ICLR 2025 accepted papers on Graph learning
151 of the 3,703 papers accepted at ICLR 2025 (4.1%) are on Graph learning, compared with 5.4% at ICLR 2024. They fall into 4 topics.
See ICLR 2025 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 · 76 papers
- HG-Adapter: Improving Pre-Trained Heterogeneous Graph Neural Networks with Dual Adapters (2 citations)
- Improving Graph Neural Networks by Learning Continuous Edge Directions (2 citations)
- MAGE: Model-Level Graph Neural Networks Explanations via Motif-based Graph Generation (2 citations)
- Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective (1 citation)
- Joint Graph Rewiring and Feature Denoising via Spectral Resonance (1 citation)
- KAA: Kolmogorov-Arnold Attention for Enhancing Attentive Graph Neural Networks (1 citation)
- Learning Efficient Positional Encodings with Graph Neural Networks (1 citation)
- PhyMPGN: Physics-encoded Message Passing Graph Network for spatiotemporal PDE systems (1 citation)
- Residual Connections and Normalization Can Provably Prevent Oversmoothing in GNNs (1 citation)
- Schur's Positive-Definite Network: Deep Learning in the SPD cone with structure (1 citation)
- The Effectiveness of Curvature-Based Rewiring and the Role of Hyperparameters in GNNs Revisited (1 citation)
- Training-Free Message Passing for Learning on Hypergraphs (1 citation)
and 64 more in the interactive map.
Graph self-supervised learning · 51 papers
- gRNAde: Geometric Deep Learning for 3D RNA inverse design (24 citations)
- Learning Molecular Representation in a Cell (6 citations)
- Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A Benchmark (2 citations)
- DiffGAD: A Diffusion-based Unsupervised Graph Anomaly Detector (1 citation)
- Fully-inductive Node Classification on Arbitrary Graphs (1 citation)
- How Do Large Language Models Understand Graph Patterns? A Benchmark for Graph Pattern Comprehension (1 citation)
- ICLR: In-Context Learning of Representations (1 citation)
- Pushing the Limits of All-Atom Geometric Graph Neural Networks: Pre-Training, Scaling, and Zero-Shot Transfer (1 citation)
- Advancing Graph Generation through Beta Diffusion
- AutoG: Towards automatic graph construction from tabular data
- Biologically Plausible Brain Graph Transformer
- BrainOOD: Out-of-distribution Generalizable Brain Network Analysis
and 39 more in the interactive map.
Graph algorithms and clustering · 13 papers
- Neural Spacetimes for DAG Representation Learning (2 citations)
- GOAL: A Generalist Combinatorial Optimization Agent Learner
- How Low Can You Go? Searching for the Intrinsic Dimensionality of Complex Networks using Metric Node Embeddings
- Learning Partial Graph Matching via Optimal Partial Transport
- Node Similarities under Random Projections: Limits and Pathological Cases
- Recovering Manifold Structure Using Ollivier Ricci Curvature
- A Graph Enhanced Symbolic Discovery Framework For Efficient Logic Optimization
- Analytic DAG Constraints for Differentiable DAG Learning
- Balanced Ranking with Relative Centrality: A multi-core periphery perspective
- Clique Number Estimation via Differentiable Functions of Adjacency Matrix Permutations
- Learning to Explore and Exploit with GNNs for Unsupervised Combinatorial Optimization
- Learning to Select Nodes in Branch and Bound with Sufficient Tree Representation
and 1 more in the interactive map.
Knowledge and temporal graphs · 11 papers
- Expand and Compress: Exploring Tuning Principles for Continual Spatio-Temporal Graph Forecasting (1 citation)
- TGB-Seq Benchmark: Challenging Temporal GNNs with Complex Sequential Dynamics (1 citation)
- GeSubNet: Gene Interaction Inference for Disease Subtype Network Generation
- Graph-based Document Structure Analysis
- Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generation
- Node-Time Conditional Prompt Learning in Dynamic Graphs
- Charting the Design Space of Neural Graph Representations for Subgraph Matching
- INFER: A Neural-symbolic Model For Extrapolation Reasoning on Temporal Knowledge Graph
- Systematic Relational Reasoning With Epistemic Graph Neural Networks
- Temporal Heterogeneous Graph Generation with Privacy, Utility, and Efficiency
- Towards Synergistic Path-based Explanations for Knowledge Graph Completion: Exploration and Evaluation