ICLR 2021 accepted papers on Graph learning
38 of the 860 papers accepted at ICLR 2021 (4.4%) are on Graph learning, compared with 7.1% at ICLR 2020. They fall into 4 topics.
See ICLR 2021 in the interactive map
Submitting to ICLR? 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 · 26 papers
- Combining Label Propagation and Simple Models out-performs Graph Neural Networks (127 citations)
- How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision (115 citations)
- How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks (110 citations)
- Adaptive Universal Generalized PageRank Graph Neural Network (92 citations)
- On the Bottleneck of Graph Neural Networks and its Practical Implications (89 citations)
- Degree-Quant: Quantization-Aware Training for Graph Neural Networks (71 citations)
- Accurate Learning of Graph Representations with Graph Multiset Pooling (68 citations)
- Retrieval-Augmented Generation for Code Summarization via Hybrid GNN (68 citations)
- Gauge Equivariant Mesh CNNs: Anisotropic convolutions on geometric graphs (44 citations)
- Analyzing the Expressive Power of Graph Neural Networks in a Spectral Perspective (42 citations)
- Directed Acyclic Graph Neural Networks (40 citations)
- Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking (37 citations)
and 14 more in the interactive map.
Knowledge and temporal graphs · 8 papers
- Explainable Subgraph Reasoning for Forecasting on Temporal Knowledge Graphs (70 citations)
- Complex Query Answering with Neural Link Predictors (38 citations)
- DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation Dialogues (19 citations)
- Learning to Deceive Knowledge Graph Augmented Models via Targeted Perturbation (9 citations)
- Spatio-Temporal Graph Scattering Transform (8 citations)
- Interpreting Knowledge Graph Relation Representation from Word Embeddings (7 citations)
- Lossless Compression of Structured Convolutional Models via Lifting (3 citations)
- Generative Scene Graph Networks
