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 571 篇，第 2 / 12 页

51. ICLR 2026Do We Really Need Permutations? Impact of Width Expansion on Linear Mode Connectivity
52. ICLR 2026DOPPLER: Dual-Policy Learning for Device Assignment in Asynchronous Dataflow Graphs
53. ICLR 2026DR-GGAD: Dual Residual Centering for Mitigating Anomaly Non‑Discriminativity in Generalist Graph Anomaly Detection
54. ICLR 2026Dynamic Multi-sample Mixup with Gradient Exploration for Open-set Graph Anomaly Detection
55. ICLR 2026Efficient Learning on Large Graphs using a Densifying Regularity Lemma
56. ICLR 2026Enhancing LLMs for Knowledge Base Question Answering by Chain-of-Decomposition
57. ICLR 2026EvA: Evolutionary Attacks on Graphs
58. ICLR 2026Experience-based Knowledge Correction for Robust Planning in Minecraft
59. ICLR 2026Expert Heads: Robust Evidence Identification for Large Language Models
60. ICLR 2026Explain in Your Own Words: Improving Reasoning via Token-Selective Dual Knowledge Distillation
61. ICLR 2026Explore-on-Graph: Incentivizing Autonomous Exploration of Large Language Models on Knowledge Graphs with Path-refined Reward Modeling
62. ICLR 2026Exploring Knowledge Purification in Multi-Teacher Knowledge Distillation for LLMs
63. ICLR 2026Exposing Weaknesses of Large Reasoning Models through Graph Algorithm Problems
64. ICLR 2026Expressive and Invariant Graph Learning via Canonical Tree Cover Neural Networks
65. ICLR 2026Federated Graph-Level Clustering Network with Dual Knowledge Separation
66. ICLR 2026FedMC: Federated Manifold Calibration
67. ICLR 2026Fine-tuning Done Right in Model Editing
68. ICLR 2026Flock: A Knowledge Graph Foundation Model via Learning on Random Walks
69. ICLR 2026FlowSymm: Physics–Aware, Symmetry–Preserving Graph Attention for Network Flow Completion
70. ICLR 2026Forest-Based Graph Learning for Semi-Supervised Node Classification
71. ICLR 2026Fresh in memory: Training-order recency is linearly encoded in language model activations
72. ICLR 2026FSD-CAP: Fractional Subgraph Diffusion with Class-Aware Propagation for Graph Feature Imputation
73. ICLR 2026FutureMind: Equipping Small Language Models with Strategic Thinking-Pattern Priors via Adaptive Knowledge Distillation
74. ICLR 2026G-Merging: Graph Models Merging for Parameter-Efficient Multi-Task Knowledge Consolidation
75. ICLR 2026G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledge
76. ICLR 2026Gelato: Graph Edit Distance via Autoregressive Neural Combinatorial Optimization
77. ICLR 2026General search techniques without common knowledge for imperfect-information games, and application to superhuman Fog of War chess
78. ICLR 2026Generalized Spherical Neural Operators: Green’s Function Formulation
79. ICLR 2026Generating Directed Graphs with Dual Attention and Asymmetric Encoding
80. ICLR 2026Global-Recent Semantic Reasoning on Dynamic Text-Attributed Graphs with Large Language Models
81. ICLR 2026gLSTM: Mitigating Over-Squashing by Increasing Storage Capacity
82. ICLR 2026Graph homophily booster: Reimagining the role of discrete features in heterophilic graph learning
83. ICLR 2026Graph Mixing Additive Networks
84. ICLR 2026Graph Random Features for Scalable Gaussian Processes
85. ICLR 2026Graph Representational Learning: When Does More Expressivity Hurt Generalization?
86. ICLR 2026Graph Tokenization for Bridging Graphs and Transformers
87. ICLR 2026GraphOmni: A Comprehensive and Extensible Benchmark Framework for Large Language Models on Graph-theoretic Tasks
88. ICLR 2026Graphon Cross-Validation: Assessing Models on Network Data
89. ICLR 2026GraphPlanner: Graph-Based Agentic Routing for LLMs
90. ICLR 2026H$^3$GNNs: Harmonizing Heterophily and Homophily in GNNs via Self-Supervised Node Encoding
91. ICLR 2026HGNet: Scalable Foundation Model for Automated Knowledge Graph Generation from Scientific Literature
92. ICLR 2026Hourglass Persistence for Graphs, Simplices, and Cells
93. ICLR 2026HYPER: A Foundation Model for Inductive Link Prediction with Knowledge Hypergraphs
94. ICLR 2026In Good GRACES: Principled Teacher Selection for Knowledge Distillation
95. ICLR 2026Inductive Reasoning for Temporal Knowledge Graphs with Emerging Entities
96. ICLR 2026Inheriting Generalizable Knowledge from LLMs to Diverse Vertical Tasks
97. ICLR 2026Interference-Isolated Elastic Weight Consolidation and Knowledge Calibration for Incremental Object Detection
98. ICLR 2026Intrinsic Lorentz Neural Network
99. ICLR 2026KGOT: Unified Knowledge Graph and Optimal Transport Pseudo-Labeling for Molecule-Protein Interaction Prediction
100. ICLR 2026Knowledge Distillation as Decontamination? Revisiting the “Data Laundering” Concern

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。