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 571 篇，第 8 / 12 页

  1. ICLR 2025Structuring Benchmark into Knowledge Graphs to Assist Large Language Models in Retrieving and Designing Models
  2. ICLR 2025Subgraph Federated Learning for Local Generalization
  3. ICLR 2025Systematic Relational Reasoning With Epistemic Graph Neural Networks
  4. ICLR 2025TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models
  5. ICLR 2025The Computational Complexity of Positive Non-Clashing Teaching in Graphs
  6. ICLR 2025The Effectiveness of Curvature-Based Rewiring and the Role of Hyperparameters in GNNs Revisited
  7. ICLR 2025Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation
  8. ICLR 2025Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity
  9. ICLR 2025Topological Zigzag Spaghetti for Diffusion-based Generation and Prediction on Graphs
  10. ICLR 2025Towards a Complete Logical Framework for GNN Expressiveness
  11. ICLR 2025Towards Automated Knowledge Integration From Human-Interpretable Representations
  12. ICLR 2025Towards Bridging Generalization and Expressivity of Graph Neural Networks
  13. ICLR 2025Towards Continuous Reuse of Graph Models via Holistic Memory Diversification
  14. ICLR 2025Towards Explaining the Power of Constant-depth Graph Neural Networks for Structured Linear Programming
  15. ICLR 2025Towards Fast, Specialized Machine Learning Force Fields: Distilling Foundation Models via Energy Hessians
  16. ICLR 2025Towards Synergistic Path-based Explanations for Knowledge Graph Completion: Exploration and Evaluation
  17. ICLR 2025Training-Free Message Passing for Learning on Hypergraphs
  18. ICLR 2025Uncovering Overfitting in Large Language Model Editing
  19. ICLR 2025Understanding Virtual Nodes: Oversquashing and Node Heterogeneity
  20. ICLR 2025Unsupervised Multiple Kernel Learning for Graphs via Ordinality Preservation
  21. ICLR 2025Valid Conformal Prediction for Dynamic GNNs
  22. ICLR 2025What Are Good Positional Encodings for Directed Graphs?
  23. ICLR 2025When Graph Neural Networks Meet Dynamic Mode Decomposition
  24. ICLR 2024A Characterization Theorem for Equivariant Networks with Point-wise Activations
  25. ICLR 2024A Differentially Private Clustering Algorithm for Well-Clustered Graphs
  26. ICLR 2024A Good Learner can Teach Better: Teacher-Student Collaborative Knowledge Distillation
  27. ICLR 2024A Poincaré Inequality and Consistency Results for Signal Sampling on Large Graphs
  28. ICLR 2024A Topological Perspective on Demystifying GNN-Based Link Prediction Performance
  29. ICLR 2024Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts
  30. ICLR 2024Approximately Piecewise E(3) Equivariant Point Networks
  31. ICLR 2024Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual Information
  32. ICLR 2024Beyond Spatio-Temporal Representations: Evolving Fourier Transform for Temporal Graphs
  33. ICLR 2024BioBridge: Bridging Biomedical Foundation Models via Knowledge Graphs
  34. ICLR 2024Boosting the Adversarial Robustness of Graph Neural Networks: An OOD Perspective
  35. ICLR 2024Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attacks
  36. ICLR 2024Causality-Inspired Spatial-Temporal Explanations for Dynamic Graph Neural Networks
  37. ICLR 2024Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources
  38. ICLR 2024Clifford Group Equivariant Simplicial Message Passing Networks
  39. ICLR 2024Confidential-DPproof: Confidential Proof of Differentially Private Training
  40. ICLR 2024Conformal Inductive Graph Neural Networks
  41. ICLR 2024Consistency Training with Learnable Data Augmentation for Graph Anomaly Detection with Limited Supervision
  42. ICLR 2024Constraint-Free Structure Learning with Smooth Acyclic Orientations
  43. ICLR 2024CoRe-GD: A Hierarchical Framework for Scalable Graph Visualization with GNNs
  44. ICLR 2024Counting Graph Substructures with Graph Neural Networks
  45. ICLR 2024Deceptive Fairness Attacks on Graphs via Meta Learning
  46. ICLR 2024Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks
  47. ICLR 2024DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models
  48. ICLR 2024DistillSpec: Improving Speculative Decoding via Knowledge Distillation
  49. ICLR 2024Effective Structural Encodings via Local Curvature Profiles
  50. ICLR 2024Efficient Subgraph GNNs by Learning Effective Selection Policies

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