Gaussian Smoothing in Saliency Maps: The Stability-Fidelity Trade-Off in Neural Network Interpretability

• URL: http://arxiv.org/abs/2411.05837v2
• Date: Tue, 11 Mar 2025 10:19:52 GMT
• Title: Gaussian Smoothing in Saliency Maps: The Stability-Fidelity Trade-Off in Neural Network Interpretability
• Abstract summary: Saliency maps have been widely used to interpret the decisions of neural network classifiers.<n>Standard-based maps are frequently observed to be highly sensitive to the randomness of training data and the gradientity in the training process.<n>We study the role of Gaussian smoothing in the well-known Smooth-Grad algorithm in the stability of the gradient-based maps to the randomness of training samples.
• Score: 9.054540533394926
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Saliency maps have been widely used to interpret the decisions of neural network classifiers and discover phenomena from their learned functions. However, standard gradient-based maps are frequently observed to be highly sensitive to the randomness of training data and the stochasticity in the training process. In this work, we study the role of Gaussian smoothing in the well-known Smooth-Grad algorithm in the stability of the gradient-based maps to the randomness of training samples. We extend the algorithmic stability framework to gradient-based interpretation maps and prove bounds on the stability error of standard Simple-Grad, Integrated-Gradients, and Smooth-Grad saliency maps. Our theoretical results suggest the role of Gaussian smoothing in boosting the stability of gradient-based maps to the randomness of training settings. On the other hand, we analyze the faithfulness of the Smooth-Grad maps to the original Simple-Grad and show the lower fidelity under a more intense Gaussian smoothing. We support our theoretical results by performing several numerical experiments on standard image datasets. Our empirical results confirm our hypothesis on the fidelity-stability trade-off in the application of Gaussian smoothing to gradient-based interpretation maps.

