NeurIPS 2023 accepted papers on Graph learning
178 of the 3,584 papers accepted at NeurIPS 2023 (5.0%) are on Graph learning, compared with 5.0% at NeurIPS 2022. They fall into 4 topics.
See NeurIPS 2023 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
- Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarking (25 citations)
- Universal Prompt Tuning for Graph Neural Networks (20 citations)
- Uncertainty Quantification over Graph with Conformalized Graph Neural Networks (16 citations)
- Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All? (12 citations)
- Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling (12 citations)
- Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions (10 citations)
- Demystifying Oversmoothing in Attention-Based Graph Neural Networks (10 citations)
- Layer-Neighbor Sampling --- Defusing Neighborhood Explosion in GNNs (10 citations)
- A new perspective on building efficient and expressive 3D equivariant graph neural networks (9 citations)
- Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyond (9 citations)
- Sheaf Hypergraph Networks (9 citations)
- GNNEvaluator: Evaluating GNN Performance On Unseen Graphs Without Labels (8 citations)
and 65 more in the interactive map.
Graph self-supervised learning · 53 papers
- SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations (37 citations)
- GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning (26 citations)
- Towards Self-Interpretable Graph-Level Anomaly Detection (24 citations)
- A Comprehensive Study on Text-attributed Graphs: Benchmarking and Rethinking (22 citations)
- GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detection (19 citations)
- MuSe-GNN: Learning Unified Gene Representation From Multimodal Biological Graph Data (13 citations)
- Simple and Asymmetric Graph Contrastive Learning without Augmentations (12 citations)
- Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalization (10 citations)
- Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Data (9 citations)
- Truncated Affinity Maximization: One-class Homophily Modeling for Graph Anomaly Detection (9 citations)
- D4Explainer: In-distribution Explanations of Graph Neural Network via Discrete Denoising Diffusion (8 citations)
- SPA: A Graph Spectral Alignment Perspective for Domain Adaptation (8 citations)
and 41 more in the interactive map.
Knowledge and temporal graphs · 26 papers
- Temporal Graph Benchmark for Machine Learning on Temporal Graphs (22 citations)
- Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatment (16 citations)
- UUKG: Unified Urban Knowledge Graph Dataset for Urban Spatiotemporal Prediction (13 citations)
- A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphs (10 citations)
- NeuroGraph: Benchmarks for Graph Machine Learning in Brain Connectomics (9 citations)
- TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discovery (8 citations)
- Complex Query Answering on Eventuality Knowledge Graph with Implicit Logical Constraints (6 citations)
- Differentiable Neuro-Symbolic Reasoning on Large-Scale Knowledge Graphs (5 citations)
- Graph Neural Networks for Road Safety Modeling: Datasets and Evaluations for Accident Analysis (5 citations)
- Live Graph Lab: Towards Open, Dynamic and Real Transaction Graphs with NFT (5 citations)
- TFLEX: Temporal Feature-Logic Embedding Framework for Complex Reasoning over Temporal Knowledge Graph (5 citations)
- Equivariant Spatio-Temporal Attentive Graph Networks to Simulate Physical Dynamics (4 citations)
and 14 more in the interactive map.
Graph algorithms and clustering · 22 papers
- Unsupervised Learning for Solving the Travelling Salesman Problem (8 citations)
- Network Regression with Graph Laplacians (6 citations)
- A Graph-Theoretic Framework for Understanding Open-World Semi-Supervised Learning (4 citations)
- Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding (3 citations)
- Maximum Independent Set: Self-Training through Dynamic Programming (3 citations)
- Neural Multi-Objective Combinatorial Optimization with Diversity Enhancement (3 citations)
- Beyond Exponential Graph: Communication-Efficient Topologies for Decentralized Learning via Finite-time Convergence (2 citations)
- GraphMP: Graph Neural Network-based Motion Planning with Efficient Graph Search (2 citations)
- An Optimization-based Approach To Node Role Discovery in Networks: Approximating Equitable Partitions (1 citation)
- Exact Representation of Sparse Networks with Symmetric Nonnegative Embeddings (1 citation)
- Interpretable Graph Networks Formulate Universal Algebra Conjectures (1 citation)
- On Learning Necessary and Sufficient Causal Graphs (1 citation)
and 10 more in the interactive map.