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 8 / 35 页

  1. ICML 2026Neural Feature Geometry Evolves as Discrete Ricci Flow
  2. ICML 2026On Efficient Scaling of GNNs via IO-Aware Layers Implementations
  3. ICML 2026On the Origin of Neural Scaling Laws: from Random Graphs to Natural Language
  4. ICML 2026On the Spectral Unreachability of Brain Graph Learning
  5. ICML 2026On the Theoretical Limitations of Embedding-based Link Prediction
  6. ICML 2026PACER: Acyclic Causal Discovery from Large-scale Interventional Data
  7. ICML 2026PADD: Path-Aligned Decompression Distillation for Non-Router Teacher to Guide MoE Student Learning
  8. ICML 2026Parametrized Power-Iteration Clustering for Directed Graphs
  9. ICML 2026Plain Transformers are Surprisingly Powerful Link Predictors
  10. ICML 2026PPI Candidate Ranking: Large-Scale Evaluation of a Domain Knowledge–Guided Pipeline
  11. ICML 2026PromptDyG: Test-Time Prompt Adaptation on Dynamic Graphs
  12. ICML 2026Provable Accuracy Collapse of Embedding-Based Representations under Dimensionality Mismatch
  13. ICML 2026Quantifying Cross-Domain Knowledge Distillation in the Presence of Domain Shift
  14. ICML 2026REAL: Resolving Knowledge Conflicts in Knowledge-Intensive Visual Question Answering via Reasoning-Pivot Alignment
  15. ICML 2026Reasoning Structure of Large Language Models
  16. ICML 2026Regret Pre-training: Bridging Prior and Posterior Views for Enhanced Knowledge Grounding
  17. ICML 2026Rethinking Efficient Graph Coarsening via a Non-Selfishness Principle
  18. ICML 2026Rethinking Graph Transformers as Graph Signal Denoisers: The Role of Block-Diagonal Priors
  19. ICML 2026Revisiting Parameter-Based Knowledge Editing in Large Language Models: Theoretical Limits and Empirical Evidence
  20. ICML 2026Revisiting Positive Samples in Graph Contrastive Learning: From the Perspective of Message Passing
  21. ICML 2026Robust Signal Enhancement via Fractional Detail Views and Knowledge Guided Multi-view Fusion
  22. ICML 2026Rotary Position Encodings for Graphs
  23. ICML 2026RSF-GLLM: Bridging the Semantic Gap in Multi-Hop Knowledge Graph QA via Recurrent Soft-Flow and Decoupled LLM Generation
  24. ICML 2026Scalable Topology-Preserving Graph Coarsening: Concepts and Algorithms
  25. ICML 2026Selecting Samples on Graphs: A Unified Dataset Pruning Framework for Lossless Training Acceleration
  26. ICML 2026Semi-Supervised Learning for Molecular Graphs via Ensemble Consensus
  27. ICML 2026Semi-Supervised Noise Adaptation: Transferring Knowledge from Noise Domain
  28. ICML 2026SG2Loc: Sequential Visual Localization on 3D Scene Graphs
  29. ICML 2026Size Transferability of Graph Convolutional Networks across Sparsity: A Generalized Graphon Perspective
  30. ICML 2026SPA: A Simple but Tough-to-Beat Baseline for Knowledge Injection
  31. ICML 2026SpaEF: Spatially Resolved Transcriptomics Data Element-Wise Denoising Framework Powered by Large Models
  32. ICML 2026Split Personality Training: Revealing Latent Knowledge Through Alternate Personalities
  33. ICML 2026Structure-Centric Graph Foundation Model via Geometric Bases
  34. ICML 2026Structured Progressive Knowledge Activation for LLM-Driven Neural Architecture Search
  35. ICML 2026SWING: Unlocking Implicit Graph Representations for Graph Random Features
  36. ICML 2026Symbiosis-Inspired Knowledge Distillation for Incremental Object Detection
  37. ICML 2026TaskLoom: Weaving Knowledge Across Tasks in World Models
  38. ICML 2026The Bridge-Garden Dilemma in LLM Distillation: Why Mixing Hard and Soft Labels Works
  39. ICML 2026Torus Graphs for Large Scale Neural Phase Analysis
  40. ICML 2026Towards Rule-Based Knowledge Sharing in Federated Learning
  41. ICML 2026Towards Universal Gene Regulatory Network Inference: Unlocking Generalizable Regulatory Knowledge in Single-cell Foundation Models
  42. ICML 2026Trajectory Seriation via Spectral Tangent Alignment and Global Embedding
  43. ICML 2026Unitary Convolutions for Message-passing and Positional Encodings on Directed Graphs
  44. ICML 2026Unveiling the Structure of Do-Calculus Reasoning via Derivation Graphs
  45. ICML 2026Use What You Know: Causal Foundation Models with Partial Graphs
  46. ICML 2026View Space: Learning Representation across Arbitrary Graphs
  47. ICML 2026Weaving Graph over Tokens: Contextualizing Structured Sequences for LLMs
  48. ICML 2026What Makes a Desired Graph for Relational Deep Learning?
  49. ICML 2026What Makes a Strong Model? A Unified Spectral Analysis of Knowledge Transfer over High-dimensional Linear Regression
  50. ICML 2026When Do Hallucinations Arise? A Graph Perspective on the Evolution of Path Reuse and Path Compression

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