NeurIPS 2021 accepted papers on Graph learning
129 of the 2,508 papers accepted at NeurIPS 2021 (5.1%) are on Graph learning, compared with 4.9% at NeurIPS 2020. They fall into 4 topics.
See NeurIPS 2021 in the interactive map
Submitting to NeurIPS? Checklist →
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
GNN architectures · 54 papers
- Do Transformers Really Perform Badly for Graph Representation? (378 citations)
- Representing Long-Range Context for Graph Neural Networks with Global Attention (125 citations)
- GemNet: Universal Directional Graph Neural Networks for Molecules (123 citations)
- Rethinking Graph Transformers with Spectral Attention (70 citations)
- Federated Graph Classification over Non-IID Graphs (62 citations)
- Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods (59 citations)
- Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning (58 citations)
- Universal Graph Convolutional Networks (55 citations)
- Decoupling the Depth and Scope of Graph Neural Networks (51 citations)
- MagNet: A Neural Network for Directed Graphs (47 citations)
- Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction (46 citations)
- Dirichlet Energy Constrained Learning for Deep Graph Neural Networks (38 citations)
and 42 more in the interactive map.
Graph self-supervised learning · 28 papers
- Adversarial Graph Augmentation to Improve Graph Contrastive Learning (141 citations)
- OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs (119 citations)
- Subgraph Federated Learning with Missing Neighbor Generation (76 citations)
- Topology-Imbalance Learning for Semi-Supervised Node Classification (47 citations)
- Motif-based Graph Self-Supervised Learning for Molecular Property Prediction (44 citations)
- GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph (38 citations)
- Property-Aware Relation Networks for Few-Shot Molecular Property Prediction (36 citations)
- Disentangled Contrastive Learning on Graphs (33 citations)
- InfoGCL: Information-Aware Graph Contrastive Learning (32 citations)
- SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQL (27 citations)
- Topic Modeling Revisited: A Document Graph-based Neural Network Perspective (23 citations)
- Contrastive Laplacian Eigenmaps (22 citations)
and 16 more in the interactive map.
Graph algorithms and clustering · 27 papers
- NeuroLKH: Combining Deep Learning Model with Lin-Kernighan-Helsgaun Heuristic for Solving the Traveling Salesman Problem (44 citations)
- Reducing Collision Checking for Sampling-Based Motion Planning Using Graph Neural Networks (22 citations)
- A Bi-Level Framework for Learning to Solve Combinatorial Optimization on Graphs (15 citations)
- Differentiable Unsupervised Feature Selection based on a Gated Laplacian (14 citations)
- Correlated Stochastic Block Models: Exact Graph Matching with Applications to Recovering Communities (13 citations)
- Graphical Models in Heavy-Tailed Markets (12 citations)
- Slow Learning and Fast Inference: Efficient Graph Similarity Computation via Knowledge Distillation (10 citations)
- Spectral embedding for dynamic networks with stability guarantees (7 citations)
- Exponential Graph is Provably Efficient for Decentralized Deep Training (5 citations)
- KS-GNN: Keywords Search over Incomplete Graphs via Graphs Neural Network (4 citations)
- Residual2Vec: Debiasing graph embedding with random graphs (4 citations)
- Implicit SVD for Graph Representation Learning (3 citations)
and 15 more in the interactive map.
Knowledge and temporal graphs · 20 papers
- Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction (113 citations)
- Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attention (72 citations)
- ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs (44 citations)
- INDIGO: GNN-Based Inductive Knowledge Graph Completion Using Pair-Wise Encoding (31 citations)
- Neural Production Systems (20 citations)
- Predicting Molecular Conformation via Dynamic Graph Score Matching (18 citations)
- Distilling Meta Knowledge on Heterogeneous Graph for Illicit Drug Trafficker Detection on Social Media (16 citations)
- Adaptive Data Augmentation on Temporal Graphs (15 citations)
- Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones (11 citations)
- DEBAGREEMENT: A comment-reply dataset for (dis)agreement detection in online debates (10 citations)
- Rot-Pro: Modeling Transitivity by Projection in Knowledge Graph Embedding (9 citations)
- Coupled Segmentation and Edge Learning via Dynamic Graph Propagation (5 citations)
and 8 more in the interactive map.
