Deep learning · graph neural networks papers, 2023–2026

Key findings

• Deep learning · graph neural networks fell from 728 papers in 2023 to 326 in 2026, so interest is cooling.
• NeurIPS publishes the most Deep learning · graph neural networks work: 842 papers from 2023 to 2026, 51% of the four-venue total.
• The fastest-growing overlap is with Datasets and Benchmarks: papers tagged with both rose from 9 in 2023 to 20 in 2026.
• Among the 11 topics under Deep Learning, it ranks #5 by 2026 paper count; the fastest grower in the group, Diffusion Models, is up 4.1x versus 0.4x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026A New Perspective on Target-Conditioned Structural Dynamics for Link Prediction in Dynamic Graphs
• ICML 2026A Graph Foundation Model with Cross-Modal Alignment and Modality-Aware Expert Fusion for Multi-Modal Graphs
• ICLR 2026Laplacian Kernelized Bandit
• CVPR 2026Gamba Mamba-based graph convolutional network with dynamic graph topology learning
• NeurIPS 2025Depth-Width Tradeoffs for Transformers on Graph Tasks
• ICML 2025A Cognac Shot To Forget Bad Memories: Corrective Unlearning for Graph Neural Networks
• ICLR 2025Factor Graph-based Interpretable Neural Networks
• CVPR 2025Coeff-Tuning: A Graph Filter Subspace View for Tuning Attention-Based Large Models
• NeurIPS 2024[Re] GNNInterpreter: A probabilistic generative model-level explanation for Graph Neural Networks
• ICML 2024A Graph is Worth $K$ Words: Euclideanizing Graph using Pure Transformer
• ICLR 2024A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks
• CVPR 2024Learning Structure-from-Motion with Graph Attention Networks
• NeurIPS 2023[Re] On Explainability of Graph Neural Networks via Subgraph Explorations
• ICML 2023A Gromov--Wasserstein Geometric View of Spectrum-Preserving Graph Coarsening
• ICLR 2023Anti-Symmetric DGN: a stable architecture for Deep Graph Networks
• CVPR 2023An Actor-Centric Causality Graph for Asynchronous Temporal Inference in Group Activity
• NeurIPS 2026A Topological Encoder Decoder Framework for Temporal Graph Learning
• ICML 2026A Graphop Analysis of Graph Neural Networks on Sparse Graphs: Generalization and Universal Approximation
• ICLR 2026GTool: Graph Enhanced Tool Planning with Large Language Model
• CVPR 2026GSNR Graph Smooth Null-Space Representation for Inverse Problems

