AAAI 2025 accepted papers on Graph learning
221 of the 3,486 papers accepted at AAAI 2025 (6.3%) are on Graph learning, compared with 7.0% at AAAI 2024. They fall into 4 topics.
See AAAI 2025 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Graph self-supervised learning · 83 papers
- Revolutionizing Encrypted Traffic Classification with MH-Net: A Multi-View Heterogeneous Graph Model (30 citations)
- Dynamic Spectral Graph Anomaly Detection (25 citations)
- Structure-Adaptive Multi-View Graph Clustering for Remote Sensing Data (24 citations)
- Why Does Dropping Edges Usually Outperform Adding Edges in Graph Contrastive Learning? (18 citations)
- A Label-free Heterophily-guided Approach for Unsupervised Graph Fraud Detection (15 citations)
- Global Graph Propagation with Hierarchical Information Transfer for Incomplete Contrastive Multi-view Clustering (13 citations)
- Context-aware Graph Neural Network for Graph-based Fraud Detection with Extremely Limited Labels (12 citations)
- Leveraging Large Language Models for Node Generation in Few-Shot Learning on Text-Attributed Graphs (12 citations)
- BindGPT: A Scalable Framework for 3D Molecular Design via Language Modeling and Reinforcement Learning (11 citations)
- GraphMoRE: Mitigating Topological Heterogeneity via Mixture of Riemannian Experts (11 citations)
- Large Language Model Meets Graph Neural Network in Knowledge Distillation (11 citations)
- IOHunter: Graph Foundation Model to Uncover Online Information Operations (10 citations)
and 71 more in the interactive map.
Knowledge and temporal graphs · 61 papers
- Spatiotemporal-aware Trend-Seasonality Decomposition Network for Traffic Flow Forecasting (49 citations)
- Efficient Traffic Prediction Through Spatio-Temporal Distillation (23 citations)
- Revisiting Multimodal Emotion Recognition in Conversation from the Perspective of Graph Spectrum (19 citations)
- PRAGA: Prototype-aware Graph Adaptive Aggregation for Spatial Multi-modal Omics Analysis (18 citations)
- A Generalizable Anomaly Detection Method in Dynamic Graphs (15 citations)
- Dynamic Multi-Interest Graph Neural Network for Session-Based Recommendation (15 citations)
- Dynamic Graph Learning with Static Relations for Credit Risk Assessment (13 citations)
- APKGC: Noise-enhanced Multi-Modal Knowledge Graph Completion with Attention Penalty (12 citations)
- Graph Structure Learning for Spatial-Temporal Imputation: Adapting to Node and Feature Scales (11 citations)
- LS-TGNN: Long and Short-Term Temporal Graph Neural Network for Session-Based Recommendation (11 citations)
- Beyond Graph Convolution: Multimodal Recommendation with Topology-aware MLPs (10 citations)
- Feature-Structure Adaptive Completion Graph Neural Network for Cold-start Recommendation (10 citations)
and 49 more in the interactive map.
GNN architectures · 56 papers
- When Hypergraph Meets Heterophily: New Benchmark Datasets and Baseline (34 citations)
- Mind Individual Information! Principal Graph Learning for Multimedia Recommendation (25 citations)
- Modality-Independent Graph Neural Networks with Global Transformers for Multimodal Recommendation (20 citations)
- Deep Hypergraph Neural Networks with Tight Framelets (15 citations)
- Cluster-guided Contrastive Class-imbalanced Graph Classification (11 citations)
- DeepSN: A Sheaf Neural Framework for Influence Maximization (10 citations)
- Graph Coarsening via Supervised Granular-Ball for Scalable Graph Neural Network Training (10 citations)
- Pre-Training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneck (10 citations)
- AutoSGNN: Automatic Propagation Mechanism Discovery for Spectral Graph Neural Networks (9 citations)
- Self-Explainable Graph Transformer for Link Sign Prediction (7 citations)
- AeroGTO: An Efficient Graph-Transformer Operator for Learning Large-Scale Aerodynamics of 3D Vehicle Geometries (6 citations)
- Disentangling, Amplifying, and Debiasing: Learning Disentangled Representations for Fair Graph Neural Networks (6 citations)
and 44 more in the interactive map.
Graph algorithms and clustering · 21 papers
- Anchor Learning with Potential Cluster Constraints for Multi-view Clustering (25 citations)
- Fast Incomplete Multi-view Clustering with Adaptive Similarity Completion and Reconstruction (9 citations)
- One Node One Model: Featuring the Missing-Half for Graph Clustering (9 citations)
- Dimension Reduction with Locally Adjusted Graphs (6 citations)
- Destroy and Repair Using Hyper-Graphs for Routing (3 citations)
- GraSP: Simple Yet Effective Graph Similarity Predictions (3 citations)
- Highly Efficient Rotation-Invariant Spectral Embedding for Scalable Incomplete Multi-View Clustering (3 citations)
- Pre-Assignment Problem for Unique Minimum Vertex Cover on Bounded Clique-Width Graphs (2 citations)
- Learn2Aggregate: Supervised Generation of Chvatal-Gomory Cuts Using Graph Neural Networks (1 citation)
- Neuro-Guided Graph Search for Symbolic Regression (Student Abstract) (1 citation)
- Temporal Triadic Closure: Finding Dense Substructures in Social Networks That Evolve over Time (1 citation)
- 3DPGS: 3D Probabilistic Graph Search for Archaeological Piece Grouping
and 9 more in the interactive map.