知识图谱论文趋势 2023–2026

图谱嵌入与推理

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,715 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

知识图谱论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202376787261287
202415312010350426
20251541729941466
202613320114953536

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

全部知识图谱论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 1,715 篇，第 15 / 35 页

  1. ICLR 2025Rationalizing and Augmenting Dynamic Graph Neural Networks
  2. ICLR 2025Reasoning of Large Language Models over Knowledge Graphs with Super-Relations
  3. ICLR 2025Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval
  4. ICLR 2025Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNs
  5. ICLR 2025Recovering Manifold Structure Using Ollivier Ricci Curvature
  6. ICLR 2025Refine Knowledge of Large Language Models via Adaptive Contrastive Learning
  7. ICLR 2025Relation-Aware Diffusion for Heterogeneous Graphs with Partially Observed Features
  8. ICLR 2025Reliable and Diverse Evaluation of LLM Medical Knowledge Mastery
  9. ICLR 2025Residual Connections and Normalization Can Provably Prevent Oversmoothing in GNNs
  10. ICLR 2025Rethinking Graph Neural Networks From A Geometric Perspective Of Node Features
  11. ICLR 2025Revealing and Mitigating Over-Attention in Knowledge Editing
  12. ICLR 2025Revisiting Random Walks for Learning on Graphs
  13. ICLR 2025Scalable and Certifiable Graph Unlearning: Overcoming the Approximation Error Barrier
  14. ICLR 2025Scalable Influence and Fact Tracing for Large Language Model Pretraining
  15. ICLR 2025Scale-Free Graph-Language Models
  16. ICLR 2025SelKD: Selective Knowledge Distillation via Optimal Transport Perspective
  17. ICLR 2025Shapley-Guided Utility Learning for Effective Graph Inference Data Valuation
  18. ICLR 2025Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation
  19. ICLR 2025Single Teacher, Multiple Perspectives: Teacher Knowledge Augmentation for Enhanced Knowledge Distillation
  20. ICLR 2025SpaceGNN: Multi-Space Graph Neural Network for Node Anomaly Detection with Extremely Limited Labels
  21. ICLR 2025Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
  22. ICLR 2025Spectro-Riemannian Graph Neural Networks
  23. ICLR 2025Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling
  24. ICLR 2025Spreading Out-of-Distribution Detection on Graphs
  25. ICLR 2025ST-GCond: Self-supervised and Transferable Graph Dataset Condensation
  26. ICLR 2025StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization
  27. ICLR 2025Structuring Benchmark into Knowledge Graphs to Assist Large Language Models in Retrieving and Designing Models
  28. ICLR 2025Subgraph Federated Learning for Local Generalization
  29. ICLR 2025Systematic Relational Reasoning With Epistemic Graph Neural Networks
  30. ICLR 2025TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models
  31. ICLR 2025The Computational Complexity of Positive Non-Clashing Teaching in Graphs
  32. ICLR 2025The Effectiveness of Curvature-Based Rewiring and the Role of Hyperparameters in GNNs Revisited
  33. ICLR 2025Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation
  34. ICLR 2025Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity
  35. ICLR 2025Topological Zigzag Spaghetti for Diffusion-based Generation and Prediction on Graphs
  36. ICLR 2025Towards a Complete Logical Framework for GNN Expressiveness
  37. ICLR 2025Towards Automated Knowledge Integration From Human-Interpretable Representations
  38. ICLR 2025Towards Bridging Generalization and Expressivity of Graph Neural Networks
  39. ICLR 2025Towards Continuous Reuse of Graph Models via Holistic Memory Diversification
  40. ICLR 2025Towards Explaining the Power of Constant-depth Graph Neural Networks for Structured Linear Programming
  41. ICLR 2025Towards Fast, Specialized Machine Learning Force Fields: Distilling Foundation Models via Energy Hessians
  42. ICLR 2025Towards Synergistic Path-based Explanations for Knowledge Graph Completion: Exploration and Evaluation
  43. ICLR 2025Training-Free Message Passing for Learning on Hypergraphs
  44. ICLR 2025Uncovering Overfitting in Large Language Model Editing
  45. ICLR 2025Understanding Virtual Nodes: Oversquashing and Node Heterogeneity
  46. ICLR 2025Unsupervised Multiple Kernel Learning for Graphs via Ordinality Preservation
  47. ICLR 2025Valid Conformal Prediction for Dynamic GNNs
  48. ICLR 2025What Are Good Positional Encodings for Directed Graphs?
  49. ICLR 2025When Graph Neural Networks Meet Dynamic Mode Decomposition
  50. ICML 2025A Cognac Shot To Forget Bad Memories: Corrective Unlearning for Graph Neural Networks

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查知识图谱在 ICLR 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "knowledge-graphs"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「图与结构化数据」下的其他主题