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 17 / 35 页

  1. ICML 2025Learn Beneficial Noise as Graph Augmentation
  2. ICML 2025Learning Condensed Graph via Differentiable Atom Mapping for Reaction Yield Prediction
  3. ICML 2025Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing
  4. ICML 2025MASS: Mathematical Data Selection via Skill Graphs for Pretraining Large Language Models
  5. ICML 2025Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding
  6. ICML 2025MemFreezing: A Novel Adversarial Attack on Temporal Graph Neural Networks under Limited Future Knowledge
  7. ICML 2025Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing
  8. ICML 2025Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification
  9. ICML 2025Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignment
  10. ICML 2025On the Power of Context-Enhanced Learning in LLMs
  11. ICML 2025Online Sparsification of Bipartite-Like Clusters in Graphs
  12. ICML 2025PAC Learning with Improvements
  13. ICML 2025Polynomial-Delay MAG Listing with Novel Locally Complete Orientation Rules
  14. ICML 2025Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks
  15. ICML 2025Position: Spectral GNNs Rely Less on Graph Fourier Basis than Conceived
  16. ICML 2025Positional Encoding meets Persistent Homology on Graphs
  17. ICML 2025Pre-Training Graph Contrastive Masked Autoencoders are Strong Distillers for EEG
  18. ICML 2025Primal-Dual Neural Algorithmic Reasoning
  19. ICML 2025Propagate and Inject: Revisiting Propagation-Based Feature Imputation for Graphs with Partially Observed Features
  20. ICML 2025Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing
  21. ICML 2025Retrieval-Augmented Language Model for Knowledge-aware Protein Encoding
  22. ICML 2025Right Time to Learn: Promoting Generalization via Bio-inspired Spacing Effect in Knowledge Distillation
  23. ICML 2025RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph Explanation
  24. ICML 2025Robust ML Auditing using Prior Knowledge
  25. ICML 2025SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models
  26. ICML 2025sciLaMA: A Single-Cell Representation Learning Framework to Leverage Prior Knowledge from Large Language Models
  27. ICML 2025SHARP-Distill: A 68× Faster Recommender System with Hypergraph Neural Networks and Language Models
  28. ICML 2025Sort Before You Prune: Improved Worst-Case Guarantees of the DiskANN Family of Graphs
  29. ICML 2025Speculate, then Collaborate: Fusing Knowledge of Language Models during Decoding
  30. ICML 2025Stability and Generalization Capability of Subgraph Reasoning Models for Inductive Knowledge Graph Completion
  31. ICML 2025Strengthen Out-of-Distribution Detection Capability with Progressive Self-Knowledge Distillation
  32. ICML 2025Structure Is All You Need: Structural Representation Learning on Hyper-Relational Knowledge Graphs
  33. ICML 2025Taming Knowledge Conflicts in Language Models
  34. ICML 2025TeDS: Joint Learning of Diachronic and Synchronic Perspectives in Quaternion Space for Temporal Knowledge Graph Completion
  35. ICML 2025Test-time Adaptation on Graphs via Adaptive Subgraph-based Selection and Regularized Prototypes
  36. ICML 2025The Generalized Skew Spectrum of Graphs
  37. ICML 2025TINED: GNNs-to-MLPs by Teacher Injection and Dirichlet Energy Distillation
  38. ICML 2025TMetaNet: Topological Meta-Learning Framework for Dynamic Link Prediction
  39. ICML 2025TopInG: Topologically Interpretable Graph Learning via Persistent Rationale Filtration
  40. ICML 2025Toward Data-centric Directed Graph Learning: An Entropy-driven Approach
  41. ICML 2025Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Trees
  42. ICML 2025Towards Understanding Parametric Generalized Category Discovery on Graphs
  43. ICML 2025Trusted Multi-View Classification with Expert Knowledge Constraints
  44. ICML 2025Uncertainty Estimation for Heterophilic Graphs Through the Lens of Information Theory
  45. ICML 2025Unifying Knowledge from Diverse Datasets to Enhance Spatial-Temporal Modeling: A Granularity-Adaptive Geographical Embedding Approach
  46. ICML 2025Weisfeiler and Leman Go Gambling: Why Expressive Lottery Tickets Win
  47. ICML 2025What Makes a Good Feedforward Computational Graph?
  48. ICML 2025When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Need
  49. NeurIPS 2025$\texttt{G1}$: Teaching LLMs to Reason on Graphs with Reinforcement Learning
  50. NeurIPS 2025A CLT for Polynomial GNNs on Community-Based 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