Explaining text classifiers through progressive neighborhood approximation with realistic samples

• URL: http://arxiv.org/abs/2302.07733v1
• Date: Sat, 11 Feb 2023 11:42:39 GMT
• Title: Explaining text classifiers through progressive neighborhood approximation with realistic samples
• Authors: Yi Cai, Arthur Zimek, Eirini Ntoutsi, Gerhard Wunder
• Abstract summary: The importance of neighborhood construction in local explanation methods has been highlighted in the literature. Several attempts have been made to improve neighborhood quality for high-dimensional data, for example, texts, by adopting generative models. We propose a progressive approximation approach that refines the neighborhood of a to-be-explained decision with a careful two-stage approach.
• Score: 19.26084350822197
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The importance of neighborhood construction in local explanation methods has been already highlighted in the literature. And several attempts have been made to improve neighborhood quality for high-dimensional data, for example, texts, by adopting generative models. Although the generators produce more realistic samples, the intuitive sampling approaches in the existing solutions leave the latent space underexplored. To overcome this problem, our work, focusing on local model-agnostic explanations for text classifiers, proposes a progressive approximation approach that refines the neighborhood of a to-be-explained decision with a careful two-stage interpolation using counterfactuals as landmarks. We explicitly specify the two properties that should be satisfied by generative models, the reconstruction ability and the locality-preserving property, to guide the selection of generators for local explanation methods. Moreover, noticing the opacity of generative models during the study, we propose another method that implements progressive neighborhood approximation with probability-based editions as an alternative to the generator-based solution. The explanation results from both methods consist of word-level and instance-level explanations benefiting from the realistic neighborhood. Through exhaustive experiments, we qualitatively and quantitatively demonstrate the effectiveness of the two proposed methods.

Related papers

• Transparent Neighborhood Approximation for Text Classifier Explanation [12.803856207094615]
  This paper introduces a probability-based editing method as an alternative to black-box text generators. The resultant explanation method, XPROB, exhibits competitive performance according to the evaluation conducted on two real-world datasets.
  arXiv  Detail & Related papers  (2024-11-25T10:10:09Z)
• Finding Patterns in Ambiguity: Interpretable Stress Testing in the Decision~Boundary [3.66599628097164]
  We propose a novel approach to enhance the interpretability of deep binary classifiers. We select representative samples from the decision boundary and apply post-model explanation algorithms. Our work contributes to the responsible development and deployment of reliable machine learning systems.
  arXiv  Detail & Related papers  (2024-08-12T17:14:41Z)
• Representation and De-interleaving of Mixtures of Hidden Markov Processes [3.7348616912887445]
  De-interleaving of mixtures of Hidden Markov Processes (HMPs) generally depends on its representation model. This paper proposes a novel representation model and corresponding de-interleaving methods for the mixtures of HMPs.
  arXiv  Detail & Related papers  (2024-06-01T12:24:23Z)
• Compressing Image-to-Image Translation GANs Using Local Density Structures on Their Learned Manifold [69.33930972652594]
  Generative Adversarial Networks (GANs) have shown remarkable success in modeling complex data distributions for image-to-image translation. Existing GAN compression methods mainly rely on knowledge distillation or convolutional classifiers' pruning techniques. We propose a new approach by explicitly encouraging the pruned model to preserve the density structure of the original parameter-heavy model on its learned manifold. Our experiments on image translation GAN models, Pix2Pix and CycleGAN, with various benchmark datasets and architectures demonstrate our method's effectiveness.
  arXiv  Detail & Related papers  (2023-12-22T15:43:12Z)
• Flow Factorized Representation Learning [109.51947536586677]
  We introduce a generative model which specifies a distinct set of latent probability paths that define different input transformations. We show that our model achieves higher likelihoods on standard representation learning benchmarks while simultaneously being closer to approximately equivariant models.
  arXiv  Detail & Related papers  (2023-09-22T20:15:37Z)
• Diffusion Action Segmentation [63.061058214427085]
  We propose a novel framework via denoising diffusion models, which shares the same inherent spirit of such iterative refinement. In this framework, action predictions are iteratively generated from random noise with input video features as conditions.
  arXiv  Detail & Related papers  (2023-03-31T10:53:24Z)
• XPROAX-Local explanations for text classification with progressive neighborhood approximation [13.312630052709766]
  We propose a progressive approximation of the neighborhood using counterfactual instances as initial landmarks. We then refine counterfactuals and generate factuals in the neighborhood of the input instance to be explained. Our experiments on real-world datasets demonstrate that our method outperforms the competitors in terms of usefulness and stability.
  arXiv  Detail & Related papers  (2021-09-30T11:01:07Z)
• Unsupervised Sentence-embeddings by Manifold Approximation and Projection [3.04585143845864]
  We propose a novel technique to generate sentence-embeddings in an unsupervised fashion by projecting the sentences onto a fixed-dimensional manifold. We test our approach, which we term EMAP or Embeddings by Manifold Approximation and Projection, on six publicly available text-classification datasets of varying size and complexity.
  arXiv  Detail & Related papers  (2021-02-07T13:27:58Z)
• Goal-directed Generation of Discrete Structures with Conditional Generative Models [85.51463588099556]
  We introduce a novel approach to directly optimize a reinforcement learning objective, maximizing an expected reward. We test our methodology on two tasks: generating molecules with user-defined properties and identifying short python expressions which evaluate to a given target value.
  arXiv  Detail & Related papers  (2020-10-05T20:03:13Z)
• Composed Variational Natural Language Generation for Few-shot Intents [118.37774762596123]
  We generate training examples for few-shot intents in the realistic imbalanced scenario. To evaluate the quality of the generated utterances, experiments are conducted on the generalized few-shot intent detection task. Our proposed model achieves state-of-the-art performances on two real-world intent detection datasets.
  arXiv  Detail & Related papers  (2020-09-21T17:48:43Z)
• Efficient Ensemble Model Generation for Uncertainty Estimation with Bayesian Approximation in Segmentation [74.06904875527556]
  We propose a generic and efficient segmentation framework to construct ensemble segmentation models. In the proposed method, ensemble models can be efficiently generated by using the layer selection method. We also devise a new pixel-wise uncertainty loss, which improves the predictive performance.
  arXiv  Detail & Related papers  (2020-05-21T16:08:38Z)

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.