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 172 篇，第 3 / 4 页

101. ICLR 2025Medium-Difficulty Samples Constitute Smoothed Decision Boundary for Knowledge Distillation on Pruned Datasets
102. ICLR 2025metabench - A Sparse Benchmark of Reasoning and Knowledge in Large Language Models
103. ICLR 2025MiniPLM: Knowledge Distillation for Pre-training Language Models
104. ICLR 2025MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge
105. ICLR 2025MQuAKE-Remastered: Multi-Hop Knowledge Editing Can Only Be Advanced with Reliable Evaluations
106. ICLR 2025Multi-Label Node Classification with Label Influence Propagation
107. ICLR 2025Multiple Heads are Better than One: Mixture of Modality Knowledge Experts for Entity Representation Learning
108. ICLR 2025N-ForGOT: Towards Not-forgetting and Generalization of Open Temporal Graph Learning
109. ICLR 2025Neural Spacetimes for DAG Representation Learning
110. ICLR 2025Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning
111. ICLR 2025Node-Time Conditional Prompt Learning in Dynamic Graphs
112. ICLR 2025On the Byzantine-Resilience of Distillation-Based Federated Learning
113. ICLR 2025On the Completeness of Invariant Geometric Deep Learning Models
114. ICLR 2025On the Expressive Power of Sparse Geometric MPNNs
115. ICLR 2025On the Hölder Stability of Multiset and Graph Neural Networks
116. ICLR 2025Open-Set Graph Anomaly Detection via Normal Structure Regularisation
117. ICLR 2025Physics of Language Models: Part 3.2, Knowledge Manipulation
118. ICLR 2025Point-based Instance Completion with Scene Constraints
119. ICLR 2025PolyhedronNet: Representation Learning for Polyhedra with Surface-attributed Graph
120. ICLR 2025Precedence-Constrained Winter Value for Effective Graph Data Valuation
121. ICLR 2025Precise Localization of Memories: A Fine-grained Neuron-level Knowledge Editing Technique for LLMs
122. ICLR 2025Quality Measures for Dynamic Graph Generative Models
123. ICLR 2025Query-based Knowledge Transfer for Heterogeneous Learning Environments
124. ICLR 2025Rationalizing and Augmenting Dynamic Graph Neural Networks
125. ICLR 2025Reasoning of Large Language Models over Knowledge Graphs with Super-Relations
126. ICLR 2025Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval
127. ICLR 2025Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNs
128. ICLR 2025Recovering Manifold Structure Using Ollivier Ricci Curvature
129. ICLR 2025Refine Knowledge of Large Language Models via Adaptive Contrastive Learning
130. ICLR 2025Relation-Aware Diffusion for Heterogeneous Graphs with Partially Observed Features
131. ICLR 2025Reliable and Diverse Evaluation of LLM Medical Knowledge Mastery
132. ICLR 2025Residual Connections and Normalization Can Provably Prevent Oversmoothing in GNNs
133. ICLR 2025Rethinking Graph Neural Networks From A Geometric Perspective Of Node Features
134. ICLR 2025Revealing and Mitigating Over-Attention in Knowledge Editing
135. ICLR 2025Revisiting Random Walks for Learning on Graphs
136. ICLR 2025Scalable and Certifiable Graph Unlearning: Overcoming the Approximation Error Barrier
137. ICLR 2025Scalable Influence and Fact Tracing for Large Language Model Pretraining
138. ICLR 2025Scale-Free Graph-Language Models
139. ICLR 2025SelKD: Selective Knowledge Distillation via Optimal Transport Perspective
140. ICLR 2025Shapley-Guided Utility Learning for Effective Graph Inference Data Valuation
141. ICLR 2025Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation
142. ICLR 2025Single Teacher, Multiple Perspectives: Teacher Knowledge Augmentation for Enhanced Knowledge Distillation
143. ICLR 2025SpaceGNN: Multi-Space Graph Neural Network for Node Anomaly Detection with Extremely Limited Labels
144. ICLR 2025Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
145. ICLR 2025Spectro-Riemannian Graph Neural Networks
146. ICLR 2025Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling
147. ICLR 2025Spreading Out-of-Distribution Detection on Graphs
148. ICLR 2025ST-GCond: Self-supervised and Transferable Graph Dataset Condensation
149. ICLR 2025StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization
150. ICLR 2025Structuring Benchmark into Knowledge Graphs to Assist Large Language Models in Retrieving and Designing Models

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。