知识图谱论文趋势 2023–2026

主要结论

• 知识图谱论文从 2023 年的 287 篇增长到 2026 年的 536 篇，三年间扩大到约 1.9 倍。
• ICLR 是发知识图谱论文最多的会议，2023–2026 年共 571 篇，占四个会议总量的 33%。
• 交叉方向里涨得最快的是多模态大模型：同时属于两个主题的论文从 2023 年的 17 篇增至 2026 年的 93 篇。
• 在「图与结构化数据」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的时间序列是 3.2 倍，知识图谱是 1.9 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026Aligning LLMs with Biomedical Knowledge using Balanced Fine-Tuning
• ICML 2026Belief Propagation Converges to Gaussian Distributions in Sparsely-Connected Factor Graphs
• ICLR 2026$\ell_1$ Latent Distance based Continuous-time Graph Representation
• CVPR 2026A Unified Framework for Knowledge Transfer in Bidirectional Model Scaling
• NeurIPS 2025A CLT for Polynomial GNNs on Community-Based Graphs
• ICML 2025A Selective Learning Method for Temporal Graph Continual Learning
• ICLR 2025$R^2$-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical Reasoning
• CVPR 2025A Hubness Perspective on Representation Learning for Graph-Based Multi-View Clustering
• NeurIPS 2024Can Large Language Models Analyze Graphs like Professionals? A Benchmark, Datasets and Models
• ICML 2024Bipartite Matching in Massive Graphs: A Tight Analysis of EDCS
• ICLR 2024A Good Learner can Teach Better: Teacher-Student Collaborative Knowledge Distillation
• CVPR 2024De-confounded Data-free Knowledge Distillation for Handling Distribution Shifts
• NeurIPS 2023A Comprehensive Study on Text-attributed Graphs: Benchmarking and Rethinking
• ICML 2023A Generalization of ViT/MLP-Mixer to Graphs
• ICLR 2023A Differential Geometric View and Explainability of GNN on Evolving Graphs
• CVPR 2023A Unified Knowledge Distillation Framework for Deep Directed Graphical Models
• NeurIPS 2026AT-SKM-Net: An Accelerated Trainable Sampling Kaczmarz-Motzkin Framework for Linear Hard-Constraint Feasibility on Dynamic Graphs
• ICML 2026Cross-Modal Knowledge Distillation without Paired Data: Theoretical Foundation and Algorithm
• ICLR 2026A Graph Meta-Network for Learning on Kolmogorov–Arnold Networks
• CVPR 2026Distilling Balanced Knowledge from a Biased Teacher

