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 193 篇，第 3 / 4 页

101. NeurIPS 2025Practical do-Shapley Explanations with Estimand-Agnostic Causal Inference
102. NeurIPS 2025Proxy-SPEX: Sample-Efficient Interpretability via Sparse Feature Interactions in LLMs
103. NeurIPS 2025Regional Explanations: Bridging Local and Global Variable Importance
104. NeurIPS 2025Rescaled Influence Functions: Accurate Data Attribution in High Dimension
105. NeurIPS 2025Revising and Falsifying Sparse Autoencoder Feature Explanations
106. NeurIPS 2025Revisiting LRP: Positional Attribution as the Missing Ingredient for Transformer Explainability
107. NeurIPS 2025Scalable Feature Learning on Huge Knowledge Graphs for Downstream Machine Learning
108. NeurIPS 2025Sculpting Features from Noise: Reward-Guided Hierarchical Diffusion for Task-Optimal Feature Transformation
109. NeurIPS 2025SHAP values via sparse Fourier representation
110. NeurIPS 2025Smoothed Differentiation Efficiently Mitigates Shattered Gradients in Explanations
111. NeurIPS 2025Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformation
112. NeurIPS 2025Taming Hyperparameter Sensitivity in Data Attribution: Practical Selection Without Costly Retraining
113. NeurIPS 2025The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation
114. NeurIPS 2025The Computational Advantage of Depth in Learning High-Dimensional Hierarchical Targets
115. NeurIPS 2025The Fragile Truth of Saliency: Improving LLM Input Attribution via Attention Bias Optimization
116. NeurIPS 2025Tracing the Roots: Leveraging Temporal Dynamics in Diffusion Trajectories for Origin Attribution
117. NeurIPS 2025Vertical Federated Feature Screening
118. NeurIPS 2025X-Mahalanobis: Transformer Feature Mixing for Reliable OOD Detection
119. NeurIPS 2024$\texttt{dattri}$: A Library for Efficient Data Attribution
120. NeurIPS 2024Benchmarking the Attribution Quality of Vision Models
121. NeurIPS 2024Credit Attribution and Stable Compression
122. NeurIPS 2024Data-faithful Feature Attribution: Mitigating Unobservable Confounders via Instrumental Variables
123. NeurIPS 2024DeepDRK: Deep Dependency Regularized Knockoff for Feature Selection
124. NeurIPS 2024Denoising Diffusion Path: Attribution Noise Reduction with An Auxiliary Diffusion Model
125. NeurIPS 2024DETAIL: Task DEmonsTration Attribution for Interpretable In-context Learning
126. NeurIPS 2024Dimension-free deterministic equivalents and scaling laws for random feature regression
127. NeurIPS 2024Efficient Sketches for Training Data Attribution and Studying the Loss Landscape
128. NeurIPS 2024Efficiently Learning Significant Fourier Feature Pairs for Statistical Independence Testing
129. NeurIPS 2024EnOF-SNN: Training Accurate Spiking Neural Networks via Enhancing the Output Feature
130. NeurIPS 2024ETO:Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography Hypotheses
131. NeurIPS 2024Explanations that reveal all through the definition of encoding
132. NeurIPS 2024Fast Iterative Hard Thresholding Methods with Pruning Gradient Computations
133. NeurIPS 2024Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivity
134. NeurIPS 2024FUGAL: Feature-fortified Unrestricted Graph Alignment
135. NeurIPS 2024Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning
136. NeurIPS 2024Handling Learnwares from Heterogeneous Feature Spaces with Explicit Label Exploitation
137. NeurIPS 2024Infinite-Dimensional Feature Interaction
138. NeurIPS 2024Is Function Similarity Over-Engineered? Building a Benchmark
139. NeurIPS 2024Learning Low-Rank Feature for Thorax Disease Classification
140. NeurIPS 2024Learning Successor Features the Simple Way
141. NeurIPS 2024MatrixNet: Learning over symmetry groups using learned group representations
142. NeurIPS 2024MemoryFormer : Minimize Transformer Computation by Removing Fully-Connected Layers
143. NeurIPS 2024Mitigating Biases in Blackbox Feature Extractors for Image Classification Tasks
144. NeurIPS 2024Most Influential Subset Selection: Challenges, Promises, and Beyond
145. NeurIPS 2024Neural Collapse Inspired Feature Alignment for Out-of-Distribution Generalization
146. NeurIPS 2024NeuroBOLT: Resting-state EEG-to-fMRI Synthesis with Multi-dimensional Feature Mapping
147. NeurIPS 2024On Feature Learning in Structured State Space Models
148. NeurIPS 2024On the Efficiency of ERM in Feature Learning
149. NeurIPS 2024On the Impact of Feature Heterophily on Link Prediction with Graph Neural Networks
150. NeurIPS 2024Online Feature Updates Improve Online (Generalized) Label Shift Adaptation

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。