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 7 / 10 页

  1. ICML 2025TINED: GNNs-to-MLPs by Teacher Injection and Dirichlet Energy Distillation
  2. ICML 2025TMetaNet: Topological Meta-Learning Framework for Dynamic Link Prediction
  3. ICML 2025TopInG: Topologically Interpretable Graph Learning via Persistent Rationale Filtration
  4. ICML 2025Toward Data-centric Directed Graph Learning: An Entropy-driven Approach
  5. ICML 2025Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Trees
  6. ICML 2025Towards Understanding Parametric Generalized Category Discovery on Graphs
  7. ICML 2025Trusted Multi-View Classification with Expert Knowledge Constraints
  8. ICML 2025Uncertainty Estimation for Heterophilic Graphs Through the Lens of Information Theory
  9. ICML 2025Unifying Knowledge from Diverse Datasets to Enhance Spatial-Temporal Modeling: A Granularity-Adaptive Geographical Embedding Approach
  10. ICML 2025Weisfeiler and Leman Go Gambling: Why Expressive Lottery Tickets Win
  11. ICML 2025What Makes a Good Feedforward Computational Graph?
  12. ICML 2025When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Need
  13. NeurIPS 2025$\texttt{G1}$: Teaching LLMs to Reason on Graphs with Reinforcement Learning
  14. NeurIPS 2025A CLT for Polynomial GNNs on Community-Based Graphs
  15. NeurIPS 2025A Pre-training Framework for Relational Data with Information-theoretic Principles
  16. NeurIPS 2025A Signed Graph Approach to Understanding and Mitigating Oversmoothing
  17. NeurIPS 2025A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone
  18. NeurIPS 2025AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders
  19. NeurIPS 2025Adjusted Count Quantification Learning on Graphs
  20. NeurIPS 2025Angular Constraint Embedding via SpherePair Loss for Constrained Clustering
  21. NeurIPS 2025Black-Box Membership Inference Attack for LVLMs via Prior Knowledge-Calibrated Memory Probing
  22. NeurIPS 2025C$^2$Prompt: Class-aware Client Knowledge Interaction for Federated Continual Learning
  23. NeurIPS 2025Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?
  24. NeurIPS 2025Characterization and Learning of Causal Graphs from Hard Interventions
  25. NeurIPS 2025Co-Regularization Enhances Knowledge Transfer in High Dimensions
  26. NeurIPS 2025Codifying Character Logic in Role-Playing
  27. NeurIPS 2025Conditional Diffusion Anomaly Modeling on Graphs
  28. NeurIPS 2025Conflict-Aware Knowledge Editing in the Wild: Semantic-Augmented Graph Representation for Unstructured Text
  29. NeurIPS 2025Copresheaf Topological Neural Networks: A Generalized Deep Learning Framework
  30. NeurIPS 2025Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models
  31. NeurIPS 2025Curriculum Abductive Learning
  32. NeurIPS 2025Data Mixing Can Induce Phase Transitions in Knowledge Acquisition
  33. NeurIPS 2025DCA: Graph-Guided Deep Embedding Clustering for Brain Atlases
  34. NeurIPS 2025Deeper with Riemannian Geometry: Overcoming Oversmoothing and Oversquashing for Graph Foundation Models
  35. NeurIPS 2025DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer
  36. NeurIPS 2025Defining and Discovering Hyper-meta-paths for Heterogeneous Hypergraphs
  37. NeurIPS 2025Deliberation on Priors: Trustworthy Reasoning of Large Language Models on Knowledge Graphs
  38. NeurIPS 2025Democratizing Clinical Risk Prediction with Cross-Cohort Cross-Modal Knowledge Transfer
  39. NeurIPS 2025Dependency Matters: Enhancing LLM Reasoning with Explicit Knowledge Grounding
  40. NeurIPS 2025Diagnosing and Addressing Pitfalls in KG-RAG Datasets: Toward More Reliable Benchmarking
  41. NeurIPS 2025Distance Adaptive Beam Search for Provably Accurate Graph-Based Nearest Neighbor Search
  42. NeurIPS 2025Distribution Learning Meets Graph Structure Sampling
  43. NeurIPS 2025DKDR: Dynamic Knowledge Distillation for Reliability in Federated Learning
  44. NeurIPS 2025Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness
  45. NeurIPS 2025DuetGraph: Coarse-to-Fine Knowledge Graph Reasoning with Dual-Pathway Global-Local Fusion
  46. NeurIPS 2025DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs
  47. NeurIPS 2025Dynamic Bundling with Large Language Models for Zero-Shot Inference on Text-Attributed Graphs
  48. NeurIPS 2025Edit Less, Achieve More: Dynamic Sparse Neuron Masking for Lifelong Knowledge Editing in LLMs
  49. NeurIPS 2025Efficient Knowledge Transfer in Federated Recommendation for Joint Venture Ecosystem
  50. NeurIPS 2025Efficient Verified Unlearning For Distillation

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