AAAI 2021 accepted papers on Graph learning
126 of the 1,654 papers accepted at AAAI 2021 (7.6%) are on Graph learning, compared with 8.5% at AAAI 2020. They fall into 4 topics.
See AAAI 2021 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Knowledge and temporal graphs · 58 papers
- Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting (904 citations)
- Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition (335 citations)
- Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks (320 citations)
- Knowledge-Enhanced Hierarchical Graph Transformer Network for Multi-Behavior Recommendation (234 citations)
- Hierarchical Graph Convolution Network for Traffic Forecasting (211 citations)
- Graph Heterogeneous Multi-Relational Recommendation (202 citations)
- Knowledge-aware Coupled Graph Neural Network for Social Recommendation (191 citations)
- Coupled Layer-wise Graph Convolution for Transportation Demand Prediction (183 citations)
- Dual Quaternion Knowledge Graph Embeddings (160 citations)
- Transfer Graph Neural Networks for Pandemic Forecasting (154 citations)
- Rain Streak Removal via Dual Graph Convolutional Network (153 citations)
- KAN: Knowledge-aware Attention Network for Fake News Detection (126 citations)
and 46 more in the interactive map.
Graph self-supervised learning · 26 papers
- Deep Fusion Clustering Network (242 citations)
- Contrastive Self-supervised Learning for Graph Classification (134 citations)
- Uncertain Graph Neural Networks for Facial Action Unit Detection (79 citations)
- Modular Graph Transformer Networks for Multi-Label Image Classification (76 citations)
- Towards Consumer Loan Fraud Detection: Graph Neural Networks with Role-Constrained Conditional Random Field (75 citations)
- Relative and Absolute Location Embedding for Few-Shot Node Classification on Graph (73 citations)
- Adversarial Directed Graph Embedding (46 citations)
- MIMOSA: Multi-constraint Molecule Sampling for Molecule Optimization (45 citations)
- MolGrow: A Graph Normalizing Flow for Hierarchical Molecular Generation (44 citations)
- Tri-level Robust Clustering Ensemble with Multiple Graph Learning (39 citations)
- SMART: A Situation Model for Algebra Story Problems via Attributed Grammar (28 citations)
- Gaining Insight into SARS-CoV-2 Infection and COVID-19 Severity Using Self-supervised Edge Features and Graph Neural Networks (19 citations)
and 14 more in the interactive map.
Graph algorithms and clustering · 23 papers
- Fast Multi-view Discrete Clustering with Anchor Graphs (77 citations)
- Multiple Kernel Clustering with Kernel k-Means Coupled Graph Tensor Learning (76 citations)
- Graph Neural Network to Dilute Outliers for Refactoring Monolith Application (73 citations)
- A Bottom-Up DAG Structure Extraction Model for Math Word Problems (46 citations)
- Improving Maximum k-plex Solver via Second-Order Reduction and Graph Color Bounding (36 citations)
- Interpretable Clustering on Dynamic Graphs with Recurrent Graph Neural Networks (33 citations)
- TreeCaps: Tree-Based Capsule Networks for Source Code Processing (31 citations)
- Movie Summarization via Sparse Graph Construction (24 citations)
- The Price of Connectivity in Fair Division (21 citations)
- Gene Regulatory Network Inference as Relaxed Graph Matching (19 citations)
- Learning Graphons via Structured Gromov-Wasserstein Barycenters (18 citations)
- Scalable and Explainable 1-Bit Matrix Completion via Graph Signal Learning (15 citations)
and 11 more in the interactive map.
GNN architectures · 19 papers
- Beyond Low-frequency Information in Graph Convolutional Networks (533 citations)
- Data Augmentation for Graph Neural Networks (350 citations)
- Heterogeneous Graph Structure Learning for Graph Neural Networks (288 citations)
- Graph Neural Networks with Heterophily (218 citations)
- Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning (153 citations)
- Identity-aware Graph Neural Networks (140 citations)
- GraphMix: Improved Training of GNNs for Semi-Supervised Learning (121 citations)
- Learning to Pre-train Graph Neural Networks (117 citations)
- SDGNN: Learning Node Representation for Signed Directed Networks (96 citations)
- Rethinking Graph Regularization for Graph Neural Networks (49 citations)
- One-shot Graph Neural Architecture Search with Dynamic Search Space (39 citations)
- Hierarchical Graph Capsule Network (29 citations)
and 7 more in the interactive map.
