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 133 篇，第 2 / 3 页

51. NeurIPS 2026Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs
52. NeurIPS 2026Integrating Background Knowledge for Scalable Causal Discovery
53. NeurIPS 2026Interactive Combinatorial Reinforcement Learning for Knowledge Graph Reasoning
54. NeurIPS 2026Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists
55. NeurIPS 2026Joint Certification for Attributed Graphs: Beyond Topology-Only Robustness
56. NeurIPS 2026K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs
57. NeurIPS 2026KDASO: Knowledge-Data Dual-Driven Automated Skill Optimization for Liability Adjudication Task
58. NeurIPS 2026KG-Guard: Graph-Based Hallucination Detection for Knowledge Base Question Answering
59. NeurIPS 2026KnowEvo: Knowledge Evolution for Protein Optimization
60. NeurIPS 2026Knowledge Localization in Mixture-of-Experts LLMs Using Cross-Lingual Inconsistency
61. NeurIPS 2026LeAct: Learning to Reason from Expert Actions
62. NeurIPS 2026Learning Minimal Sufficient Evidence Graphs for GraphRAG via Nash-Guided Optimization
63. NeurIPS 2026Learning Pseudo-Riemannian Manifolds for Heterophilic Graphs via Graph Signature
64. NeurIPS 2026Learning to Evolve Scenes: Reasoning about Human Activities with Scene Graphs
65. NeurIPS 2026LibEvoBench: Probing Temporal Knowledge Stratification in Code Generation Models
66. NeurIPS 2026LittleLearner: Language Models Under Pedagogically-Controlled Knowledge Exposure
67. NeurIPS 2026Load Balancing Mixture of Experts with Similarity Preserving Routers
68. NeurIPS 2026Logistic Bandits with $\tilde{O}(\sqrt{dT})$ Regret without Context Diversity Assumptions
69. NeurIPS 2026LUMOS: Tracing Parametric Knowledge from Training Data to Behavioral Outputs in LLMs
70. NeurIPS 2026Manifold Random Features
71. NeurIPS 2026MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge
72. NeurIPS 2026Mean-Field Control on Sparse Graphs: From Local Limits to GNNs via Neighborhood Distributions
73. NeurIPS 2026MedKIT: Evaluating Knowledge Integration and Generalization in Large Language Models
74. NeurIPS 2026MedZERO: Self-Evolving Agents for Open-Ended Medical Reasoning Through Controlled Knowledge Accumulation
75. NeurIPS 2026MemCoRe: Recovering Evidence from Progressively Compressed Factual Knowledge for Agent Memory
76. NeurIPS 2026MetaKE: Meta-Learning for Knowledge Editing Toward a Better Accuracy-Editability Trade-off
77. NeurIPS 2026MicroWorld: Empowering Multimodal Large Language Models to Bridge the Microscopic Domain Gap with Multimodal Attribute Graph
78. NeurIPS 2026MineEvolve: Self-Evolution with Accumulated Knowledge for Long-Horizon Embodied Minecraft Agents
79. NeurIPS 2026MM-DyGraph: A Dataset, Benchmark, and Model for Multimodal Dynamic Graphs
80. NeurIPS 2026MMGraph-Agent: Agentic Multimodal RAG via Cache-Inspired Multimodal Knowledge HyperGraphs
81. NeurIPS 2026Near-Linear Time Generalized Sinkhorn Algorithms for Bounded Genus Graphs
82. NeurIPS 2026NeSyKC: Neurosymbolic Knowledge Compilation For Lifelong Learning Embodied Agents
83. NeurIPS 2026NeuralFieldManifold: Reconstruction of LFP manifold with Lag Embedding
84. NeurIPS 2026Neuro-KE: Knowledge-Guided Interfaces for Semantically Grounded EEG Foundation Models
85. NeurIPS 2026NGDB-Zoo: Towards Efficient and Scalable Neural Graph Databases Training
86. NeurIPS 2026Noisy isomorphism: Robust expressivity of GNNs under structural perturbation
87. NeurIPS 2026On the Fragility of Latent Knowledge: Layer-wise Influence under Unlearning in Large Language Model
88. NeurIPS 2026One-Shot Federated Graph Learning via High-Fidelity Proxies and Transferability-Guided Collaboration
89. NeurIPS 2026Overthinking as a Symptom of Knowledge Conflict: Understanding and Detecting LLM's Hallucinations in Retrieval-Augmented Question Answering
90. NeurIPS 2026Permutation-Invariant Spectral Learning via Dyson Diffusion
91. NeurIPS 2026PerturbReason: A Knowledge-Grounded Benchmark and Framework for Cell-State–Conditioned Mechanistic Reasoning of Perturbation Effects
92. NeurIPS 2026PhysGraphNet: Physical-State Scene Graphs via Latent Graph Reasoning and Counterfactual Supervision
93. NeurIPS 2026Querying Counterfactuals on Tissue Graphs with Supervised Disentanglement
94. NeurIPS 2026RadOmni: Advancing Foundation Model for Non-contrast CT with Omni Radiology Knowledge
95. NeurIPS 2026Reasoning over Coupled Receptive Fields: Eliminating Subgraph Redundancy at Scale
96. NeurIPS 2026Reasoning Pathologies in Large Language Models: A Diagnostic Perspective
97. NeurIPS 2026Reconfiguring Procedural Knowledge for Compositional Robot Skill Adaptation
98. NeurIPS 2026REGATE: Confidence-Calibrated Integration of Temporally-Aligned Exogenous Texts for Dynamic Graphs
99. NeurIPS 2026Rethinking Knowledge Distillation for Diffusion Language Models
100. NeurIPS 2026Return to Basics: Very Simple Graph Contrastive Learning via Noise Cancellation Principle

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。