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 42 篇，第 1 / 1 页

1. ICLR 2025A Differentiable Rank-Based Objective for Better Feature Learning
2. ICLR 2025Accelerating Diffusion Transformers with Token-wise Feature Caching
3. ICLR 2025AI as Humanity’s Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text
4. ICLR 2025AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution
5. ICLR 2025Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness
6. ICLR 2025Breaking Class Barriers: Efficient Dataset Distillation via Inter-Class Feature Compensator
7. ICLR 2025Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index Model
8. ICLR 2025Capturing the Temporal Dependence of Training Data Influence
9. ICLR 2025Deep Networks Learn Features From Local Discontinuities in the Label Function
10. ICLR 2025DICE: Data Influence Cascade in Decentralized Learning
11. ICLR 2025Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion Models
12. ICLR 2025Explain Yourself, Briefly! Self-Explaining Neural Networks with Concise Sufficient Reasons
13. ICLR 2025Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks
14. ICLR 2025Feature Responsiveness Scores: Model-Agnostic Explanations for Recourse
15. ICLR 2025Feature-Based Online Bilateral Trade
16. ICLR 2025For Better or For Worse? Learning Minimum Variance Features With Label Augmentation
17. ICLR 2025Formation of Representations in Neural Networks
18. ICLR 2025GNNs Getting ComFy: Community and Feature Similarity Guided Rewiring
19. ICLR 2025Graph Neural Ricci Flow: Evolving Feature from a Curvature Perspective
20. ICLR 2025How Feature Learning Can Improve Neural Scaling Laws
21. ICLR 2025Influence Functions for Scalable Data Attribution in Diffusion Models
22. ICLR 2025InstaSHAP: Interpretable Additive Models Explain Shapley Values Instantly
23. ICLR 2025Joint Graph Rewiring and Feature Denoising via Spectral Resonance
24. ICLR 2025Learning Hierarchical Polynomials of Multiple Nonlinear Features
25. ICLR 2025Local Loss Optimization in the Infinite Width: Stable Parameterization of Predictive Coding Networks and Target Propagation
26. ICLR 2025LoRanPAC: Low-rank Random Features and Pre-trained Models for Bridging Theory and Practice in Continual Learning
27. ICLR 2025Machine Unlearning via Simulated Oracle Matching
28. ICLR 2025Make Haste Slowly: A Theory of Emergent Structured Mixed Selectivity in Feature Learning ReLU Networks
29. ICLR 2025MaxCutPool: differentiable feature-aware Maxcut for pooling in graph neural networks
30. ICLR 2025On the Feature Learning in Diffusion Models
31. ICLR 2025Pursuing Feature Separation based on Neural Collapse for Out-of-Distribution Detection
32. ICLR 2025RankSHAP: Shapley Value Based Feature Attributions for Learning to Rank
33. ICLR 2025Rethinking Multiple-Instance Learning From Feature Space to Probability Space
34. ICLR 2025Rethinking Shapley Value for Negative Interactions in Non-convex Games
35. ICLR 2025Robust Feature Learning for Multi-Index Models in High Dimensions
36. ICLR 2025Salvage: Shapley-distribution Approximation Learning Via Attribution Guided Exploration for Explainable Image Classification
37. ICLR 2025Scalable Influence and Fact Tracing for Large Language Model Pretraining
38. ICLR 2025Small-to-Large Generalization: Training Data Influences Models Consistently Across Scale
39. ICLR 2025Three Mechanisms of Feature Learning in a Linear Network
40. ICLR 2025Tree-Wasserstein Distance for High Dimensional Data with a Latent Feature Hierarchy
41. ICLR 2025Unlearning-based Neural Interpretations
42. ICLR 2025When GNNs meet symmetry in ILPs: an orbit-based feature augmentation approach

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。