Characterising Bias in Compressed Models

• URL: http://arxiv.org/abs/2010.03058v2
• Date: Fri, 18 Dec 2020 14:03:13 GMT
• Title: Characterising Bias in Compressed Models
• Authors: Sara Hooker, Nyalleng Moorosi, Gregory Clark, Samy Bengio, Emily Denton
• Abstract summary: pruning and quantization techniques achieve high levels of compression with negligible impact on top-line metrics. We call this subset Compression Identified Exemplars (CIE) CIE is a relatively small subset but a great contributor of error in the model. We propose its use as a human-in-the-loop auditing tool to surface a tractable subset of the dataset.
• Score: 20.901725971127973
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The popularity and widespread use of pruning and quantization is driven by the severe resource constraints of deploying deep neural networks to environments with strict latency, memory and energy requirements. These techniques achieve high levels of compression with negligible impact on top-line metrics (top-1 and top-5 accuracy). However, overall accuracy hides disproportionately high errors on a small subset of examples; we call this subset Compression Identified Exemplars (CIE). We further establish that for CIE examples, compression amplifies existing algorithmic bias. Pruning disproportionately impacts performance on underrepresented features, which often coincides with considerations of fairness. Given that CIE is a relatively small subset but a great contributor of error in the model, we propose its use as a human-in-the-loop auditing tool to surface a tractable subset of the dataset for further inspection or annotation by a domain expert. We provide qualitative and quantitative support that CIE surfaces the most challenging examples in the data distribution for human-in-the-loop auditing.

Related papers

• A Disentangled Representation Learning Framework for Low-altitude Network Coverage Prediction [42.71119573226285]
  The expansion of the low-altitude economy has underscored the significance of Low-Altitude Network Coverage (LANC) prediction for designing aerial corridors.<n>We introduce a dual strategy comprising expert knowledge-based feature compression and disentangled representation learning.<n> Experimental evaluation confirms the efficacy of our framework, yielding a 7% reduction in error compared to the best baseline algorithm.
  arXiv  Detail & Related papers  (2025-07-13T05:31:35Z)
• Boosting Test Performance with Importance Sampling--a Subpopulation Perspective [16.678910111353307]
  In this paper, we identify important sampling as a simple yet powerful tool for solving the subpopulation problem. We provide a new systematic formulation of the subpopulation problem and explicitly identify the assumptions that are not clearly stated in the existing works. On the application side, we demonstrate a single estimator is enough to solve the subpopulation problem.
  arXiv  Detail & Related papers  (2024-12-17T15:25:24Z)
• EControl: Fast Distributed Optimization with Compression and Error Control [8.624830915051021]
  We propose EControl, a novel mechanism that can regulate the strength of the feedback signal. We show that EControl mitigates the naive implementation of our method and support our findings.
  arXiv  Detail & Related papers  (2023-11-06T10:00:13Z)
• Causality and Independence Enhancement for Biased Node Classification [56.38828085943763]
  We propose a novel Causality and Independence Enhancement (CIE) framework, applicable to various graph neural networks (GNNs) Our approach estimates causal and spurious features at the node representation level and mitigates the influence of spurious correlations. Our approach CIE not only significantly enhances the performance of GNNs but outperforms state-of-the-art debiased node classification methods.
  arXiv  Detail & Related papers  (2023-10-14T13:56:24Z)
• Correcting sampling biases via importance reweighting for spatial modeling [2.6862667248315386]
  In machine learning models, the estimation of errors is often complex due to distribution bias. We introduce an approach based on the ideas of importance sampling to obtain an unbiased estimate of the target error.
  arXiv  Detail & Related papers  (2023-09-09T15:36:28Z)
• Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures [93.17009514112702]
  Pruning, setting a significant subset of the parameters of a neural network to zero, is one of the most popular methods of model compression. Despite existing evidence for this phenomenon, the relationship between neural network pruning and induced bias is not well-understood.
  arXiv  Detail & Related papers  (2023-04-25T07:42:06Z)
• Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness [68.97830259849086]
  Most datasets only capture a simpler subproblem and likely suffer from spurious features. We study adversarial robustness - a local generalization property - to reveal hard, model-specific instances and spurious features. Unlike in other applications, where perturbation models are designed around subjective notions of imperceptibility, our perturbation models are efficient and sound. Surprisingly, with such perturbations, a sufficiently expressive neural solver does not suffer from the limitations of the accuracy-robustness trade-off common in supervised learning.
  arXiv  Detail & Related papers  (2021-10-21T07:28:11Z)
• Unsupervised Learning of Debiased Representations with Pseudo-Attributes [85.5691102676175]
  We propose a simple but effective debiasing technique in an unsupervised manner. We perform clustering on the feature embedding space and identify pseudoattributes by taking advantage of the clustering results. We then employ a novel cluster-based reweighting scheme for learning debiased representation.
  arXiv  Detail & Related papers  (2021-08-06T05:20:46Z)
• Enhanced Principal Component Analysis under A Collaborative-Robust Framework [89.28334359066258]
  We introduce a general collaborative-robust weight learning framework that combines weight learning and robust loss in a non-trivial way. Under the proposed framework, only a part of well-fitting samples are activated which indicates more importance during training, and others, whose errors are large, will not be ignored. In particular, the negative effects of inactivated samples are alleviated by the robust loss function.
  arXiv  Detail & Related papers  (2021-03-22T15:17:37Z)
• Robustness in Compressed Neural Networks for Object Detection [2.9823962001574182]
  The sensitivity of compressed models to different distortion types is nuanced. Some of the corruptions are heavily impacted by the compression methods. Data augmentation was confirmed to positively affect models' robustness.
  arXiv  Detail & Related papers  (2021-02-10T15:52:11Z)
• Compressing Large Sample Data for Discriminant Analysis [78.12073412066698]
  We consider the computational issues due to large sample size within the discriminant analysis framework. We propose a new compression approach for reducing the number of training samples for linear and quadratic discriminant analysis.
  arXiv  Detail & Related papers  (2020-05-08T05:09:08Z)

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.