prompt Tuning for Graph Neural Networks

  2026cites this paper
• Training-Free Cross-Architecture Merging for Graph Neural Networks

  2026cites this paper
• Beyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models

  2026cites this paper
• Drop the mask! GAMM-A Taxonomy for Graph Attributes Missing Mechanisms

  2026cites this paper
• Signal from Structure: Exploiting Submodular Upper Bounds in Generative Flow Networks

  2026cites this paper
• Beyond Homophily: Community Search on Heterophilic Graphs

  2026cites this paper
• CGMAE: Self-supervised Masked Auto-Encoder with Cross-Graph node alignment for node classification

  2026cites this paper
• RoLED: Role-disentangled graph neural network for both homophily and heterophily

  2026cites this paper
• Semi-supervised subgraph network for few-sample road breakage events recognition with fiber-optic distributed acoustic sensing

  2026cites this paper
• Rethinking Federated Graph Foundation Models: A Graph-Language Alignment-based Approach

  2026influential citation
• Training A Foundation Model to Represent Graphs as Vectors

  2026cites this paper
• TFMLinker: Universal Link Predictor by Graph In-Context Learning with Tabular Foundation Models

  2026cites this paper
• COMBA: Cross Batch Aggregation for Learning Large Graphs with Context Gating State Space Models

  2026cites this paper
• VL-KGE: Vision-Language Models Meet Knowledge Graph Embeddings

  2026cites this paper
• DiMAE: A State-Space Modeling Framework for Semi-Supervised Community Detection via Geometry-Regularized Similarity Diffusion

  2026cites this paper
• SDGraphMeta: A novel similarity-driven framework for graph meta-learning

  2026cites this paper
• Colorful Talks with Graphs: Human-Interpretable Graph Encodings for Large Language Models

  2026influential citation
• Bayesian Neighborhood Adaptation for Graph Neural Networks

  2026cites this paper
• Prior-Informed Flow Matching for Graph Reconstruction

  2026cites this paper
• ASHAS: Adaptive structural-homophilic aware sampling for Universal Graph Neural Networks

  2026cites this paper
• Parallelizing Node-Level Explainability in Graph Neural Networks

  2026cites this paper
• TCGU: Data-Centric Graph Unlearning Based on Transferable Condensation

  2026cites this paper
• CentralityPool: Centrality-Aware Hierarchical Graph Pooling

  2026influential citation
• Let Invariant Learning Inspire Neighbor-Shift Generalization on Graphs

  2026cites this paper
• AGCN: A Service Computing-Oriented Anchor-Guided Graph Clustering Network

  2026cites this paper
• Bijective graph learning architecture with multi-level attributes interaction

  2026influential citation
• Improving LLM Reasoning with Homophily-aware Structural and Semantic Text-Attributed Graph Compression

  2026cites this paper
• Multibranch Dendritic Computing for Federated Graph Neural Networks: Maintaining Interpretability Under Privacy Constraints

  2026cites this paper
• BoostFGL: Boosting Fairness in Federated Graph Learning

  2026cites this paper
• An adaptive multi-task learning method with task-specific attention for node classification and link prediction

  2026cites this paper
• Counterfactual Explanations for Hypergraph Neural Networks

  2026cites this paper
• Semantic enhancement in graph contrastive learning by combining topology and features

  2026cites this paper
• TAAM:Inductive Graph-Class Incremental Learning with Task-Aware Adaptive Modulation

  2026cites this paper
• Both Topology and Text Matter: Revisiting LLM-guided Out-of-Distribution Detection on Text-attributed Graphs

  2026cites this paper
• Learning Robust Node Representations via Graph Neural Network and Multilayer Perceptron Classifier

  2026cites this paper
• MUG: Meta-path-aware Universal Heterogeneous Graph Pre-Training

  2026cites this paper
• Toward Graph-Tokenizing Large Language Models with Reconstructive Graph Instruction Tuning

  2026cites this paper
• Towards Effective Few-Shot OOD Detection for Text-Attributed Graphs via Topology-Text Consensus Modeling

  2026cites this paper
• Resonance in message propagation to improve GCN performance on semi-supervised node classification

  2026cites this paper
• DynamicGTR: Leveraging Graph Topology Representation Preferences to Boost VLM Capabilities on Graph QAs

  2026cites this paper
• CITED: A Decision Boundary-Aware Signature for GNNs Towards Model Extraction Defense

  2026cites this paper
• CuGNN: Cross-perspective contrastive learning for enhancing unsupervised GNNs beyond homophily

  2026cites this paper
• GP2F: Cross-Domain Graph Prompting with Adaptive Fusion of Pre-trained Graph Neural Networks

  2026cites this paper
• HoGS: Homophily-Oriented Graph Synthesis for Local Differentially Private GNN Training

  2026cites this paper
• Which Graph Shift Operator? A Spectral Answer to an Empirical Question

  2026cites this paper
• Plain Transformers are Surprisingly Powerful Link Predictors

