Wrapper Boxes: Faithful Attribution of Model Predictions to Training Data

• URL: http://arxiv.org/abs/2311.08644v3
• Date: Fri, 04 Oct 2024 17:23:15 GMT
• Title: Wrapper Boxes: Faithful Attribution of Model Predictions to Training Data
• Authors: Yiheng Su, Junyi Jessy Li, Matthew Lease,
• Abstract summary: We propose a "wrapper box'' pipeline: training a neural model as usual and then using its learned feature representation in classic, interpretable models to perform prediction. Across seven language models of varying sizes, we first show that the predictive performance of wrapper classic models is largely comparable to the original neural models. Our pipeline thus preserves the predictive performance of neural language models while faithfully attributing classic model decisions to training data.
• Score: 40.7542543934205
• License:
• Abstract: Can we preserve the accuracy of neural models while also providing faithful explanations of model decisions to training data? We propose a "wrapper box'' pipeline: training a neural model as usual and then using its learned feature representation in classic, interpretable models to perform prediction. Across seven language models of varying sizes, including four large language models (LLMs), two datasets at different scales, three classic models, and four evaluation metrics, we first show that the predictive performance of wrapper classic models is largely comparable to the original neural models. Because classic models are transparent, each model decision is determined by a known set of training examples that can be directly shown to users. Our pipeline thus preserves the predictive performance of neural language models while faithfully attributing classic model decisions to training data. Among other use cases, such attribution enables model decisions to be contested based on responsible training instances. Compared to prior work, our approach achieves higher coverage and correctness in identifying which training data to remove to change a model decision. To reproduce findings, our source code is online at: https://github.com/SamSoup/WrapperBox.

Related papers

• A Two-Phase Recall-and-Select Framework for Fast Model Selection [13.385915962994806]
  We propose a two-phase (coarse-recall and fine-selection) model selection framework. It aims to enhance the efficiency of selecting a robust model by leveraging the models' training performances on benchmark datasets. It has been demonstrated that the proposed methodology facilitates the selection of a high-performing model at a rate about 3x times faster than conventional baseline methods.
  arXiv  Detail & Related papers  (2024-03-28T14:44:44Z)
• Budgeted Online Model Selection and Fine-Tuning via Federated Learning [26.823435733330705]
  Online model selection involves selecting a model from a set of candidate models 'on the fly' to perform prediction on a stream of data. The choice of candidate models henceforth has a crucial impact on the performance. The present paper proposes an online federated model selection framework where a group of learners (clients) interacts with a server with sufficient memory. Using the proposed algorithm, clients and the server collaborate to fine-tune models to adapt them to a non-stationary environment.
  arXiv  Detail & Related papers  (2024-01-19T04:02:49Z)
• TRAK: Attributing Model Behavior at Scale [79.56020040993947]
  We present TRAK (Tracing with Randomly-trained After Kernel), a data attribution method that is both effective and computationally tractable for large-scale, differenti models.
  arXiv  Detail & Related papers  (2023-03-24T17:56:22Z)
• Dataless Knowledge Fusion by Merging Weights of Language Models [51.8162883997512]
  Fine-tuning pre-trained language models has become the prevalent paradigm for building downstream NLP models. This creates a barrier to fusing knowledge across individual models to yield a better single model. We propose a dataless knowledge fusion method that merges models in their parameter space.
  arXiv  Detail & Related papers  (2022-12-19T20:46:43Z)
• Synthetic Model Combination: An Instance-wise Approach to Unsupervised Ensemble Learning [92.89846887298852]
  Consider making a prediction over new test data without any opportunity to learn from a training set of labelled data. Give access to a set of expert models and their predictions alongside some limited information about the dataset used to train them.
  arXiv  Detail & Related papers  (2022-10-11T10:20:31Z)
• Revealing Secrets From Pre-trained Models [2.0249686991196123]
  Transfer-learning has been widely adopted in many emerging deep learning algorithms. We show that pre-trained models and fine-tuned models have significantly high similarities in weight values. We propose a new model extraction attack that reveals the model architecture and the pre-trained model used by the black-box victim model.
  arXiv  Detail & Related papers  (2022-07-19T20:19:03Z)
• Model Selection, Adaptation, and Combination for Deep Transfer Learning through Neural Networks in Renewable Energies [5.953831950062808]
  We conduct the first thorough experiment for model selection and adaptation for transfer learning in renewable power forecast. We adopt models based on data from different seasons and limit the amount of training data. We show how combining multiple models through ensembles can significantly improve the model selection and adaptation approach.
  arXiv  Detail & Related papers  (2022-04-28T05:34:50Z)
• Dependency-based Mixture Language Models [53.152011258252315]
  We introduce the Dependency-based Mixture Language Models. In detail, we first train neural language models with a novel dependency modeling objective. We then formulate the next-token probability by mixing the previous dependency modeling probability distributions with self-attention.
  arXiv  Detail & Related papers  (2022-03-19T06:28:30Z)
• ModelDiff: Testing-Based DNN Similarity Comparison for Model Reuse Detection [9.106864924968251]
  ModelDiff is a testing-based approach to deep learning model similarity comparison. A study on mobile deep learning apps has shown the feasibility of ModelDiff on real-world models.
  arXiv  Detail & Related papers  (2021-06-11T15:16:18Z)
• A linearized framework and a new benchmark for model selection for fine-tuning [112.20527122513668]
  Fine-tuning from a collection of models pre-trained on different domains is emerging as a technique to improve test accuracy in the low-data regime. We introduce two new baselines for model selection -- Label-Gradient and Label-Feature Correlation. Our benchmark highlights accuracy gain with model zoo compared to fine-tuning Imagenet models.
  arXiv  Detail & Related papers  (2021-01-29T21:57:15Z)

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.