Sample based Explanations via Generalized Representers

• URL: http://arxiv.org/abs/2310.18526v1
• Date: Fri, 27 Oct 2023 22:54:47 GMT
• Title: Sample based Explanations via Generalized Representers
• Abstract summary: We show that generalized representers are the only class of sample based explanations satisfying a natural set of axiomatic properties. We discuss approaches to extract global importances given a kernel, and also natural choices of kernels given modern non-linear models.
• Score: 42.53488505266559
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose a general class of sample based explanations of machine learning models, which we term generalized representers. To measure the effect of a training sample on a model's test prediction, generalized representers use two components: a global sample importance that quantifies the importance of the training point to the model and is invariant to test samples, and a local sample importance that measures similarity between the training sample and the test point with a kernel. A key contribution of the paper is to show that generalized representers are the only class of sample based explanations satisfying a natural set of axiomatic properties. We discuss approaches to extract global importances given a kernel, and also natural choices of kernels given modern non-linear models. As we show, many popular existing sample based explanations could be cast as generalized representers with particular choices of kernels and approaches to extract global importances. Additionally, we conduct empirical comparisons of different generalized representers on two image and two text classification datasets.

Related papers

• Generalization of Diffusion Models Arises with a Balanced Representation Space [32.68561555837436]
  We analyze the distinctions between memorization and generalization in diffusion models through the lens of representation learning.<n>We show that memorization corresponds to the model storing raw training samples in the learned weights for encoding and decoding, yielding localized "spiky" representations.<n>We propose a representation-based method for detecting memorization and a training-free editing technique that allows precise control via representation steering.
  arXiv  Detail & Related papers  (2025-12-24T05:40:40Z)
• Two Is Better Than One: Aligned Representation Pairs for Anomaly Detection [56.57122939745213]
  Anomaly detection focuses on identifying samples that deviate from the norm.<n>Recent self-supervised methods have successfully learned such representations by employing prior knowledge about anomalies to create synthetic outliers during training.<n>We address this limitation with our new approach Con$$, which leverages prior knowledge about symmetries in normal samples to observe the data in different contexts.
  arXiv  Detail & Related papers  (2024-05-29T07:59:06Z)
• Towards the Visualization of Aggregated Class Activation Maps to Analyse the Global Contribution of Class Features [0.47248250311484113]
  Class Activation Maps (CAMs) visualizes the importance of each feature of a data sample contributing to the classification. We aggregate CAMs from multiple samples to show a global explanation of the classification for semantically structured data. Our approach allows an analyst to detect important features of high-dimensional data and derive adjustments to the AI model based on our global explanation visualization.
  arXiv  Detail & Related papers  (2023-07-29T11:13:11Z)
• Representer Point Selection for Explaining Regularized High-dimensional Models [105.75758452952357]
  We introduce a class of sample-based explanations we term high-dimensional representers. Our workhorse is a novel representer theorem for general regularized high-dimensional models. We study the empirical performance of our proposed methods on three real-world binary classification datasets and two recommender system datasets.
  arXiv  Detail & Related papers  (2023-05-31T16:23:58Z)
• An Additive Instance-Wise Approach to Multi-class Model Interpretation [53.87578024052922]
  Interpretable machine learning offers insights into what factors drive a certain prediction of a black-box system. Existing methods mainly focus on selecting explanatory input features, which follow either locally additive or instance-wise approaches. This work exploits the strengths of both methods and proposes a global framework for learning local explanations simultaneously for multiple target classes.
  arXiv  Detail & Related papers  (2022-07-07T06:50:27Z)
• A Model of One-Shot Generalization [6.155604731137828]
  One-shot generalization refers to the ability of an algorithm to perform transfer learning within a single task. We show that the most direct neural network architecture for our data model performs one-shot generalization almost perfectly.
  arXiv  Detail & Related papers  (2022-05-29T01:41:29Z)
• Sampling from Arbitrary Functions via PSD Models [55.41644538483948]
  We take a two-step approach by first modeling the probability distribution and then sampling from that model. We show that these models can approximate a large class of densities concisely using few evaluations, and present a simple algorithm to effectively sample from these models.
  arXiv  Detail & Related papers  (2021-10-20T12:25:22Z)
• Instance-Based Neural Dependency Parsing [56.63500180843504]
  We develop neural models that possess an interpretable inference process for dependency parsing. Our models adopt instance-based inference, where dependency edges are extracted and labeled by comparing them to edges in a training set.
  arXiv  Detail & Related papers  (2021-09-28T05:30:52Z)
• Toward Scalable and Unified Example-based Explanation and Outlier Detection [128.23117182137418]
  We argue for a broader adoption of prototype-based student networks capable of providing an example-based explanation for their prediction. We show that our prototype-based networks beyond similarity kernels deliver meaningful explanations and promising outlier detection results without compromising classification accuracy.
  arXiv  Detail & Related papers  (2020-11-11T05:58:17Z)
• Interpretable Time-series Classification on Few-shot Samples [27.05851877375113]
  This paper proposes an interpretable neural-based framework, namely textitDual Prototypical Shapelet Networks (DPSN) for few-shot time-series classification. DPSN interprets the model from dual granularity: 1) global overview using representative time series samples, and 2) local highlights using discriminative shapelets. We have derived 18 few-shot TSC datasets from public benchmark datasets and evaluated the proposed method by comparing with baselines.
  arXiv  Detail & Related papers  (2020-06-03T03:47:14Z)

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.