ICLR 2026 accepted papers on Graph learning
144 of the 5,358 papers accepted at ICLR 2026 (2.7%) are on Graph learning, compared with 4.1% at ICLR 2025. They fall into 4 topics.
See ICLR 2026 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 · 52 papers
- Rapid Training of Hamiltonian Graph Networks Using Random Features (1 citation)
- A Graph Meta-Network for Learning on Kolmogorov–Arnold Networks
- AdS-GNN - a Conformally Equivariant Graph Neural Network
- Are we measuring oversmoothing in graph neural networks correctly?
- Beyond Simple Graphs: Neural Multi-Objective Routing on Multigraphs
- Can You Hear Me Now? A Benchmark for Long-Range Graph Propagation
- Cooperative Sheaf Neural Networks
- DHG-Bench: A Comprehensive Benchmark for Deep Hypergraph Learning
- Differentiable Lifting for Topological Neural Networks
- Directed Semi-Simplicial Learning with Applications to Brain Activity Decoding
- Directional Sheaf Hypergraph Networks: Unifying Learning on Directed and Undirected Hypergraphs
- FlowSymm: Physics–Aware, Symmetry–Preserving Graph Attention for Network Flow Completion
and 40 more in the interactive map.
Graph self-supervised learning · 51 papers
- A Brain Graph Foundation Model: Pre-Training and Prompt-Tuning across Broad Atlases and Disorders (1 citation)
- Relational Graph Transformer (1 citation)
- Actions Speak Louder than Prompts: A Large-Scale Study of LLMs for Graph Inference
- Beyond Structure: Invariant Crystal Property Prediction with Pseudo-Particle Ray Diffraction
- Bridging Input Feature Spaces Towards Graph Foundation Models
- CheckMate! Watermarking Graph Diffusion Models in Polynomial Time
- Discrete Bayesian Sample Inference for Graph Generation
- FSD-CAP: Fractional Subgraph Diffusion with Class-Aware Propagation for Graph Feature Imputation
- GDGB: A Benchmark for Generative Dynamic Text-Attributed Graph Learning
- Generating Directed Graphs with Dual Attention and Asymmetric Encoding
- GGBall: Graph Generative Model on Poincaré Ball
- Global-Recent Semantic Reasoning on Dynamic Text-Attributed Graphs with Large Language Models
and 39 more in the interactive map.
Knowledge and temporal graphs · 23 papers
- Adaptive Data-Knowledge Alignment in Genetic Perturbation Prediction
- Flock: A Knowledge Graph Foundation Model via Learning on Random Walks
- HGNet: Scalable Foundation Model for Automated Knowledge Graph Generation from Scientific Literature
- HYPER: A Foundation Model for Inductive Link Prediction with Knowledge Hypergraphs
- Inductive Reasoning for Temporal Knowledge Graphs with Emerging Entities
- Panoptic Pairwise Distortion Graph
- ProofFlow: A Dependency Graph Approach to Faithful Proof Autoformalization
- Query-Aware Flow Diffusion for Graph-Based RAG with Retrieval Guarantees
- TGM: A Modular and Efficient Library for Machine Learning on Temporal Graphs
- A General Spatio-Temporal Backbone with Scalable Contextual Pattern Bank for Urban Continual Forecasting
- Adaptive Mixture of Disentangled Experts for Dynamic Graphs under Distribution Shifts
- APT: Towards Universal Scene Graph Generation via Plug-in Adaptive Prompt Tuning
and 11 more in the interactive map.
Graph algorithms and clustering · 18 papers
- BoGrape: Bayesian optimization over graphs with shortest-path encoded (1 citation)
- FrontierCO: Real-World and Large-Scale Evaluation of Machine Learning Solvers for Combinatorial Optimization (1 citation)
- A Scalable Inter-edge Correlation Modeling in CopulaGNN for Link Sign Prediction
- DOPPLER: Dual-Policy Learning for Device Assignment in Asynchronous Dataflow Graphs
- Efficient Learning on Large Graphs using a Densifying Regularity Lemma
- Gelato: Graph Edit Distance via Autoregressive Neural Combinatorial Optimization
- Graph-based Nearest Neighbors with Dynamic Updates via Random Walks
- Learning from Algorithm Feedback: One-Shot SAT Solver Guidance with GNNs
- Neural Graduated Assignment for Maximum Common Edge Subgraphs
- PolyGraph Discrepancy: a classifier-based metric for graph generation
- A Hierarchical Circuit Symbolic Discovery Framework for Efficient Logic Optimization
- ConRep4CO: Contrastive Representation Learning of Combinatorial Optimization Instances across Types
and 6 more in the interactive map.