ICML 2024 accepted papers on Graph learning
141 of the 2,610 papers accepted at ICML 2024 (5.4%) are on Graph learning, compared with 6.2% at ICML 2023. They fall into 4 topics.
See ICML 2024 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
GNN architectures · 58 papers
- Hypergraph-enhanced Dual Semi-supervised Graph Classification (8 citations)
- How Universal Polynomial Bases Enhance Spectral Graph Neural Networks: Heterophily, Over-smoothing, and Over-squashing (7 citations)
- Networked Inequality: Preferential Attachment Bias in Graph Neural Network Link Prediction (5 citations)
- Graph External Attention Enhanced Transformer (4 citations)
- Cooperative Graph Neural Networks (3 citations)
- Expressivity and Generalization: Fragment-Biases for Molecular GNNs (3 citations)
- Graph Neural Networks Use Graphs When They Shouldn't (2 citations)
- Mitigating Label Noise on Graphs via Topological Sample Selection (2 citations)
- Neural SPH: Improved Neural Modeling of Lagrangian Fluid Dynamics (2 citations)
- PANDA: Expanded Width-Aware Message Passing Beyond Rewiring (2 citations)
- Verifying message-passing neural networks via topology-based bounds tightening (2 citations)
- An Empirical Study of Realized GNN Expressiveness (1 citation)
and 46 more in the interactive map.
Graph self-supervised learning · 38 papers
- Less is More: on the Over-Globalizing Problem in Graph Transformers (9 citations)
- Community-Invariant Graph Contrastive Learning (4 citations)
- Graph Positional and Structural Encoder (3 citations)
- Position: Graph Foundation Models Are Already Here (3 citations)
- Translating Subgraphs to Nodes Makes Simple GNNs Strong and Efficient for Subgraph Representation Learning (3 citations)
- Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformers (3 citations)
- Class-Imbalanced Graph Learning without Class Rebalancing (2 citations)
- Explaining Graph Neural Networks via Structure-aware Interaction Index (2 citations)
- Hyperbolic Geometric Latent Diffusion Model for Graph Generation (2 citations)
- LLaGA: Large Language and Graph Assistant (2 citations)
- Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks (2 citations)
- A Graph is Worth $K$ Words: Euclideanizing Graph using Pure Transformer (1 citation)
and 26 more in the interactive map.
Graph algorithms and clustering · 29 papers
- Gaussian Processes on Cellular Complexes (2 citations)
- Surprisingly Strong Performance Prediction with Neural Graph Features (2 citations)
- Differentiable Mapper for Topological Optimization of Data Representation (1 citation)
- LSEnet: Lorentz Structural Entropy Neural Network for Deep Graph Clustering (1 citation)
- MGit: A Model Versioning and Management System (1 citation)
- Multi-View Stochastic Block Models (1 citation)
- Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matching (1 citation)
- Probabilistic Routing for Graph-Based Approximate Nearest Neighbor Search (1 citation)
- Simulation of Graph Algorithms with Looped Transformers (1 citation)
- Bipartite Matching in Massive Graphs: A Tight Analysis of EDCS
- Cluster-Aware Similarity Diffusion for Instance Retrieval
- Convergence Guarantees for the DeepWalk Embedding on Block Models
and 17 more in the interactive map.
Knowledge and temporal graphs · 16 papers
- Position: Topological Deep Learning is the New Frontier for Relational Learning (8 citations)
- Position: Relational Deep Learning - Graph Representation Learning on Relational Databases (3 citations)
- KnowFormer: Revisiting Transformers for Knowledge Graph Reasoning (2 citations)
- CARTE: Pretraining and Transfer for Tabular Learning (1 citation)
- PGODE: Towards High-quality System Dynamics Modeling (1 citation)
- Scene Graph Generation Strategy with Co-occurrence Knowledge and Learnable Term Frequency (1 citation)
- Temporal Spiking Neural Networks with Synaptic Delay for Graph Reasoning (1 citation)
- DUPLEX: Dual GAT for Complex Embedding of Directed Graphs
- Generalizing Knowledge Graph Embedding with Universal Orthogonal Parameterization
- Long Range Propagation on Continuous-Time Dynamic Graphs
- OxyGenerator: Reconstructing Global Ocean Deoxygenation Over a Century with Deep Learning
- PAC-Bayesian Generalization Bounds for Knowledge Graph Representation Learning
and 4 more in the interactive map.