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 149 篇，第 1 / 3 页

1. ICML 2026$G^2$-Reader: Dual Evolving Graphs for Multimodal Document QA
2. ICML 2026A Graph Foundation Model with Cross-Modal Alignment and Modality-Aware Expert Fusion for Multi-Modal Graphs
3. ICML 2026A Graphop Analysis of Graph Neural Networks on Sparse Graphs: Generalization and Universal Approximation
4. ICML 2026A Tale of Two Graphs: Separating Knowledge Exploration from Outline Structure for Open-Ended Deep Research
5. ICML 2026A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions
6. ICML 2026A Unifying Relational Perspective on Expressive Lottery Tickets
7. ICML 2026Adapting to Evolving Graphs: A Scalable Framework for Dynamic Coarsening
8. ICML 2026Adaptive Memory Retention in Dynamic Graphs
9. ICML 2026Adaptive Recurrent Message Passing for Test Time Computing on Graphs
10. ICML 2026An Approximation Algorithm for Graph Label Selection
11. ICML 2026Anchor-guided Hypergraph Condensation with Dual-level Discrimination
12. ICML 2026Any-dimensional invariant universality
13. ICML 2026AnyEdit++: Adaptive Long-Form Knowledge Editing via Bayesian Surprise
14. ICML 2026Backjump-on-Graph: Empowering Large Language Models with Reinforced Retrospective Exploration for Agentic Knowledge Graph Reasoning
15. ICML 2026Belief Propagation Converges to Gaussian Distributions in Sparsely-Connected Factor Graphs
16. ICML 2026Beyond Explicit Edges: Robust Reasoning over Noisy and Sparse Knowledge Graphs
17. ICML 2026Beyond Extrapolation: Knowledge Utilization Paradigm with Bidirectional Inspiration for Time Series Forecasting
18. ICML 2026Beyond Model Base Retrieval: Weaving Knowledge to Master Fine-grained Neural Network Design
19. ICML 2026BlitzRank: Principled Zero-shot Ranking Agents with Tournament Graphs
20. ICML 2026Boundary Embedding Shaping with Adaptive Contrastive Learning for Graph Structural Disentanglement
21. ICML 2026Breaking the Scale Barrier: One-Shot Knowledge Transfer via Frequency Transform
22. ICML 2026Bridging Structure and Semantics: Uncertainty-Modulated Dual-Path Diffusion for Robust Text-Attributed Graph Learning
23. ICML 2026Calibrated Knowledge Aggregation in Bayesian Mixture-of-Experts for Continual VQA
24. ICML 2026CausalRAG2: Hierarchical Causal Knowledge Graph Design for RAG
25. ICML 2026CL-GCL: Comprehensive and Lightweight Graph Contrastive Learning
26. ICML 2026Clustering as Reasoning: A $k$-Means Interpretation of Chain-of-Thought Graph Learning
27. ICML 2026Collapsed Effective Operators for Higher-order Structures
28. ICML 2026Conformal Path Reasoning: Trustworthy Knowledge Graph Question Answering via Path-Level Calibration
29. ICML 2026Continual Model Routing in Evolving Model Hubs
30. ICML 2026Cross-Modal Knowledge Distillation without Paired Data: Theoretical Foundation and Algorithm
31. ICML 2026DANCE: Dynamic, Available, Neighbor-gated Condensation for Federated Text-Attributed Graphs
32. ICML 2026Deep neural networks divide and conquer dihedral multiplication
33. ICML 2026Discrete Survival Knowledge Distillation for Competing Risks Analysis
34. ICML 2026Discriminative Mixture-of-Experts on Graphs with Reliable Expert Fusion
35. ICML 2026Dispersion Loss Counteracts Embedding Condensation and Improves Generalization in Small Language Models
36. ICML 2026Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning
37. ICML 2026DNA: Uncovering Universal Latent Forgery Knowledge
38. ICML 2026DTKG: Dual-Track Knowledge Graph-Verified Reasoning Framework for Multi-Hop QA
39. ICML 2026Dynamics Reveals Structure: Challenging the Linear Propagation Assumption
40. ICML 2026EmBrace: A Collective Knowledge Fusion Framework Toward Unified EEG Foundation Models
41. ICML 2026Entropy-aware Span-Constrained Optimal Transport for Robust Cross-Tokenizer Knowledge Distillation
42. ICML 2026ERAlign: Energy-based Representation Alignment of GNNs and LLMs on Text-attributed Graphs
43. ICML 2026Expressive Graph Neural Networks via Equivariant Use of Noise
44. ICML 2026Faithful Relational Reasoning with Region-based Embeddings: Expressivity of Convex Coordinate-wise Models
45. ICML 2026Fast Estimation for Forest Matrix of Signed Graphs
46. ICML 2026Fast Mixture of Curvature-Aware Experts for Diverse and Dynamic Graph Topologies
47. ICML 2026Finding the Minimal Parameter Budget for Implicit Reasoning: A Data Complexity Driven Scaling Law for Language Models
48. ICML 2026Fix the Mind, Not the Move: Interpretable AI Assistance via Knowledge-Gap Localization
49. ICML 2026FlatLand: Personalized Graph Federated Learning via Tailored Lorentz Space
50. ICML 2026FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment

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。