Related papers

• Almost Sure Convergence Analysis of Stochastic Gradient Methods with Clipping and Additive Noise [7.061954653503474]
  gradient descent (SGD) with gradient clipping and additive noise has become a standard technique for machine learning training, particularly in applications.<n>SGD with gradient clipping and additive noise has become a standard technique for machine learning training, particularly in applications.
  arXiv  Detail & Related papers  (2026-09-10T18:48:16Z)
• Stochastic Gradient Descent in the Saddle-to-Saddle Regime of Deep Linear Networks [74.46751089984072]
  gradient descent (SGD) noise on descent in deep linear networks is poorly understood.<n>We investigate the dynamics of SGD during training of DLNs in the saddle-to-saddle regime.<n>Our results establish that SGD noise encodes information about the progression of feature learning but does not fundamentally alter the saddle-to-saddle dynamics.
  arXiv  Detail & Related papers  (2026-04-07T18:43:08Z)
• Training for Trustworthy Saliency Maps: Adversarial Training Meets Feature-Map Smoothing [4.014524824655106]
  We propose a lightweight feature-map smoothing block that applies a differentiable Gaussian filter in an intermediate layer.<n>Across FMNIST, CIFAR-10, and ImageNette, our method preserves the sparsity benefits of adversarial training while improving both input-side stability and output-side stability.
  arXiv  Detail & Related papers  (2026-03-07T18:00:05Z)
• Robust Stochastic Gradient Posterior Sampling with Lattice Based Discretisation [20.44428092865608]
  MCMC methods enable scalable posterior sampling but often suffer from sensitivity to minibatch size and gradient noise.<n>We propose Gradient Random Walk (SGLRW), an extension of the Lattice Random Walk discretization.
  arXiv  Detail & Related papers  (2026-02-17T18:09:49Z)
• Provably Convergent Decentralized Optimization over Directed Graphs under Generalized Smoothness [1.5892054128426507]
  Hessian norm is allowed to grow linearly with the gradient norm, thereby accommodating rapidly varying gradients beyond Lipschitz smoothness.<n>We integrate gradient-tracking techniques with gradient clipping to ensure accurate convergence over directed communication graphs.<n>Our results remain valid even when the gradient dissimilarity is unbounded, making the proposed framework more applicable to realistic heterogeneous data environments.
  arXiv  Detail & Related papers  (2026-01-07T04:25:33Z)
• Unlearning-based Neural Interpretations [51.99182464831169]
  We show that current baselines defined using static functions are biased, fragile and manipulable. We propose UNI to compute an (un)learnable, debiased and adaptive baseline by perturbing the input towards an unlearning direction of steepest ascent.
  arXiv  Detail & Related papers  (2024-10-10T16:02:39Z)
• Gradient-Variation Online Learning under Generalized Smoothness [56.38427425920781]
  gradient-variation online learning aims to achieve regret guarantees that scale with variations in gradients of online functions. Recent efforts in neural network optimization suggest a generalized smoothness condition, allowing smoothness to correlate with gradient norms. We provide the applications for fast-rate convergence in games and extended adversarial optimization.
  arXiv  Detail & Related papers  (2024-08-17T02:22:08Z)
• Stochastic Gradient Flow Dynamics of Test Risk and its Exact Solution for Weak Features [8.645858565518155]
  We provide a formula for computing the difference between test risk curves of pure gradient and gradient flows. We explicitly compute the corrections brought about by the added term in the dynamics. The analytical results are compared to simulations of discrete-time gradient descent and show good agreement.
  arXiv  Detail & Related papers  (2024-02-12T13:11:11Z)
• Leveraging Gradients for Unsupervised Accuracy Estimation under Distribution Shift [24.49100064042827]
  Estimating the test performance of a model without access to the ground-truth labels is a challenging problem.<n>We use the norm of classification-layer gradients, backpropagated from the cross-entropy loss after only one gradient step over test data.<n>Our intuition is that these gradients should be of higher magnitude when the model generalizes poorly.
  arXiv  Detail & Related papers  (2024-01-17T01:33:23Z)
• Using Stochastic Gradient Descent to Smooth Nonconvex Functions: Analysis of Implicit Graduated Optimization [0.6906005491572401]
  We show that noise in batch descent gradient (SGD) has the effect of smoothing objective function. We analyze a new graduated optimization algorithm that varies the degree of smoothing by learning rate and batch size.
  arXiv  Detail & Related papers  (2023-11-15T07:27:40Z)
• Multi-fidelity Stability for Graph Representation Learning [38.31487722188051]
  We introduce a weaker uniform generalization termed emphmulti-fidelity stability and give an example. We present lower bounds for the discrepancy between the two types of stability, which justified the multi-fidelity design.
  arXiv  Detail & Related papers  (2021-11-25T01:33:41Z)
• Tight Second-Order Certificates for Randomized Smoothing [106.06908242424481]
  We show that there also exists a universal curvature-like bound for Gaussian random smoothing. In addition to proving the correctness of this novel certificate, we show that SoS certificates are realizable and therefore tight.
  arXiv  Detail & Related papers  (2020-10-20T18:03:45Z)
• Reintroducing Straight-Through Estimators as Principled Methods for Stochastic Binary Networks [85.94999581306827]
  Training neural networks with binary weights and activations is a challenging problem due to the lack of gradients and difficulty of optimization over discrete weights. Many successful experimental results have been achieved with empirical straight-through (ST) approaches. At the same time, ST methods can be truly derived as estimators in the binary network (SBN) model with Bernoulli weights.
  arXiv  Detail & Related papers  (2020-06-11T23:58:18Z)
• Path Sample-Analytic Gradient Estimators for Stochastic Binary Networks [78.76880041670904]
  In neural networks with binary activations and or binary weights the training by gradient descent is complicated. We propose a new method for this estimation problem combining sampling and analytic approximation steps. We experimentally show higher accuracy in gradient estimation and demonstrate a more stable and better performing training in deep convolutional models.
  arXiv  Detail & Related papers  (2020-06-04T21:51:21Z)
• Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution [70.78655569298923]
  Integrated Gradients as an attribution method for deep neural network models offers simple implementability. It suffers from noisiness of explanations which affects the ease of interpretability. The SmoothGrad technique is proposed to solve the noisiness issue and smoothen the attribution maps of any gradient-based attribution method.
  arXiv  Detail & Related papers  (2020-04-22T10:43:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.