Knowledge Graphs papers, 2023–2026

Key findings

• Knowledge Graphs went from 287 papers in 2023 to 536 in 2026, roughly 1.9x in three years.
• ICLR publishes the most Knowledge Graphs work: 571 papers from 2023 to 2026, 33% of the four-venue total.
• The fastest-growing overlap is with Multimodal LLMs: papers tagged with both rose from 17 in 2023 to 93 in 2026.
• Among the 5 topics under Graph and Structured Data, it ranks #2 by 2026 paper count; the fastest grower in the group, Time Series, is up 3.2x versus 1.9x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Knowledge Graphs papers

154 papers, page 3 of 4

101. NeurIPS 2025One for All: Universal Topological Primitive Transfer for Graph Structure Learning
102. NeurIPS 2025Optimal community detection in dense bipartite graphs
103. NeurIPS 2025OSKAR: Omnimodal Self-supervised Knowledge Abstraction and Representation
104. NeurIPS 2025Pattern-Guided Adaptive Prior for Structure Learning
105. NeurIPS 2025Personalized Exercise Recommendation with Semantically-Grounded Knowledge Tracing
106. NeurIPS 2025PLD: A Choice-Theoretic List-Wise Knowledge Distillation
107. NeurIPS 2025pLSTM: parallelizable Linear Source Transition Mark networks
108. NeurIPS 2025Preference-driven Knowledge Distillation for Few-shot Node Classification
109. NeurIPS 2025PRING: Rethinking Protein-Protein Interaction Prediction from Pairs to Graphs
110. NeurIPS 2025Probing Hidden Knowledge Holes in Unlearned LLMs
111. NeurIPS 2025ProDAG: Projected Variational Inference for Directed Acyclic Graphs
112. NeurIPS 2025Pseudo-Riemannian Graph Transformer
113. NeurIPS 2025Quantifying Elicitation of Latent Capabilities in Language Models
114. NeurIPS 2025RAG4GFM: Bridging Knowledge Gaps in Graph Foundation Models through Graph Retrieval Augmented Generation
115. NeurIPS 2025ReMindRAG: Low-Cost LLM-Guided Knowledge Graph Traversal for Efficient RAG
116. NeurIPS 2025Restricted Global-Aware Graph Filters Bridging GNNs and Transformer for Node Classification
117. NeurIPS 2025Rethinking Residual Distribution in Locate-then-Edit Model Editing
118. NeurIPS 2025Root Cause Analysis of Outliers with Missing Structural Knowledge
119. NeurIPS 2025RvLLM: LLM Runtime Verification with Domain Knowledge
120. NeurIPS 2025SALoM: Structure Aware Temporal Graph Networks with Long-Short Memory Updater
121. NeurIPS 2025Scalable Feature Learning on Huge Knowledge Graphs for Downstream Machine Learning
122. NeurIPS 2025Scaling Embedding Layers in Language Models
123. NeurIPS 2025SegGraph: Leveraging Graphs of SAM Segments for Few-Shot 3D Part Segmentation
124. NeurIPS 2025Semantic-KG: Using Knowledge Graphs to Construct Benchmarks for Measuring Semantic Similarity
125. NeurIPS 2025Simple and Efficient Heterogeneous Temporal Graph Neural Network
126. NeurIPS 2025Single-Teacher View Augmentation: Boosting Knowledge Distillation via Angular Diversity
127. NeurIPS 2025Sketch-Augmented Features Improve Learning Long-Range Dependencies in Graph Neural Networks
128. NeurIPS 2025Spectral Graph Neural Networks are Incomplete on Graphs with a Simple Spectrum
129. NeurIPS 2025SSTAG: Structure-Aware Self-Supervised Learning Method for Text-Attributed Graphs
130. NeurIPS 2025Structured Spectral Reasoning for Frequency-Adaptive Multimodal Recommendation
131. NeurIPS 2025Subgraph Federated Learning via Spectral Methods
132. NeurIPS 2025The Parameterized Complexity of Computing the VC-Dimension
133. NeurIPS 2025The quest for the GRAph Level autoEncoder (GRALE)
134. NeurIPS 2025The Rise of Parameter Specialization for Knowledge Storage in Large Language Models
135. NeurIPS 2025Token Embeddings Violate the Manifold Hypothesis
136. NeurIPS 2025TOMCAT: Test-time Comprehensive Knowledge Accumulation for Compositional Zero-Shot Learning
137. NeurIPS 2025Towards Doctor-Like Reasoning: Medical RAG Fusing Knowledge with Patient Analogy through Textual Gradients
138. NeurIPS 2025Towards Effective Federated Graph Foundation Model via Mitigating Knowledge Entanglement
139. NeurIPS 2025Towards Graph Foundation Models: Training on Knowledge Graphs Enables Transferability to General Graphs
140. NeurIPS 2025Towards Pre-trained Graph Condensation via Optimal Transport
141. NeurIPS 2025Transforming Gaps into Gains: Bridging Model and Data Heterogeneity in Federated Learning via Knowledge Weak-Aware Zones
142. NeurIPS 2025Uncertain Knowledge Graph Completion via Semi-Supervised Confidence Distribution Learning
143. NeurIPS 2025Uncertainty Estimation on Graphs with Structure Informed Stochastic Partial Differential Equations
144. NeurIPS 2025Understanding and Enhancing Message Passing on Heterophilic Graphs via Compatibility Matrix
145. NeurIPS 2025UniEdit: A Unified Knowledge Editing Benchmark for Large Language Models
146. NeurIPS 2025Unifying Text Semantics and Graph Structures for Temporal Text-attributed Graphs with Large Language Models
147. NeurIPS 2025UniHG: A Large-scale Universal Heterogeneous Graph Dataset and Benchmark for Representation Learning and Cross-Domain Transferring
148. NeurIPS 2025UniZyme: A Unified Protein Cleavage Site Predictor Enhanced with Enzyme Active-Site Knowledge
149. NeurIPS 2025Unlocking SLM Potential for Data Analysis Code Generation via Non-Parametric Knowledge Distillation
150. NeurIPS 2025Unsupervised Learning for Optimal Transport plan prediction between unbalanced graphs

FAQ

How many Knowledge Graphs papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

1,715 in total: 287 in 2023, 426 in 2024, 466 in 2025, 536 in 2026.

How many Knowledge Graphs papers are at NeurIPS 2026?

NeurIPS 2026 has 133 Knowledge Graphs papers, versus 154 the year before.

How many Knowledge Graphs papers are at ICLR 2026?

ICLR 2026 has 201 Knowledge Graphs papers, versus 172 the year before.

How many Knowledge Graphs papers are at ICML 2026?

ICML 2026 has 149 Knowledge Graphs papers, versus 99 the year before.

How many Knowledge Graphs papers are at CVPR 2026?

CVPR 2026 has 53 Knowledge Graphs papers, versus 41 the year before.

Which conference publishes the most Knowledge Graphs papers?

ICLR, with 571 papers from 2023 to 2026.