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 695 篇，第 11 / 14 页

501. ICML 2024Feature Reuse and Scaling: Understanding Transfer Learning with Protein Language Models
502. ICML 2024Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions
503. ICML 2024High-dimensional Linear Bandits with Knapsacks
504. ICML 2024InterpreTabNet: Distilling Predictive Signals from Tabular Data by Salient Feature Interpretation
505. ICML 2024Iterative Search Attribution for Deep Neural Networks
506. ICML 2024Learning 1-Bit Tiny Object Detector with Discriminative Feature Refinement
507. ICML 2024Learning in Feature Spaces via Coupled Covariances: Asymmetric Kernel SVD and Nyström method
508. ICML 2024Local Feature Selection without Label or Feature Leakage for Interpretable Machine Learning Predictions
509. ICML 2024Manifold Integrated Gradients: Riemannian Geometry for Feature Attribution
510. ICML 2024MFTN: A Multi-scale Feature Transfer Network Based on IMatchFormer for Hyperspectral Image Super-Resolution
511. ICML 2024Multi-layer Rehearsal Feature Augmentation for Class-Incremental Learning
512. ICML 2024Multiply-Robust Causal Change Attribution
513. ICML 2024Observable Propagation: Uncovering Feature Vectors in Transformers
514. ICML 2024On dimensionality of feature vectors in MPNNs
515. ICML 2024On the Tractability of SHAP Explanations under Markovian Distributions
516. ICML 2024Pragmatic Feature Preferences: Learning Reward-Relevant Preferences from Human Input
517. ICML 2024Prospector Heads: Generalized Feature Attribution for Large Models & Data
518. ICML 2024ProtoGate: Prototype-based Neural Networks with Global-to-local Feature Selection for Tabular Biomedical Data
519. ICML 2024Provable Benefits of Local Steps in Heterogeneous Federated Learning for Neural Networks: A Feature Learning Perspective
520. ICML 2024Provably Better Explanations with Optimized Aggregation of Feature Attributions
521. ICML 2024Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples
522. ICML 2024Saliency strikes back: How filtering out high frequencies improves white-box explanations
523. ICML 2024SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning
524. ICML 2024Single-Model Attribution of Generative Models Through Final-Layer Inversion
525. ICML 2024Synergistic Integration of Coordinate Network and Tensorial Feature for Improving Neural Radiance Fields from Sparse Inputs
526. ICML 2024The Balanced-Pairwise-Affinities Feature Transform
527. ICML 2024Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learning
528. NeurIPS 2024$\texttt{dattri}$: A Library for Efficient Data Attribution
529. NeurIPS 2024Benchmarking the Attribution Quality of Vision Models
530. NeurIPS 2024Credit Attribution and Stable Compression
531. NeurIPS 2024Data-faithful Feature Attribution: Mitigating Unobservable Confounders via Instrumental Variables
532. NeurIPS 2024DeepDRK: Deep Dependency Regularized Knockoff for Feature Selection
533. NeurIPS 2024Denoising Diffusion Path: Attribution Noise Reduction with An Auxiliary Diffusion Model
534. NeurIPS 2024DETAIL: Task DEmonsTration Attribution for Interpretable In-context Learning
535. NeurIPS 2024Dimension-free deterministic equivalents and scaling laws for random feature regression
536. NeurIPS 2024Efficient Sketches for Training Data Attribution and Studying the Loss Landscape
537. NeurIPS 2024Efficiently Learning Significant Fourier Feature Pairs for Statistical Independence Testing
538. NeurIPS 2024EnOF-SNN: Training Accurate Spiking Neural Networks via Enhancing the Output Feature
539. NeurIPS 2024ETO:Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography Hypotheses
540. NeurIPS 2024Explanations that reveal all through the definition of encoding
541. NeurIPS 2024Fast Iterative Hard Thresholding Methods with Pruning Gradient Computations
542. NeurIPS 2024Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivity
543. NeurIPS 2024FUGAL: Feature-fortified Unrestricted Graph Alignment
544. NeurIPS 2024Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning
545. NeurIPS 2024Handling Learnwares from Heterogeneous Feature Spaces with Explicit Label Exploitation
546. NeurIPS 2024Infinite-Dimensional Feature Interaction
547. NeurIPS 2024Is Function Similarity Over-Engineered? Building a Benchmark
548. NeurIPS 2024Learning Low-Rank Feature for Thorax Disease Classification
549. NeurIPS 2024Learning Successor Features the Simple Way
550. NeurIPS 2024MatrixNet: Learning over symmetry groups using learned group representations

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。