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 201 篇，第 3 / 5 页

101. ICLR 2026Knowledge Distillation for Large Language Models through Residual Learning
102. ICLR 2026Knowledge Editing with Subspace-Aware Key-Value Mappings
103. ICLR 2026Knowledge Fusion of Large Language Models via Modular SkillPacks
104. ICLR 2026Knowledge Reasoning Language Model: Unifying Knowledge and Language for Inductive Knowledge Graph Reasoning
105. ICLR 2026KnowledgeSmith: Uncovering Knowledge Updating in LLMs with Model Editing and Unlearning
106. ICLR 2026KnowProxy: Adapting Large Language Models by Knowledge-guided Proxy
107. ICLR 2026Latent Geometry-Driven Network Automata for Complex Network Dismantling
108. ICLR 2026LEAP: Local ECT-Based Learnable Positional Encodings for Graphs
109. ICLR 2026Learning Adaptive Distribution Alignment with Neural Characteristic Function for Graph Domain Adaptation
110. ICLR 2026Learning Dynamic Causal Graphs Under Parametric Uncertainty via Polynomial Chaos Expansions
111. ICLR 2026Learning from Historical Activations in Graph Neural Networks
112. ICLR 2026Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors
113. ICLR 2026Learning Structure-Semantic Evolution Trajectories for Graph Domain Adaptation
114. ICLR 2026LINGOLY-TOO: Disentangling Reasoning from Knowledge with Templatised Orthographic Obfuscation
115. ICLR 2026LLMs Struggle to Balance Reasoning and World Knowledge in Causal Narrative Understanding
116. ICLR 2026Low-pass Personalized Subgraph Federated Recommendation
117. ICLR 2026LRIM: a Physics-Based Benchmark for Provably Evaluating Long-Range Capabilities in Graph Learning
118. ICLR 2026LUMINA: Detecting Hallucinations in RAG System with Context–Knowledge Signals
119. ICLR 2026Mapping Post-Training Forgetting in Language Models at Scale
120. ICLR 2026MaRS: Memory-Adaptive Routing for Reliable Capacity Expansion and Knowledge Retention
121. ICLR 2026MCbiF: Measuring Topological Autocorrelation in Multiscale Clusterings via 2-Parameter Persistent Homology
122. ICLR 2026Medical Interpretability and Knowledge Maps of Large Language Models
123. ICLR 2026Minimax Sample Complexity of Graph Neural Networks: Lower Bounds and Structural Effects
124. ICLR 2026Mixed-Curvature Tree-Sliced Wasserstein Distance
125. ICLR 2026MobiEdit: Resource-efficient Knowledge Editing for Personalized On-device LLMs
126. ICLR 2026MobileKGQA: On-Device KGQA System on Dynamic Mobile Environments
127. ICLR 2026Modality-free Graph In-context Alignment
128. ICLR 2026MolecularIQ: Characterizing Chemical Reasoning Capabilities Through Symbolic Verification on Molecular Graphs
129. ICLR 2026MomaGraph: State-Aware Unified Scene Graphs with Vision-Language Models for Embodied Task Planning
130. ICLR 2026Multi-Domain Transferable Graph Gluing for Building Graph Foundation Models
131. ICLR 2026Multiple Streams of Knowledge Retrieval: Enriching and Recalling in Transformers
132. ICLR 2026Neural Graduated Assignment for Maximum Common Edge Subgraphs
133. ICLR 2026Neural Message-Passing on Attention Graphs for Hallucination Detection
134. ICLR 2026Non-Clashing Teaching in Graphs: Algorithms, Complexity, and Bounds
135. ICLR 2026On The Expressive Power of GNN Derivatives
136. ICLR 2026On the Expressive Power of GNNs for Boolean Satisfiability
137. ICLR 2026On the identifiability of causal graphs with multiple environments
138. ICLR 2026On the trade-off between expressivity and privacy in graph representation learning
139. ICLR 2026On the Universality and Complexity of GNN for Solving Second-order Cone Programs
140. ICLR 2026One for Two: A Unified Framework for Imbalanced Graph Classification via Dynamic Balanced Prototype
141. ICLR 2026Oversmoothing, "Oversquashing'', Heterophily, Long-Range, and more: Demystifying Common Beliefs in Graph Machine Learning
142. ICLR 2026OWLEYE: ZERO-SHOT LEARNER FOR CROSSDOMAIN GRAPH DATA ANOMALY DETECTION
143. ICLR 2026Panoptic Pairwise Distortion Graph
144. ICLR 2026Pedagogically-Inspired Data Synthesis for Language Model Knowledge Distillation
145. ICLR 2026Plan-Answer-Refine-on-Graph: Structured Planning and Self-Refinement for Large Language Model Reasoning on Knowledge Graphs
146. ICLR 2026Pre-training Limited Memory Language Models with Internal and External Knowledge
147. ICLR 2026Pretraining with hierarchical memories: separating long-tail and common knowledge
148. ICLR 2026Principled Fast and Meta Knowledge Learners for Continual Reinforcement Learning
149. ICLR 2026Probing to Refine: Reinforcement Distillation of LLM Reasoners via Explanatory Inversion
150. ICLR 2026Programming by Backprop: Learning Behaviour from Symbolic Descriptions

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。