全部知识图谱论文

共 133 篇，第 1 / 3 页

1. NeurIPS 2026A New Perspective on Target-Conditioned Structural Dynamics for Link Prediction in Dynamic Graphs
2. NeurIPS 2026A Sparse Low-Rank Biclique Decomposition for Graphs
3. NeurIPS 2026A Unified Merge Calculus for Learning-Rate Scaling on Neural Computation Graphs
4. NeurIPS 2026ACER: Towards Generalizable Protein-ligand Co-folding
5. NeurIPS 2026Adaptive Gated Simplicial Propagation for Node Classification in Multimodal Graphs
6. NeurIPS 2026AgentCBO: Causal Belief Routing for Bayesian Optimization under Unknown Graphs
7. NeurIPS 2026Aligning LLMs with Biomedical Knowledge using Balanced Fine-Tuning
8. NeurIPS 2026Approaching Effective Merging in Model Embedding Space
9. NeurIPS 2026Argument Graph Uncertainty: Quantifying Uncertainty from the Logical Structure of Reasoning Chains
10. NeurIPS 2026ARK: A Dual-Axis Multimodal Retrieval Benchmark along Reasoning and Knowledge
11. NeurIPS 2026Ask KG Agent: A Multi-Agent Framework for Code Localization Using Code and Knowledge Graphs
12. NeurIPS 2026AT-SKM-Net: An Accelerated Trainable Sampling Kaczmarz-Motzkin Framework for Linear Hard-Constraint Feasibility on Dynamic Graphs
13. NeurIPS 2026Benchmarking Vietnamese Legal Knowledge of Large Language Models
14. NeurIPS 2026BootstrapAgent: Turning Repository Setup into Reusable Agent Knowledge
15. NeurIPS 2026Bridging Graph Worlds: Neural Approximation of Gromov-Wasserstein Distances
16. NeurIPS 2026Bridging Structure and Language: Graph-Based Visual Reasoning for Autonomous Road Understanding
17. NeurIPS 2026Capacity Allocation at the Source: Sparse Target Optimization for LLM Knowledge Editing
18. NeurIPS 2026Circuit-Level Knowledge Distillation for Large Language Models
19. NeurIPS 2026Codebook-Guided Cross-Modal Knowledge Distillation for Structurally Heterogeneous Features
20. NeurIPS 2026ColdDDI: Evaluating Knowledge Utilization in Cold-Start Drug-Drug Interaction Prediction
21. NeurIPS 2026Combating Catastrophic Forgetting in Continual Domain Adaptation via Knowledge Recasting
22. NeurIPS 2026Contractive Monoids: The Algebra Behind Stable Residual Propagation in Deep Graph Neural Networks
23. NeurIPS 2026Correspondence Pruning by Iterative Structural Rectification
24. NeurIPS 2026Cross-Domain Knowledge Separation and Positive Transmission for Noisy Domain Incremental Learning
25. NeurIPS 2026Deep Gaussian Processes on Directed Acyclic Graphs
26. NeurIPS 2026Deep Research as Rubric
27. NeurIPS 2026Despa: Resolving Spatial Collapse in VLMs via Depth-Grounded Geometry
28. NeurIPS 2026Distilling Graph Geometry: Knowledge Gap from GNNs to MLPs
29. NeurIPS 2026Do Graph Neural Networks Learn Generalizable Algorithms for Clustering Graphs?
30. NeurIPS 2026Drive vs. Decay: On the Training Dynamics of Joint-Embedding Predictive Architectures
31. NeurIPS 2026Echo-SAM: Zero-Shot Learning of Unseen Structures via Medical Knowledge Graph Grounding
32. NeurIPS 2026Effective Knowledge Conflict Detection via Joint Agentic Optimization
33. NeurIPS 2026Explanations over Graphs: An Agent Architecture for IT Enterprise Diagnostic Tasks
34. NeurIPS 2026Fast Algorithms for the Label Propagation Operator on Signed Graphs
35. NeurIPS 2026Faster Dynamic Graph Clustering with Hierarchical Graph Contraction
36. NeurIPS 2026FedProG: Federated Graph Learning via Server-Side LLM Semantic Bridging and Uncertainty-Aware Distillation
37. NeurIPS 2026FedVaccine: Knowledge Recall after Spatial-Temporal Catastrophic Forgetting in Federated Continual Learning via Gradient-Based Vaccine
38. NeurIPS 2026FlyAOC: Evaluating Agentic Ontology Curation of Drosophila Scientific Knowledge Bases
39. NeurIPS 2026Fractal-G: Topology-Aware Heterogeneous Graphs for Medical Image Segmentation
40. NeurIPS 2026FrED: External Data Influence Estimation via Domain Knowledge Graph Grounding
41. NeurIPS 2026Gaeta-Lie Neural SDEs: Symmetry-Regularized Learning of Stochastic Dynamics
42. NeurIPS 2026GEM: Interpretable Language Models via Geometric Embedding Alignment
43. NeurIPS 2026GenZ: Hybrid statistical–foundational models for knowledge discovery from real-valued multidimensional targets
44. NeurIPS 2026GIST: Gauge-Invariant Spectral Transformers for Scalable Graph Neural Operators
45. NeurIPS 2026Gradient-based Graph Structure Optimisation for Research Networks
46. NeurIPS 2026GRAPHLCP: Structure-Aware Localized Conformal Prediction on Graphs
47. NeurIPS 2026HiddenPathQA: A Benchmark for Knowledge Graph Question Answering When Questions Hide Their Paths
48. NeurIPS 2026Hierarchical Regime-Conditioned Dynamics for Spatiotemporal Graphs
49. NeurIPS 2026How well behaved is finite dimensional Diffusion Maps embedding?
50. NeurIPS 2026Hydra: Towards Transferable Multi-Task Learning on Temporal Graphs

常见问题

2023–2026 年四大会议一共有多少篇知识图谱论文？

共 1,715 篇，按年份分别是 2023 年 287 篇、2024 年 426 篇、2025 年 466 篇、2026 年 536 篇。

NeurIPS 2026 有多少篇知识图谱论文？

NeurIPS 2026 有 133 篇知识图谱论文，上一届是 154 篇。

ICLR 2026 有多少篇知识图谱论文？

ICLR 2026 有 201 篇知识图谱论文，上一届是 172 篇。

ICML 2026 有多少篇知识图谱论文？

ICML 2026 有 149 篇知识图谱论文，上一届是 99 篇。

CVPR 2026 有多少篇知识图谱论文？

CVPR 2026 有 53 篇知识图谱论文，上一届是 41 篇。

哪个会议的知识图谱论文最多？

ICLR，2023–2026 年共 571 篇。