  2026cites this paper
• GrassNet: State Space Model Meets Graph Neural Network

  2026cites this paper
• Re-understanding Graph Unlearning through Memorization

  2026cites this paper
• LightPro: Lightweight multi-channel model protection for edge-oriented deep neural network

  2026cites this paper
• Position: Don't be Afraid of Over-Smoothing And Over-Squashing

  2026cites this paper
• Assortativity attention based Multi-Dim Graph neural Architecture Search under distribution shifts

  2025cites this paper
• Active Few-Shot Learning for Vertex Classification Starting from an Unlabeled Dataset

  2025cites this paper
• Disentangled Graph Representation Based on Substructure-Aware Graph Optimal Matching Kernel Convolutional Networks

  2025cites this paper
• Str-GCL: Structural Commonsense Driven Graph Contrastive Learning

  2025cites this paper
• Heterophily-informed Message Passing

  2025cites this paper
• AGCI2L: Adversarial Graph Contrastive Information Invariant Learning

  2025cites this paper
• Advancing Local Clustering on Graphs via Compressive Sensing: Semi-supervised and Unsupervised Methods

  2025cites this paper
• Rethinking Client-oriented Federated Graph Learning

  2025cites this paper
• Integrating Structural and Semantic Signals in Text-Attributed Graphs with BiGTex

  2025cites this paper
• GraphEdge: Dynamic Graph Partition and Task Scheduling for GNNs Computing in Edge Network

  2025influential citation
• Unlocking the Potential of Black-box Pre-trained GNNs for Graph Few-shot Learning

  2025cites this paper
• Heuristic Methods are Good Teachers to Distill MLPs for Graph Link Prediction

  2025cites this paper
• Towards A Universal Graph Structural Encoder

  2025cites this paper
• Graph Wave Networks

  2025cites this paper
• Learning Laplacian Positional Encodings for Heterophilous Graphs

  2025cites this paper
• GOttack: Universal Adversarial Attacks on Graph Neural Networks via Graph Orbits Learning

  2025cites this paper
• Modeling Higher-Order Interactions in Graphs Through Combinatorial Arc-Transitive Structure Using Graph Convolutional Network

  2025influential citation
• NodeImport: Imbalanced Node Classification with Node Importance Assessment

  2025cites this paper
• Finsler Multi-Dimensional Scaling: Manifold Learning for Asymmetric Dimensionality Reduction and Embedding

  2025cites this paper
• Does GCL Need a Large Number of Negative Samples? Enhancing Graph Contrastive Learning with Effective and Efficient Negative Sampling

  2025cites this paper
• Towards Efficient Training of Graph Neural Networks: A Multiscale Approach

  2025cites this paper
• Graph Triple Attention Networks: A Decoupled Perspective

  2025cites this paper
• Unifying Attribute and Structure Preservation for Enhanced Graph Contrastive Learning

  2025cites this paper
• Learning to quantify graph nodes

  2025cites this paper
• Causal invariant geographic network representations with feature and structural distribution shifts

  2025cites this paper
• Personalized Graph Transformer for Federated Graph Learning

  2025cites this paper
• SGRAND: Stochastic Graph Neural Diffusion

  2025cites this paper
• Unsupervised Graph Anomaly Detection via Multi-Hypersphere Heterophilic Graph Learning

  2025influential citation
• Enhance GNNs with Reliable Confidence Estimation via Adversarial Calibration Learning

  2025cites this paper
• Prompt-driven graph distillation: Enabling single-layer MLPs to outperform Deep Graph Neural Networks in graph-based tasks

  2025cites this paper
• FedHERO: A Federated Learning Approach for Node Classification Task on Heterophilic Graphs

  2025cites this paper
• HHG-Bot: A Hyperheterogeneous Graph-Based Twitter Bot Detection Model

  2025cites this paper
• A Binary Classification Social Network Dataset for Graph Machine Learning

  2025cites this paper
• G-OSR: A Comprehensive Benchmark for Graph Open-Set Recognition

  2025cites this paper
• Hierarchical graph sampling based minibatch learning with chain preservation and variance reduction

  2025cites this paper
• Hyperbolic Graph Wavelet Neural Network

  2025cites this paper
• Enhancing Graph Structure Learning via Motif-Driven Hypergraph Construction

  2025influential citation
• Towards Quantifying Long-Range Interactions in Graph Machine Learning: a Large Graph Dataset and a Measurement

  2025cites this paper
• DP-GPL: Differentially Private Graph Prompt Learning

  2025cites this paper
• RETAIN: Reliable Topology Augmentation for both Heterophilic and Homophilic Graphs

  2025cites this paper
• Topology-Informed Pre-training of Graph Neural Networks

  2025cites this paper
• Cross-Domain Inductive Applications with Unsupervised (Dynamic) Graph Neural Networks(GNN): Leveraging Siamese GNN and Energy-Based PMI Optimization

  2025cites this paper
• How Low Can You Go? Searching for the Intrinsic Dimensionality of Complex Networks using Metric Node Embeddings

  2025influential citation