知识图谱论文趋势 2023–2026

主要结论

• 知识图谱论文从 2023 年的 287 篇增长到 2026 年的 536 篇，三年间扩大到约 1.9 倍。
• ICLR 是发知识图谱论文最多的会议，2023–2026 年共 571 篇，占四个会议总量的 33%。
• 交叉方向里涨得最快的是多模态大模型：同时属于两个主题的论文从 2023 年的 17 篇增至 2026 年的 93 篇。
• 在「图与结构化数据」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的时间序列是 3.2 倍，知识图谱是 1.9 倍。

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

• NeurIPS 2026Aligning LLMs with Biomedical Knowledge using Balanced Fine-Tuning
• ICML 2026Belief Propagation Converges to Gaussian Distributions in Sparsely-Connected Factor Graphs
• ICLR 2026$\ell_1$ Latent Distance based Continuous-time Graph Representation
• CVPR 2026A Unified Framework for Knowledge Transfer in Bidirectional Model Scaling
• NeurIPS 2025A CLT for Polynomial GNNs on Community-Based Graphs
• ICML 2025A Selective Learning Method for Temporal Graph Continual Learning
• ICLR 2025$R^2$-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical Reasoning
• CVPR 2025A Hubness Perspective on Representation Learning for Graph-Based Multi-View Clustering
• NeurIPS 2024Can Large Language Models Analyze Graphs like Professionals? A Benchmark, Datasets and Models
• ICML 2024Bipartite Matching in Massive Graphs: A Tight Analysis of EDCS
• ICLR 2024A Good Learner can Teach Better: Teacher-Student Collaborative Knowledge Distillation
• CVPR 2024De-confounded Data-free Knowledge Distillation for Handling Distribution Shifts
• NeurIPS 2023A Comprehensive Study on Text-attributed Graphs: Benchmarking and Rethinking
• ICML 2023A Generalization of ViT/MLP-Mixer to Graphs
• ICLR 2023A Differential Geometric View and Explainability of GNN on Evolving Graphs
• CVPR 2023A Unified Knowledge Distillation Framework for Deep Directed Graphical Models
• NeurIPS 2026AT-SKM-Net: An Accelerated Trainable Sampling Kaczmarz-Motzkin Framework for Linear Hard-Constraint Feasibility on Dynamic Graphs
• ICML 2026Cross-Modal Knowledge Distillation without Paired Data: Theoretical Foundation and Algorithm
• ICLR 2026A Graph Meta-Network for Learning on Kolmogorov–Arnold Networks
• CVPR 2026Distilling Balanced Knowledge from a Biased Teacher

全部知识图谱论文

共 103 篇，第 2 / 3 页

51. ICML 2024Inverse-Variance Weighting for Estimation of Heterogeneous Treatment Effects
52. ICML 2024KnowFormer: Revisiting Transformers for Knowledge Graph Reasoning
53. ICML 2024Knowledge Distillation with Auxiliary Variable
54. ICML 2024Knowledge Graphs Can be Learned with Just Intersection Features
55. ICML 2024Knowledge-aware Reinforced Language Models for Protein Directed Evolution
56. ICML 2024Layerwise Change of Knowledge in Neural Networks
57. ICML 2024Learning in Deep Factor Graphs with Gaussian Belief Propagation
58. ICML 2024Learning Modality Knowledge Alignment for Cross-Modality Transfer
59. ICML 2024Learning to Explore in POMDPs with Informational Rewards
60. ICML 2024Less is More: on the Over-Globalizing Problem in Graph Transformers
61. ICML 2024LLaGA: Large Language and Graph Assistant
62. ICML 2024Long Range Propagation on Continuous-Time Dynamic Graphs
63. ICML 2024MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models
64. ICML 2024Mitigating Label Noise on Graphs via Topological Sample Selection
65. ICML 2024Mitigating Oversmoothing Through Reverse Process of GNNs for Heterophilic Graphs
66. ICML 2024Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matching
67. ICML 2024Neighboring Perturbations of Knowledge Editing on Large Language Models
68. ICML 2024Neural Tangent Kernels Motivate Cross-Covariance Graphs in Neural Networks
69. ICML 2024Neuro-Visualizer: A Novel Auto-Encoder-Based Loss Landscape Visualization Method With an Application in Knowledge-Guided Machine Learning
70. ICML 2024OAK: Enriching Document Representations using Auxiliary Knowledge for Extreme Classification
71. ICML 2024On dimensionality of feature vectors in MPNNs
72. ICML 2024On the Expressive Power of Spectral Invariant Graph Neural Networks
73. ICML 2024On the Feasibility of Single-Pass Full-Capacity Learning in Linear Threshold Neurons with Binary Input Vectors
74. ICML 2024Optimal Batched Linear Bandits
75. ICML 2024PAC-Bayesian Generalization Bounds for Knowledge Graph Representation Learning
76. ICML 2024PANDA: Expanded Width-Aware Message Passing Beyond Rewiring
77. ICML 2024Physics of Language Models: Part 3.1, Knowledge Storage and Extraction
78. ICML 2024PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs
79. ICML 2024Position: Why We Must Rethink Empirical Research in Machine Learning
80. ICML 2024Positional Knowledge is All You Need: Position-induced Transformer (PiT) for Operator Learning
81. ICML 2024QBMK: Quantum-based Matching Kernels for Un-attributed Graphs
82. ICML 2024Rethinking Momentum Knowledge Distillation in Online Continual Learning
83. ICML 2024Revisit the Essence of Distilling Knowledge through Calibration
84. ICML 2024Robust Graph Matching when Nodes are Corrupt
85. ICML 2024S3GCL: Spectral, Swift, Spatial Graph Contrastive Learning
86. ICML 2024Scene Graph Generation Strategy with Co-occurrence Knowledge and Learnable Term Frequency
87. ICML 2024Semantically-correlated memories in a dense associative model
88. ICML 2024SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning
89. ICML 2024SiBBlInGS: Similarity-driven Building-Block Inference using Graphs across States
90. ICML 2024Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs
91. ICML 2024SLOG: An Inductive Spectral Graph Neural Network Beyond Polynomial Filter
92. ICML 2024Stochastic Bandits with ReLU Neural Networks
93. ICML 2024Sub-token ViT Embedding via Stochastic Resonance Transformers
94. ICML 2024Subgraphormer: Unifying Subgraph GNNs and Graph Transformers via Graph Products
95. ICML 2024Temporal Spiking Neural Networks with Synaptic Delay for Graph Reasoning
96. ICML 2024The Expressive Power of Path-Based Graph Neural Networks
97. ICML 2024Transferring Knowledge From Large Foundation Models to Small Downstream Models
98. ICML 2024Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness
99. ICML 2024Uncertainty for Active Learning on Graphs
100. ICML 2024Understanding Finetuning for Factual Knowledge Extraction

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。