Unlearning-based Neural Interpretations

• URL: http://arxiv.org/abs/2410.08069v2
• Date: Mon, 10 Feb 2025 22:59:07 GMT
• Title: Unlearning-based Neural Interpretations
• Authors: Ching Lam Choi, Alexandre Duplessis, Serge Belongie,
• Abstract summary: 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.
• Score: 51.99182464831169
• License:
• Abstract: Gradient-based interpretations often require an anchor point of comparison to avoid saturation in computing feature importance. We show that current baselines defined using static functions--constant mapping, averaging or blurring--inject harmful colour, texture or frequency assumptions that deviate from model behaviour. This leads to accumulation of irregular gradients, resulting in attribution maps that are biased, fragile and manipulable. Departing from the static approach, we propose UNI to compute an (un)learnable, debiased and adaptive baseline by perturbing the input towards an unlearning direction of steepest ascent. Our method discovers reliable baselines and succeeds in erasing salient features, which in turn locally smooths the high-curvature decision boundaries. Our analyses point to unlearning as a promising avenue for generating faithful, efficient and robust interpretations.

Related papers

• Revisiting Gradient-based Uncertainty for Monocular Depth Estimation [10.502852645001882]
  We introduce gradient-based uncertainty estimation for monocular depth estimation models. We demonstrate that our approach is effective in determining the uncertainty without re-training. In particular, for models trained with monocular sequences and therefore most prone to uncertainty, our method outperforms related approaches.
  arXiv  Detail & Related papers  (2025-02-09T17:21:41Z)
• Robust Representation Consistency Model via Contrastive Denoising [83.47584074390842]
  randomized smoothing provides theoretical guarantees for certifying robustness against adversarial perturbations. diffusion models have been successfully employed for randomized smoothing to purify noise-perturbed samples. We reformulate the generative modeling task along the diffusion trajectories in pixel space as a discriminative task in the latent space.
  arXiv  Detail & Related papers  (2025-01-22T18:52:06Z)
• Score-based Continuous-time Discrete Diffusion Models [102.65769839899315]
  We extend diffusion models to discrete variables by introducing a Markov jump process where the reverse process denoises via a continuous-time Markov chain. We show that an unbiased estimator can be obtained via simple matching the conditional marginal distributions. We demonstrate the effectiveness of the proposed method on a set of synthetic and real-world music and image benchmarks.
  arXiv  Detail & Related papers  (2022-11-30T05:33:29Z)
• Towards More Robust Interpretation via Local Gradient Alignment [37.464250451280336]
  We show that for every non-negative homogeneous neural network, a naive $ell$-robust criterion for gradients is textitnot normalization invariant. We propose to combine both $ell$ and cosine distance-based criteria as regularization terms to leverage the advantages of both in aligning the local gradient. We experimentally show that models trained with our method produce much more robust interpretations on CIFAR-10 and ImageNet-100.
  arXiv  Detail & Related papers  (2022-11-29T03:38:28Z)
• Deep Active Learning with Noise Stability [24.54974925491753]
  Uncertainty estimation for unlabeled data is crucial to active learning. We propose a novel algorithm that leverages noise stability to estimate data uncertainty. Our method is generally applicable in various tasks, including computer vision, natural language processing, and structural data analysis.
  arXiv  Detail & Related papers  (2022-05-26T13:21:01Z)
• On the Benefits of Large Learning Rates for Kernel Methods [110.03020563291788]
  We show that a phenomenon can be precisely characterized in the context of kernel methods. We consider the minimization of a quadratic objective in a separable Hilbert space, and show that with early stopping, the choice of learning rate influences the spectral decomposition of the obtained solution.
  arXiv  Detail & Related papers  (2022-02-28T13:01:04Z)
• Linear Adversarial Concept Erasure [108.37226654006153]
  We formulate the problem of identifying and erasing a linear subspace that corresponds to a given concept. We show that the method is highly expressive, effectively mitigating bias in deep nonlinear classifiers while maintaining tractability and interpretability.
  arXiv  Detail & Related papers  (2022-01-28T13:00:17Z)
• Path Integrals for the Attribution of Model Uncertainties [0.18899300124593643]
  We present a novel algorithm that relies on in-distribution curves connecting a feature vector to some counterfactual counterpart. We validate our approach on benchmark image data sets with varying resolution, and show that it significantly simplifies interpretability.
  arXiv  Detail & Related papers  (2021-07-19T11:07:34Z)
• Gradient Descent for Deep Matrix Factorization: Dynamics and Implicit Bias towards Low Rank [1.9350867959464846]
  In deep learning, gradientdescent tends to prefer solutions which generalize well. In this paper we analyze the dynamics of gradient descent in the simplifiedsetting of linear networks and of an estimation problem.
  arXiv  Detail & Related papers  (2020-11-27T15:08:34Z)
• 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)

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.