Efficient Contrastive Explanations on Demand

• URL: http://arxiv.org/abs/2412.18262v1
• Date: Tue, 24 Dec 2024 08:24:10 GMT
• Title: Efficient Contrastive Explanations on Demand
• Authors: Yacine Izza, Joao Marques-Silva,
• Abstract summary: This paper proposes novel algorithms to compute the so-called contrastive explanations for machine learning models. The paper also proposes novel algorithms for listing explanations and finding smallest contrastive explanations.
• Score: 7.109897082275965
• License:
• Abstract: Recent work revealed a tight connection between adversarial robustness and restricted forms of symbolic explanations, namely distance-based (formal) explanations. This connection is significant because it represents a first step towards making the computation of symbolic explanations as efficient as deciding the existence of adversarial examples, especially for highly complex machine learning (ML) models. However, a major performance bottleneck remains, because of the very large number of features that ML models may possess, in particular for deep neural networks. This paper proposes novel algorithms to compute the so-called contrastive explanations for ML models with a large number of features, by leveraging on adversarial robustness. Furthermore, the paper also proposes novel algorithms for listing explanations and finding smallest contrastive explanations. The experimental results demonstrate the performance gains achieved by the novel algorithms proposed in this paper.

Related papers

• Sparks of Explainability: Recent Advancements in Explaining Large Vision Models [6.1642231492615345]
  This thesis explores advanced approaches to improve explainability in computer vision by analyzing and modeling the features exploited by deep neural networks. It evaluates attribution methods, notably saliency maps, by introducing a metric based on algorithmic stability and an approach utilizing Sobol indices. Two hypotheses are examined: aligning models with human reasoning and adopting a conceptual explainability approach.
  arXiv  Detail & Related papers  (2025-02-03T04:49:32Z)
• A Theoretical Perspective for Speculative Decoding Algorithm [60.79447486066416]
  One effective way to accelerate inference is emphSpeculative Decoding, which employs a small model to sample a sequence of draft tokens and a large model to validate. This paper tackles this gap by conceptualizing the decoding problem via markov chain abstraction and studying the key properties, emphoutput quality and inference acceleration, from a theoretical perspective.
  arXiv  Detail & Related papers  (2024-10-30T01:53:04Z)
• Explaining Text Similarity in Transformer Models [52.571158418102584]
  Recent advances in explainable AI have made it possible to mitigate limitations by leveraging improved explanations for Transformers. We use BiLRP, an extension developed for computing second-order explanations in bilinear similarity models, to investigate which feature interactions drive similarity in NLP models. Our findings contribute to a deeper understanding of different semantic similarity tasks and models, highlighting how novel explainable AI methods enable in-depth analyses and corpus-level insights.
  arXiv  Detail & Related papers  (2024-05-10T17:11:31Z)
• From Robustness to Explainability and Back Again [3.7950144463212134]
  This paper addresses the poor scalability of formal explainability and proposes novel efficient algorithms for computing formal explanations. The proposed algorithm computes explanations by answering instead a number of queries, and such robustness that the number of such queries is at most linear on the number of features.
  arXiv  Detail & Related papers  (2023-06-05T17:21:05Z)
• Learning with Explanation Constraints [91.23736536228485]
  We provide a learning theoretic framework to analyze how explanations can improve the learning of our models. We demonstrate the benefits of our approach over a large array of synthetic and real-world experiments.
  arXiv  Detail & Related papers  (2023-03-25T15:06:47Z)
• Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces [14.70409833767752]
  Explainable AI aims to overcome the black-box nature of complex ML models like neural networks by generating explanations for their predictions. We propose two new analyses, extending principles found in PCA or ICA to explanations. These novel analyses, which we call principal relevant component analysis (PRCA) and disentangled relevant subspace analysis (DRSA), maximize relevance instead of e.g. variance or kurtosis.
  arXiv  Detail & Related papers  (2022-12-30T18:04:25Z)
• Invariant Causal Mechanisms through Distribution Matching [86.07327840293894]
  In this work we provide a causal perspective and a new algorithm for learning invariant representations. Empirically we show that this algorithm works well on a diverse set of tasks and in particular we observe state-of-the-art performance on domain generalization.
  arXiv  Detail & Related papers  (2022-06-23T12:06:54Z)
• ASTERYX : A model-Agnostic SaT-basEd appRoach for sYmbolic and score-based eXplanations [26.500149465292246]
  This paper proposes a generic approach named ASTERYX allowing to generate both symbolic explanations and score-based ones. Our experimental results show the feasibility of the proposed approach and its effectiveness in providing symbolic and score-based explanations.
  arXiv  Detail & Related papers  (2022-06-23T08:37:32Z)
• Deep Equilibrium Assisted Block Sparse Coding of Inter-dependent Signals: Application to Hyperspectral Imaging [71.57324258813675]
  A dataset of inter-dependent signals is defined as a matrix whose columns demonstrate strong dependencies. A neural network is employed to act as structure prior and reveal the underlying signal interdependencies. Deep unrolling and Deep equilibrium based algorithms are developed, forming highly interpretable and concise deep-learning-based architectures.
  arXiv  Detail & Related papers  (2022-03-29T21:00:39Z)
• Understanding Neural Abstractive Summarization Models via Uncertainty [54.37665950633147]
  seq2seq abstractive summarization models generate text in a free-form manner. We study the entropy, or uncertainty, of the model's token-level predictions. We show that uncertainty is a useful perspective for analyzing summarization and text generation models more broadly.
  arXiv  Detail & Related papers  (2020-10-15T16:57:27Z)

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.