ICML 2023 accepted papers on Graph learning
116 of the 1,865 papers accepted at ICML 2023 (6.2%) are on Graph learning, compared with 5.4% at ICML 2022. They fall into 4 topics.
See ICML 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 · 60 papers
- On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topology (29 citations)
- Reducing SO(3) Convolutions to SO(2) for Efficient Equivariant GNNs (28 citations)
- On the Expressive Power of Geometric Graph Neural Networks (24 citations)
- Graph Inductive Biases in Transformers without Message Passing (15 citations)
- Beyond Homophily: Reconstructing Structure for Graph-agnostic Clustering (14 citations)
- Revisiting Over-smoothing and Over-squashing Using Ollivier-Ricci Curvature (12 citations)
- Finding the Missing-half: Graph Complementary Learning for Homophily-prone and Heterophily-prone Graphs (10 citations)
- CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive Graph Classification (9 citations)
- Efficient Approximations of Complete Interatomic Potentials for Crystal Property Prediction (9 citations)
- On the Connection Between MPNN and Graph Transformer (9 citations)
- Graph Neural Networks with Learnable and Optimal Polynomial Bases (8 citations)
- A Generalization of ViT/MLP-Mixer to Graphs (7 citations)
and 48 more in the interactive map.
Graph self-supervised learning · 27 papers
- Efficiently predicting high resolution mass spectra with graph neural networks (26 citations)
- Conditional Graph Information Bottleneck for Molecular Relational Learning (13 citations)
- SEGA: Structural Entropy Guided Anchor View for Graph Contrastive Learning (5 citations)
- Spatial-Temporal Graph Learning with Adversarial Contrastive Adaptation (5 citations)
- Structural Re-weighting Improves Graph Domain Adaptation (5 citations)
- Autoregressive Diffusion Model for Graph Generation (4 citations)
- Graph Mixup with Soft Alignments (3 citations)
- Node Embedding from Neural Hamiltonian Orbits in Graph Neural Networks (3 citations)
- Efficient and Degree-Guided Graph Generation via Discrete Diffusion Modeling (2 citations)
- Graph Generative Model for Benchmarking Graph Neural Networks (2 citations)
- Hierarchical Grammar-Induced Geometry for Data-Efficient Molecular Property Prediction (2 citations)
- Leveraging Label Non-Uniformity for Node Classification in Graph Neural Networks (2 citations)
and 15 more in the interactive map.
Graph algorithms and clustering · 22 papers
- Deep Graph Representation Learning and Optimization for Influence Maximization (78 citations)
- Answering Complex Logical Queries on Knowledge Graphs via Query Computation Tree Optimization (6 citations)
- Dink-Net: Neural Clustering on Large Graphs (6 citations)
- D2Match: Leveraging Deep Learning and Degeneracy for Subgraph Matching (1 citation)
- StriderNet: A Graph Reinforcement Learning Approach to Optimize Atomic Structures on Rough Energy Landscapes (1 citation)
- Weighted Flow Diffusion for Local Graph Clustering with Node Attributes: an Algorithm and Statistical Guarantees (1 citation)
- A Gromov--Wasserstein Geometric View of Spectrum-Preserving Graph Coarsening
- ClusterFuG: Clustering Fully connected Graphs by Multicut
- Efficient Algorithms for Exact Graph Matching on Correlated Stochastic Block Models with Constant Correlation
- Fast Online Node Labeling for Very Large Graphs
- Generative Graph Dictionary Learning
- Moccasin: Efficient Tensor Rematerialization for Neural Networks
and 10 more in the interactive map.
Knowledge and temporal graphs · 7 papers
- InGram: Inductive Knowledge Graph Embedding via Relation Graphs (12 citations)
- Linkless Link Prediction via Relational Distillation (8 citations)
- Modeling Dynamic Environments with Scene Graph Memory (2 citations)
- Ske2Grid: Skeleton-to-Grid Representation Learning for Action Recognition (2 citations)
- What Makes Entities Similar? A Similarity Flooding Perspective for Multi-sourced Knowledge Graph Embeddings (1 citation)
- Quantifying Human Priors over Social and Navigation Networks
- HOPE: High-order Graph ODE For Modeling Interacting Dynamics