Regulating Model Reliance on Non-Robust Features by Smoothing Input Marginal Density

• URL: http://arxiv.org/abs/2407.04370v2
• Date: Tue, 9 Jul 2024 03:09:41 GMT
• Title: Regulating Model Reliance on Non-Robust Features by Smoothing Input Marginal Density
• Authors: Peiyu Yang, Naveed Akhtar, Mubarak Shah, Ajmal Mian,
• Abstract summary: Trustworthy machine learning requires meticulous regulation of model reliance on non-robust features. We propose a framework to delineate and regulate such features by attributing model predictions to the input.
• Score: 93.32594873253534
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Trustworthy machine learning necessitates meticulous regulation of model reliance on non-robust features. We propose a framework to delineate and regulate such features by attributing model predictions to the input. Within our approach, robust feature attributions exhibit a certain consistency, while non-robust feature attributions are susceptible to fluctuations. This behavior allows identification of correlation between model reliance on non-robust features and smoothness of marginal density of the input samples. Hence, we uniquely regularize the gradients of the marginal density w.r.t. the input features for robustness. We also devise an efficient implementation of our regularization to address the potential numerical instability of the underlying optimization process. Moreover, we analytically reveal that, as opposed to our marginal density smoothing, the prevalent input gradient regularization smoothens conditional or joint density of the input, which can cause limited robustness. Our experiments validate the effectiveness of the proposed method, providing clear evidence of its capability to address the feature leakage problem and mitigate spurious correlations. Extensive results further establish that our technique enables the model to exhibit robustness against perturbations in pixel values, input gradients, and density.

Related papers

• Conditional Pseudo-Reversible Normalizing Flow for Surrogate Modeling in Quantifying Uncertainty Propagation [11.874729463016227]
  We introduce a conditional pseudo-reversible normalizing flow for constructing surrogate models of a physical model polluted by additive noise. The training process utilizes dataset consisting of input-output pairs without requiring prior knowledge about the noise and the function. Our model, once trained, can generate samples from any conditional probability density functions whose high probability regions are covered by the training set.
  arXiv  Detail & Related papers  (2024-03-31T00:09:58Z)
• The Risk of Federated Learning to Skew Fine-Tuning Features and Underperform Out-of-Distribution Robustness [50.52507648690234]
  Federated learning has the risk of skewing fine-tuning features and compromising the robustness of the model. We introduce three robustness indicators and conduct experiments across diverse robust datasets. Our approach markedly enhances the robustness across diverse scenarios, encompassing various parameter-efficient fine-tuning methods.
  arXiv  Detail & Related papers  (2024-01-25T09:18:51Z)
• Anomaly Detection with Variance Stabilized Density Estimation [49.46356430493534]
  We present a variance-stabilized density estimation problem for maximizing the likelihood of the observed samples. To obtain a reliable anomaly detector, we introduce a spectral ensemble of autoregressive models for learning the variance-stabilized distribution. We have conducted an extensive benchmark with 52 datasets, demonstrating that our method leads to state-of-the-art results.
  arXiv  Detail & Related papers  (2023-06-01T11:52:58Z)
• Robustness of Energy Landscape Control to Dephasing [0.0]
  We analyze the robustness of the fidelity error, as measured by the logarithmic sensitivity function, to dephasing processes. We show that despite the different log sensitivity calculations employed in this study, both demonstrate that the log-sensitivity of the fidelity error to dephasing results in a conventional trade-off between performance and robustness.
  arXiv  Detail & Related papers  (2023-03-10T01:51:47Z)
• Density-Softmax: Efficient Test-time Model for Uncertainty Estimation and Robustness under Distribution Shifts [8.431465371266391]
  Density-Softmax is a sampling-free deterministic framework for uncertainty estimation. We show that our model is the solution of minimax uncertainty risk. Our method enjoys competitive results with state-of-the-art techniques in terms of uncertainty and robustness.
  arXiv  Detail & Related papers  (2023-02-13T16:21:03Z)
• Monotonicity and Double Descent in Uncertainty Estimation with Gaussian Processes [52.92110730286403]
  It is commonly believed that the marginal likelihood should be reminiscent of cross-validation metrics and that both should deteriorate with larger input dimensions. We prove that by tuning hyper parameters, the performance, as measured by the marginal likelihood, improves monotonically with the input dimension. We also prove that cross-validation metrics exhibit qualitatively different behavior that is characteristic of double descent.
  arXiv  Detail & Related papers  (2022-10-14T08:09:33Z)
• Robustness and Accuracy Could Be Reconcilable by (Proper) Definition [109.62614226793833]
  The trade-off between robustness and accuracy has been widely studied in the adversarial literature. We find that it may stem from the improperly defined robust error, which imposes an inductive bias of local invariance. By definition, SCORE facilitates the reconciliation between robustness and accuracy, while still handling the worst-case uncertainty.
  arXiv  Detail & Related papers  (2022-02-21T10:36:09Z)
• Certifying Model Accuracy under Distribution Shifts [151.67113334248464]
  We present provable robustness guarantees on the accuracy of a model under bounded Wasserstein shifts of the data distribution. We show that a simple procedure that randomizes the input of the model within a transformation space is provably robust to distributional shifts under the transformation.
  arXiv  Detail & Related papers  (2022-01-28T22:03:50Z)
• Low-rank Characteristic Tensor Density Estimation Part II: Compression and Latent Density Estimation [31.631861197477185]
  Learning generative probabilistic models is a core problem in machine learning. This paper proposes a joint dimensionality reduction and non-parametric density estimation framework. We demonstrate that the proposed model achieves very promising results on regression tasks, sampling, and anomaly detection.
  arXiv  Detail & Related papers  (2021-06-20T00:38:56Z)

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.