All Deep learning · graph neural networks papers

533 papers, page 4 of 11

151. ICML 2026Supervised Graph Contrastive Learning for Gene Regulatory Networks
152. ICML 2026SWING: Unlocking Implicit Graph Representations for Graph Random Features
153. ICML 2026Target-Oriented Pretraining Data Selection via Neuron-Activated Graph
154. ICML 2026TINNs: Time-Induced Neural Networks for Solving Time-Dependent PDEs
155. ICML 2026Towards Generative Graph Matching for Graph Edit Distance Computation
156. ICML 2026Towards Hierarchy–Uniformity Equilibrium: Recovering Semantic Depth in Hypergraph Contrastive Learning
157. ICML 2026Transformers Provably Learn Algorithmic Solutions for Graph Connectivity, But Only with the Right Data
158. ICML 2026Uncertainty-Constrained Trustworthiness for Graph Learning
159. ICML 2026Understanding Truncated Positional Encodings for Graph Neural Networks
160. ICML 2026Unitary Convolutions for Message-passing and Positional Encodings on Directed Graphs
161. ICML 2026VDW-GNNs: Vector diffusion wavelets for geometric graph neural networks
162. ICML 2026Verified SHAP: Provable Bounds for Exact Shapley Values of Neural Networks
163. ICML 2026View Space: Learning Representation across Arbitrary Graphs
164. ICML 2026What Information Matters? Graph Out-of-Distribution Detection via Tri-Component Information Decomposition
165. ICML 2026What Makes a Desired Graph for Relational Deep Learning?
166. ICML 2026When Do Graph Foundation Models Transfer? A Data-Centric Theory
167. ICML 2026Which Algorithms Can Graph Neural Networks Learn?
168. ICML 2026Why Are Linear RNNs More Parallelizable?
169. ICML 2025A Cognac Shot To Forget Bad Memories: Corrective Unlearning for Graph Neural Networks
170. ICML 2025A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Attention Networks
171. ICML 2025A General Graph Spectral Wavelet Convolution via Chebyshev Order Decomposition
172. ICML 2025A Manifold Perspective on the Statistical Generalization of Graph Neural Networks
173. ICML 2025A Recipe for Causal Graph Regression: Confounding Effects Revisited
174. ICML 2025Adapting Precomputed Features for Efficient Graph Condensation
175. ICML 2025Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreaching
176. ICML 2025Adversarial Combinatorial Semi-bandits with Graph Feedback
177. ICML 2025Aggregation Buffer: Revisiting DropEdge with a New Parameter Block
178. ICML 2025Analytical Construction on Geometric Architectures: Transitioning from Static to Temporal Link Prediction
179. ICML 2025Attention Mechanisms Perspective: Exploring LLM Processing of Graph-Structured Data
180. ICML 2025AutoGFM: Automated Graph Foundation Model with Adaptive Architecture Customization
181. ICML 2025Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based Centrality
182. ICML 2025Best of Both Worlds: Advantages of Hybrid Graph Sequence Models
183. ICML 2025Beyond Message Passing: Neural Graph Pattern Machine
184. ICML 2025Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspective
185. ICML 2025Boosting Protein Graph Representations through Static-Dynamic Fusion
186. ICML 2025Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellence
187. ICML 2025CEGA: A Cost-Effective Approach for Graph-Based Model Extraction and Acquisition
188. ICML 2025Commute Graph Neural Networks
189. ICML 2025COMRECGC: Global Graph Counterfactual Explainer through Common Recourse
190. ICML 2025Cooperation of Experts: Fusing Heterogeneous Information with Large Margin
191. ICML 2025Covered Forest: Fine-grained generalization analysis of graph neural networks
192. ICML 2025CSG-ODE: ControlSynth Graph ODE For Modeling Complex Evolution of Dynamic Graphs
193. ICML 2025CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection
194. ICML 2025De-coupled NeuroGF for Shortest Path Distance Approximations on Large Terrain Graphs
195. ICML 2025Delay-DSGN: A Dynamic Spiking Graph Neural Network with Delay Mechanisms for Evolving Graph
196. ICML 2025Directed Graph Grammars for Sequence-based Learning
197. ICML 2025Discrete Neural Algorithmic Reasoning
198. ICML 2025Disentangled Graph Spectral Domain Adaptation
199. ICML 2025Disentangling Invariant Subgraph via Variance Contrastive Estimation under Distribution Shifts
200. ICML 2025Diss-l-ECT: Dissecting Graph Data with Local Euler Characteristic Transforms

FAQ

How many Deep learning · graph neural networks papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

1,648 in total: 728 in 2023, 297 in 2024, 297 in 2025, 326 in 2026.

How many Deep learning · graph neural networks papers are at NeurIPS 2026?

NeurIPS 2026 has 102 Deep learning · graph neural networks papers, versus 91 the year before.

How many Deep learning · graph neural networks papers are at ICLR 2026?

ICLR 2026 has 32 Deep learning · graph neural networks papers, versus 50 the year before.

How many Deep learning · graph neural networks papers are at ICML 2026?

ICML 2026 has 168 Deep learning · graph neural networks papers, versus 141 the year before.

How many Deep learning · graph neural networks papers are at CVPR 2026?

CVPR 2026 has 24 Deep learning · graph neural networks papers, versus 15 the year before.

Which conference publishes the most Deep learning · graph neural networks papers?

NeurIPS, with 842 papers from 2023 to 2026.