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 168 篇，第 2 / 4 页

51. ICLR 2024Heterogeneous Personalized Federated Learning by Local-Global Updates Mixing via Convergence Rate
52. ICLR 2024Intriguing Properties of Data Attribution on Diffusion Models
53. ICLR 2024Learning Hierarchical Polynomials with Three-Layer Neural Networks
54. ICLR 2024Less is More: Fewer Interpretable Region via Submodular Subset Selection
55. ICLR 2024Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching
56. ICLR 2024More is Better: when Infinite Overparameterization is Optimal and Overfitting is Obligatory
57. ICLR 2024On the Joint Interaction of Models, Data, and Features
58. ICLR 2024Optimal criterion for feature learning of two-layer linear neural network in high dimensional interpolation regime
59. ICLR 2024Path Choice Matters for Clear Attributions in Path Methods
60. ICLR 2024Quantifying the Plausibility of Context Reliance in Neural Machine Translation
61. ICLR 2024SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation
62. ICLR 2024Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning
63. ICLR 2024SparseDFF: Sparse-View Feature Distillation for One-Shot Dexterous Manipulation
64. ICLR 2024Spurious Feature Diversification Improves Out-of-distribution Generalization
65. ICLR 2024Tensor Programs VI: Feature Learning in Infinite Depth Neural Networks
66. ICLR 2024Towards Optimal Feature-Shaping Methods for Out-of-Distribution Detection
67. ICLR 2024Understanding Convergence and Generalization in Federated Learning through Feature Learning Theory
68. ICLR 2024Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence
69. ICLR 2024Unraveling the Enigma of Double Descent: An In-depth Analysis through the Lens of Learned Feature Space
70. ICLR 2024VertiBench: Advancing Feature Distribution Diversity in Vertical Federated Learning Benchmarks
71. ICLR 2024Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation
72. ICML 2024A New Computationally Efficient Algorithm to solve Feature Selection for Functional Data Classification in High-dimensional Spaces
73. ICML 2024A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks
74. ICML 2024Acquisition Conditioned Oracle for Nongreedy Active Feature Acquisition
75. ICML 2024Asymptotics of feature learning in two-layer networks after one gradient-step
76. ICML 2024Asymptotics of Learning with Deep Structured (Random) Features
77. ICML 2024Balancing Feature Similarity and Label Variability for Optimal Size-Aware One-shot Subset Selection
78. ICML 2024Benchmarking Deletion Metrics with the Principled Explanations
79. ICML 2024Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning
80. ICML 2024Complexity Matters: Feature Learning in the Presence of Spurious Correlations
81. ICML 2024Contextual Feature Selection with Conditional Stochastic Gates
82. ICML 2024Critical feature learning in deep neural networks
83. ICML 2024Critical windows: non-asymptotic theory for feature emergence in diffusion models
84. ICML 2024Decoupling Feature Extraction and Classification Layers for Calibrated Neural Networks
85. ICML 2024DFD: Distilling the Feature Disparity Differently for Detectors
86. ICML 2024Don't trust your eyes: on the (un)reliability of feature visualizations
87. ICML 2024EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
88. ICML 2024Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanation
89. ICML 2024Feature Contamination: Neural Networks Learn Uncorrelated Features and Fail to Generalize
90. ICML 2024Feature Distribution on Graph Topology Mediates the Effect of Graph Convolution: Homophily Perspective
91. ICML 2024Feature Importance Disparities for Data Bias Investigations
92. ICML 2024Feature Reuse and Scaling: Understanding Transfer Learning with Protein Language Models
93. ICML 2024Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions
94. ICML 2024High-dimensional Linear Bandits with Knapsacks
95. ICML 2024InterpreTabNet: Distilling Predictive Signals from Tabular Data by Salient Feature Interpretation
96. ICML 2024Iterative Search Attribution for Deep Neural Networks
97. ICML 2024Learning 1-Bit Tiny Object Detector with Discriminative Feature Refinement
98. ICML 2024Learning in Feature Spaces via Coupled Covariances: Asymmetric Kernel SVD and Nyström method
99. ICML 2024Local Feature Selection without Label or Feature Leakage for Interpretable Machine Learning Predictions
100. ICML 2024Manifold Integrated Gradients: Riemannian Geometry for Feature Attribution

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。