Feature Attribution papers, 2023–2026

Key findings

• Feature Attribution went from 118 papers in 2023 to 219 in 2026, roughly 1.9x in three years.
• NeurIPS publishes the most Feature Attribution work: 193 papers from 2023 to 2026, 28% of the four-venue total.
• The fastest-growing overlap is with Theory · learning theory: papers tagged with both rose from 1 in 2023 to 14 in 2026.
• Among the 5 topics under Interpretability, it ranks #1 by 2026 paper count; the fastest grower in the group, Mechanistic Interpretability, is up 8.1x versus 1.9x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Feature Attribution papers

47 papers, page 1 of 1

1. ICML 2024A New Computationally Efficient Algorithm to solve Feature Selection for Functional Data Classification in High-dimensional Spaces
2. ICML 2024A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks
3. ICML 2024Acquisition Conditioned Oracle for Nongreedy Active Feature Acquisition
4. ICML 2024Asymptotics of feature learning in two-layer networks after one gradient-step
5. ICML 2024Asymptotics of Learning with Deep Structured (Random) Features
6. ICML 2024Balancing Feature Similarity and Label Variability for Optimal Size-Aware One-shot Subset Selection
7. ICML 2024Benchmarking Deletion Metrics with the Principled Explanations
8. ICML 2024Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning
9. ICML 2024Complexity Matters: Feature Learning in the Presence of Spurious Correlations
10. ICML 2024Contextual Feature Selection with Conditional Stochastic Gates
11. ICML 2024Critical feature learning in deep neural networks
12. ICML 2024Critical windows: non-asymptotic theory for feature emergence in diffusion models
13. ICML 2024Decoupling Feature Extraction and Classification Layers for Calibrated Neural Networks
14. ICML 2024DFD: Distilling the Feature Disparity Differently for Detectors
15. ICML 2024Don't trust your eyes: on the (un)reliability of feature visualizations
16. ICML 2024EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
17. ICML 2024Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanation
18. ICML 2024Feature Contamination: Neural Networks Learn Uncorrelated Features and Fail to Generalize
19. ICML 2024Feature Distribution on Graph Topology Mediates the Effect of Graph Convolution: Homophily Perspective
20. ICML 2024Feature Importance Disparities for Data Bias Investigations
21. ICML 2024Feature Reuse and Scaling: Understanding Transfer Learning with Protein Language Models
22. ICML 2024Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions
23. ICML 2024High-dimensional Linear Bandits with Knapsacks
24. ICML 2024InterpreTabNet: Distilling Predictive Signals from Tabular Data by Salient Feature Interpretation
25. ICML 2024Iterative Search Attribution for Deep Neural Networks
26. ICML 2024Learning 1-Bit Tiny Object Detector with Discriminative Feature Refinement
27. ICML 2024Learning in Feature Spaces via Coupled Covariances: Asymmetric Kernel SVD and Nyström method
28. ICML 2024Local Feature Selection without Label or Feature Leakage for Interpretable Machine Learning Predictions
29. ICML 2024Manifold Integrated Gradients: Riemannian Geometry for Feature Attribution
30. ICML 2024MFTN: A Multi-scale Feature Transfer Network Based on IMatchFormer for Hyperspectral Image Super-Resolution
31. ICML 2024Multi-layer Rehearsal Feature Augmentation for Class-Incremental Learning
32. ICML 2024Multiply-Robust Causal Change Attribution
33. ICML 2024Observable Propagation: Uncovering Feature Vectors in Transformers
34. ICML 2024On dimensionality of feature vectors in MPNNs
35. ICML 2024On the Tractability of SHAP Explanations under Markovian Distributions
36. ICML 2024Pragmatic Feature Preferences: Learning Reward-Relevant Preferences from Human Input
37. ICML 2024Prospector Heads: Generalized Feature Attribution for Large Models & Data
38. ICML 2024ProtoGate: Prototype-based Neural Networks with Global-to-local Feature Selection for Tabular Biomedical Data
39. ICML 2024Provable Benefits of Local Steps in Heterogeneous Federated Learning for Neural Networks: A Feature Learning Perspective
40. ICML 2024Provably Better Explanations with Optimized Aggregation of Feature Attributions
41. ICML 2024Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples
42. ICML 2024Saliency strikes back: How filtering out high frequencies improves white-box explanations
43. ICML 2024SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning
44. ICML 2024Single-Model Attribution of Generative Models Through Final-Layer Inversion
45. ICML 2024Synergistic Integration of Coordinate Network and Tensorial Feature for Improving Neural Radiance Fields from Sparse Inputs
46. ICML 2024The Balanced-Pairwise-Affinities Feature Transform
47. ICML 2024Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learning

FAQ

How many Feature Attribution papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

695 in total: 118 in 2023, 168 in 2024, 190 in 2025, 219 in 2026.

How many Feature Attribution papers are at NeurIPS 2026?

NeurIPS 2026 has 61 Feature Attribution papers, versus 57 the year before.

How many Feature Attribution papers are at ICLR 2026?

ICLR 2026 has 53 Feature Attribution papers, versus 42 the year before.

How many Feature Attribution papers are at ICML 2026?

ICML 2026 has 56 Feature Attribution papers, versus 51 the year before.

How many Feature Attribution papers are at CVPR 2026?

CVPR 2026 has 49 Feature Attribution papers, versus 40 the year before.

Which conference publishes the most Feature Attribution papers?

NeurIPS, with 193 papers from 2023 to 2026.