paper-with-me

Papers

Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate Models

2023-05-23 · Andrew Engel, Zhichao Wang, Natalie S. Frank, Ioana Dumitriu, Sutanay Choudhury, Anand Sarwate, Tony Chiang

A recent trend in explainable AI research has focused on surrogate modeling, where neural networks are approximated as simpler ML algorithms such as kernel machines. A second trend has been to utilize kernel functions in various explain-by-example or data attribution tasks. In this work, we combine these two trends to analyze approximate empirical neural tangent kernels (eNTK) for data attribution. Approximation is critical for eNTK analysis due to the high computational cost to compute the eNTK. We define new approximate eNTK and perform novel analysis on how well the resulting kernel machine surrogate models correlate with the underlying neural network. We introduce two new random projection variants of approximate eNTK which allow users to tune the time and memory complexity of their calculation. We conclude that kernel machines using approximate neural tangent kernel as the kernel function are effective surrogate models, with the introduced trace NTK the most consistent performer. Open source software allowing users to efficiently calculate kernel functions in the PyTorch framework is available (https://github.com/pnnl/projection\_ntk).

📄 PDF Abstract BibTeX arXiv:2305.14585

Code (1)

pnnl/projection_ntk 공식 구현 pytorch

Tasks

Data PoisoningLanguage ModellingLarge Language Model

Methods 이 논문이 사용한 방법론

NTK 설명 없음

Similar Papers 제목 키워드 기반

Towards Spatially-Aware and Optimally Faithful Concept-Based Explanations

2025-04-15 · Shubham Kumar, Dwip Dalal, Narendra Ahuja

Post-hoc, unsupervised concept-based explanation methods (U-CBEMs) are a promising tool for generating semantic explanations of the decision-making processes in deep neural networks, having applications in both model imp…

Decision Making

On the Complexity-Faithfulness Trade-off of Gradient-Based Explanations

2025-08-14 · Amir Mehrpanah, Matteo Gamba, Kevin Smith, Hossein Azizpour arxiv

ReLU networks, while prevalent for visual data, have sharp transitions, sometimes relying on individual pixels for predictions, making vanilla gradient-based explanations noisy and difficult to interpret. Existing method…

Select Wisely and Explain: Active Learning and Probabilistic Local Post-hoc Explainability

2021-08-16 · Aditya Saini, Ranjitha Prasad

Albeit the tremendous performance improvements in designing complex artificial intelligence (AI) systems in data-intensive domains, the black-box nature of these systems leads to the lack of trustworthiness. Post-hoc int…

Active LearningGaussian ProcessesGPR

Faithful Model Explanations through Energy-Constrained Conformal Counterfactuals

2023-12-17 · Patrick Altmeyer, Mojtaba Farmanbar, Arie van Deursen, Cynthia C. S. Liem

Counterfactual explanations offer an intuitive and straightforward way to explain black-box models and offer algorithmic recourse to individuals. To address the need for plausible explanations, existing work has primaril…

Conformal Predictioncounterfactual

A generalized neural tangent kernel for surrogate gradient learning

2024-05-24 · Luke Eilers, Raoul-Martin Memmesheimer, Sven Goedeke

State-of-the-art neural network training methods depend on the gradient of the network function. Therefore, they cannot be applied to networks whose activation functions do not have useful derivatives, such as binary and…