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 466 篇，第 6 / 10 页

  1. ICML 2025Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers
  2. ICML 2025Guided Structural Inference: Leveraging Priors with Soft Gating Mechanisms
  3. ICML 2025Hierarchical Overlapping Clustering on Graphs: Cost Function, Algorithm and Scalability
  4. ICML 2025Hierarchical Planning for Complex Tasks with Knowledge Graph-RAG and Symbolic Verification
  5. ICML 2025Homophily Enhanced Graph Domain Adaptation
  6. ICML 2025How Expressive are Knowledge Graph Foundation Models?
  7. ICML 2025Improving Soft Unification with Knowledge Graph Embedding Methods
  8. ICML 2025iN2V: Bringing Transductive Node Embeddings to Inductive Graphs
  9. ICML 2025Is Complex Query Answering Really Complex?
  10. ICML 2025KGMark: A Diffusion Watermark for Knowledge Graphs
  11. ICML 2025KIND: Knowledge Integration and Diversion for Training Decomposable Models
  12. ICML 2025Knowledge Retention in Continual Model-Based Reinforcement Learning
  13. ICML 2025Knowledge Swapping via Learning and Unlearning
  14. ICML 2025Knowledge-Guided Wasserstein Distributionally Robust Optimization
  15. ICML 2025Learn Beneficial Noise as Graph Augmentation
  16. ICML 2025Learning Condensed Graph via Differentiable Atom Mapping for Reaction Yield Prediction
  17. ICML 2025Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing
  18. ICML 2025MASS: Mathematical Data Selection via Skill Graphs for Pretraining Large Language Models
  19. ICML 2025Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding
  20. ICML 2025MemFreezing: A Novel Adversarial Attack on Temporal Graph Neural Networks under Limited Future Knowledge
  21. ICML 2025Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing
  22. ICML 2025Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification
  23. ICML 2025Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignment
  24. ICML 2025On the Power of Context-Enhanced Learning in LLMs
  25. ICML 2025Online Sparsification of Bipartite-Like Clusters in Graphs
  26. ICML 2025PAC Learning with Improvements
  27. ICML 2025Polynomial-Delay MAG Listing with Novel Locally Complete Orientation Rules
  28. ICML 2025Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks
  29. ICML 2025Position: Spectral GNNs Rely Less on Graph Fourier Basis than Conceived
  30. ICML 2025Positional Encoding meets Persistent Homology on Graphs
  31. ICML 2025Pre-Training Graph Contrastive Masked Autoencoders are Strong Distillers for EEG
  32. ICML 2025Primal-Dual Neural Algorithmic Reasoning
  33. ICML 2025Propagate and Inject: Revisiting Propagation-Based Feature Imputation for Graphs with Partially Observed Features
  34. ICML 2025Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing
  35. ICML 2025Retrieval-Augmented Language Model for Knowledge-aware Protein Encoding
  36. ICML 2025Right Time to Learn: Promoting Generalization via Bio-inspired Spacing Effect in Knowledge Distillation
  37. ICML 2025RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph Explanation
  38. ICML 2025Robust ML Auditing using Prior Knowledge
  39. ICML 2025SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models
  40. ICML 2025sciLaMA: A Single-Cell Representation Learning Framework to Leverage Prior Knowledge from Large Language Models
  41. ICML 2025SHARP-Distill: A 68× Faster Recommender System with Hypergraph Neural Networks and Language Models
  42. ICML 2025Sort Before You Prune: Improved Worst-Case Guarantees of the DiskANN Family of Graphs
  43. ICML 2025Speculate, then Collaborate: Fusing Knowledge of Language Models during Decoding
  44. ICML 2025Stability and Generalization Capability of Subgraph Reasoning Models for Inductive Knowledge Graph Completion
  45. ICML 2025Strengthen Out-of-Distribution Detection Capability with Progressive Self-Knowledge Distillation
  46. ICML 2025Structure Is All You Need: Structural Representation Learning on Hyper-Relational Knowledge Graphs
  47. ICML 2025Taming Knowledge Conflicts in Language Models
  48. ICML 2025TeDS: Joint Learning of Diachronic and Synchronic Perspectives in Quaternion Space for Temporal Knowledge Graph Completion
  49. ICML 2025Test-time Adaptation on Graphs via Adaptive Subgraph-based Selection and Regularized Prototypes
  50. ICML 2025The Generalized Skew Spectrum of Graphs

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