特征归因论文趋势 2023–2026

主要结论

• 特征归因论文从 2023 年的 118 篇增长到 2026 年的 219 篇，三年间扩大到约 1.9 倍。
• NeurIPS 是发特征归因论文最多的会议，2023–2026 年共 193 篇，占四个会议总量的 28%。
• 交叉方向里涨得最快的是理论 · learning theory：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 14 篇。
• 在「可解释性」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的机制解释是 8.1 倍，特征归因是 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 2026ADAPT: Hybrid Prompt Optimization for LLM Feature Visualization
• ICML 2026Activation with Intrinsic-Extrinsic Consensus
• ICLR 2026AnyUp: Universal Feature Upsampling
• CVPR 2026A Training-Free Style-Personalization via SVD-Based Feature Decomposition
• NeurIPS 2025Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks
• ICML 2025BCE vs. CE in Deep Feature Learning
• ICLR 2025A Differentiable Rank-Based Objective for Better Feature Learning
• CVPR 2025A Simple Data Augmentation for Feature Distribution Skewed Federated Learning
• NeurIPS 2024$\texttt{dattri}$: A Library for Efficient Data Attribution
• ICML 2024Asymptotics of feature learning in two-layer networks after one gradient-step
• ICLR 2024An Intuitive Multi-Frequency Feature Representation for SO(3)-Equivariant Networks
• CVPR 2024DYSON: Dynamic Feature Space Self-Organization for Online Task-Free Class Incremental Learning
• NeurIPS 2023$\mathcal{M}^4$: A Unified XAI Benchmark for Faithfulness Evaluation of Feature Attribution Methods across Metrics, Modalities and Models
• ICML 2023Decoding Layer Saliency in Language Transformers
• ICLR 2023Can We Faithfully Represent Absence States to Compute Shapley Values on a DNN?
• CVPR 2023A Practical Upper Bound for the Worst-Case Attribution Deviations
• NeurIPS 2026Adaptive Feature Propagation for Attribute-Missing Graph Clustering
• ICML 2026Aggregate Models, Not Explanations: Improving Feature Importance Estimation
• ICLR 2026Attribution-Guided Decoding
• CVPR 2026FBTA Enabling Single-GPU End-to-End Gigapixel WSI Classification with Feature Bridging

全部特征归因论文

共 36 篇，第 1 / 1 页

1. ICLR 2024Adversarial Feature Map Pruning for Backdoor
2. ICLR 2024An Intuitive Multi-Frequency Feature Representation for SO(3)-Equivariant Networks
3. ICLR 2024AttEXplore: Attribution for Explanation with model parameters eXploration
4. ICLR 2024Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data
5. ICLR 2024Bounding Box Stability against Feature Dropout Reflects Detector Generalization across Environments
6. ICLR 2024Elastic Feature Consolidation For Cold Start Exemplar-Free Incremental Learning
7. ICLR 2024Estimating Conditional Mutual Information for Dynamic Feature Selection
8. ICLR 2024Exploring the cloud of feature interaction scores in a Rashomon set
9. ICLR 2024Feature Collapse
10. ICLR 2024Feature emergence via margin maximization: case studies in algebraic tasks
11. ICLR 2024Feature-aligned N-BEATS with Sinkhorn divergence
12. ICLR 2024Fixed Non-negative Orthogonal Classifier: Inducing Zero-mean Neural Collapse with Feature Dimension Separation
13. ICLR 2024GOAt: Explaining Graph Neural Networks via Graph Output Attribution
14. ICLR 2024Going Beyond Neural Network Feature Similarity: The Network Feature Complexity and Its Interpretation Using Category Theory
15. ICLR 2024Grokking as the transition from lazy to rich training dynamics
16. ICLR 2024Heterogeneous Personalized Federated Learning by Local-Global Updates Mixing via Convergence Rate
17. ICLR 2024Intriguing Properties of Data Attribution on Diffusion Models
18. ICLR 2024Learning Hierarchical Polynomials with Three-Layer Neural Networks
19. ICLR 2024Less is More: Fewer Interpretable Region via Submodular Subset Selection
20. ICLR 2024Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching
21. ICLR 2024More is Better: when Infinite Overparameterization is Optimal and Overfitting is Obligatory
22. ICLR 2024On the Joint Interaction of Models, Data, and Features
23. ICLR 2024Optimal criterion for feature learning of two-layer linear neural network in high dimensional interpolation regime
24. ICLR 2024Path Choice Matters for Clear Attributions in Path Methods
25. ICLR 2024Quantifying the Plausibility of Context Reliance in Neural Machine Translation
26. ICLR 2024SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation
27. ICLR 2024Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning
28. ICLR 2024SparseDFF: Sparse-View Feature Distillation for One-Shot Dexterous Manipulation
29. ICLR 2024Spurious Feature Diversification Improves Out-of-distribution Generalization
30. ICLR 2024Tensor Programs VI: Feature Learning in Infinite Depth Neural Networks
31. ICLR 2024Towards Optimal Feature-Shaping Methods for Out-of-Distribution Detection
32. ICLR 2024Understanding Convergence and Generalization in Federated Learning through Feature Learning Theory
33. ICLR 2024Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence
34. ICLR 2024Unraveling the Enigma of Double Descent: An In-depth Analysis through the Lens of Learned Feature Space
35. ICLR 2024VertiBench: Advancing Feature Distribution Diversity in Vertical Federated Learning Benchmarks
36. ICLR 2024Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation

常见问题

2023–2026 年四大会议一共有多少篇特征归因论文？

共 695 篇，按年份分别是 2023 年 118 篇、2024 年 168 篇、2025 年 190 篇、2026 年 219 篇。

NeurIPS 2026 有多少篇特征归因论文？

NeurIPS 2026 有 61 篇特征归因论文，上一届是 57 篇。

ICLR 2026 有多少篇特征归因论文？

ICLR 2026 有 53 篇特征归因论文，上一届是 42 篇。

ICML 2026 有多少篇特征归因论文？

ICML 2026 有 56 篇特征归因论文，上一届是 51 篇。

CVPR 2026 有多少篇特征归因论文？

CVPR 2026 有 49 篇特征归因论文，上一届是 40 篇。

哪个会议的特征归因论文最多？

NeurIPS，2023–2026 年共 193 篇。