NeurIPS 2024 accepted papers on Graph learning
184 of the 4,560 papers accepted at NeurIPS 2024 (4.0%) are on Graph learning, compared with 5.0% at NeurIPS 2023. They fall into 4 topics.
See NeurIPS 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 · 77 papers
- Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification (33 citations)
- PowerGraph: A power grid benchmark dataset for graph neural networks (11 citations)
- LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddings (10 citations)
- Unifying Homophily and Heterophily for Spectral Graph Neural Networks via Triple Filter Ensembles (9 citations)
- Can Graph Learning Improve Planning in LLM-based Agents? (8 citations)
- RelBench: A Benchmark for Deep Learning on Relational Databases (8 citations)
- Are High-Degree Representations Really Unnecessary in Equivariant Graph Neural Networks? (7 citations)
- Boosting Graph Pooling with Persistent Homology (6 citations)
- Mixture of Link Predictors on Graphs (6 citations)
- On the Scalability of GNNs for Molecular Graphs (6 citations)
- GraphTrail: Translating GNN Predictions into Human-Interpretable Logical Rules (5 citations)
- Non-convolutional graph neural networks. (5 citations)
and 65 more in the interactive map.
Graph self-supervised learning · 49 papers
- Exploitation of a Latent Mechanism in Graph Contrastive Learning: Representation Scattering (9 citations)
- FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preference (8 citations)
- GFT: Graph Foundation Model with Transferable Tree Vocabulary (8 citations)
- Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insights (8 citations)
- Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure Learning (6 citations)
- Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedy (6 citations)
- UniGAD: Unifying Multi-level Graph Anomaly Detection (6 citations)
- Generative Semi-supervised Graph Anomaly Detection (5 citations)
- Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention (4 citations)
- FairWire: Fair Graph Generation (4 citations)
- GC-Bench: An Open and Unified Benchmark for Graph Condensation (4 citations)
- HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder for Graph Representation Learning (4 citations)
and 37 more in the interactive map.
Knowledge and temporal graphs · 30 papers
- G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering (74 citations)
- Long-range Brain Graph Transformer (14 citations)
- A Prompt-Based Knowledge Graph Foundation Model for Universal In-Context Reasoning (12 citations)
- Improving Temporal Link Prediction via Temporal Walk Matrix Projection (9 citations)
- TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs (9 citations)
- DTGB: A Comprehensive Benchmark for Dynamic Text-Attributed Graphs (8 citations)
- DECRL: A Deep Evolutionary Clustering Jointed Temporal Knowledge Graph Representation Learning Approach (6 citations)
- Learning Cooperative Trajectory Representations for Motion Forecasting (6 citations)
- Using Time-Aware Graph Neural Networks to Predict Temporal Centralities in Dynamic Graphs (6 citations)
- Clustering then Propagation: Select Better Anchors for Knowledge Graph Embedding (5 citations)
- Construction and Application of Materials Knowledge Graph in Multidisciplinary Materials Science via Large Language Model (5 citations)
- DisenGCD: A Meta Multigraph-assisted Disentangled Graph Learning Framework for Cognitive Diagnosis (5 citations)
and 18 more in the interactive map.
Graph algorithms and clustering · 28 papers
- Long-range Meta-path Search on Large-scale Heterogeneous Graphs (9 citations)
- A Structure-Aware Framework for Learning Device Placements on Computation Graphs (7 citations)
- Differentiable Structure Learning with Partial Orders (3 citations)
- Efficient Graph Matching for Correlated Stochastic Block Models (3 citations)
- The Map Equation Goes Neural: Mapping Network Flows with Graph Neural Networks (3 citations)
- Community Detection Guarantees using Embeddings Learned by Node2Vec (2 citations)
- Faster Local Solvers for Graph Diffusion Equations (2 citations)
- Graph Edit Distance with General Costs Using Neural Set Divergence (2 citations)
- Harnessing Multiple Correlated Networks for Exact Community Recovery (2 citations)
- Navigable Graphs for High-Dimensional Nearest Neighbor Search: Constructions and Limits (2 citations)
- Semantic Routing via Autoregressive Modeling (2 citations)
- Bayesian Optimization of Functions over Node Subsets in Graphs (1 citation)
and 16 more in the interactive map.