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

99 papers, page 2 of 2

51. ICML 2025Knowledge-Guided Wasserstein Distributionally Robust Optimization
52. ICML 2025Learn Beneficial Noise as Graph Augmentation
53. ICML 2025Learning Condensed Graph via Differentiable Atom Mapping for Reaction Yield Prediction
54. ICML 2025Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing
55. ICML 2025MASS: Mathematical Data Selection via Skill Graphs for Pretraining Large Language Models
56. ICML 2025Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding
57. ICML 2025MemFreezing: A Novel Adversarial Attack on Temporal Graph Neural Networks under Limited Future Knowledge
58. ICML 2025Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing
59. ICML 2025Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification
60. ICML 2025Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignment
61. ICML 2025On the Power of Context-Enhanced Learning in LLMs
62. ICML 2025Online Sparsification of Bipartite-Like Clusters in Graphs
63. ICML 2025PAC Learning with Improvements
64. ICML 2025Polynomial-Delay MAG Listing with Novel Locally Complete Orientation Rules
65. ICML 2025Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks
66. ICML 2025Position: Spectral GNNs Rely Less on Graph Fourier Basis than Conceived
67. ICML 2025Positional Encoding meets Persistent Homology on Graphs
68. ICML 2025Pre-Training Graph Contrastive Masked Autoencoders are Strong Distillers for EEG
69. ICML 2025Primal-Dual Neural Algorithmic Reasoning
70. ICML 2025Propagate and Inject: Revisiting Propagation-Based Feature Imputation for Graphs with Partially Observed Features
71. ICML 2025Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing
72. ICML 2025Retrieval-Augmented Language Model for Knowledge-aware Protein Encoding
73. ICML 2025Right Time to Learn: Promoting Generalization via Bio-inspired Spacing Effect in Knowledge Distillation
74. ICML 2025RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph Explanation
75. ICML 2025Robust ML Auditing using Prior Knowledge
76. ICML 2025SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models
77. ICML 2025sciLaMA: A Single-Cell Representation Learning Framework to Leverage Prior Knowledge from Large Language Models
78. ICML 2025SHARP-Distill: A 68× Faster Recommender System with Hypergraph Neural Networks and Language Models
79. ICML 2025Sort Before You Prune: Improved Worst-Case Guarantees of the DiskANN Family of Graphs
80. ICML 2025Speculate, then Collaborate: Fusing Knowledge of Language Models during Decoding
81. ICML 2025Stability and Generalization Capability of Subgraph Reasoning Models for Inductive Knowledge Graph Completion
82. ICML 2025Strengthen Out-of-Distribution Detection Capability with Progressive Self-Knowledge Distillation
83. ICML 2025Structure Is All You Need: Structural Representation Learning on Hyper-Relational Knowledge Graphs
84. ICML 2025Taming Knowledge Conflicts in Language Models
85. ICML 2025TeDS: Joint Learning of Diachronic and Synchronic Perspectives in Quaternion Space for Temporal Knowledge Graph Completion
86. ICML 2025Test-time Adaptation on Graphs via Adaptive Subgraph-based Selection and Regularized Prototypes
87. ICML 2025The Generalized Skew Spectrum of Graphs
88. ICML 2025TINED: GNNs-to-MLPs by Teacher Injection and Dirichlet Energy Distillation
89. ICML 2025TMetaNet: Topological Meta-Learning Framework for Dynamic Link Prediction
90. ICML 2025TopInG: Topologically Interpretable Graph Learning via Persistent Rationale Filtration
91. ICML 2025Toward Data-centric Directed Graph Learning: An Entropy-driven Approach
92. ICML 2025Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Trees
93. ICML 2025Towards Understanding Parametric Generalized Category Discovery on Graphs
94. ICML 2025Trusted Multi-View Classification with Expert Knowledge Constraints
95. ICML 2025Uncertainty Estimation for Heterophilic Graphs Through the Lens of Information Theory
96. ICML 2025Unifying Knowledge from Diverse Datasets to Enhance Spatial-Temporal Modeling: A Granularity-Adaptive Geographical Embedding Approach
97. ICML 2025Weisfeiler and Leman Go Gambling: Why Expressive Lottery Tickets Win
98. ICML 2025What Makes a Good Feedforward Computational Graph?
99. ICML 2025When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Need

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.