cs.LGOct 9, 2024

quanda: An Interpretability Toolkit for Training Data Attribution Evaluation

Authors: Dilyara Bareeva, Galip Ümit Yolcu, Anna Hedström, Niklas Schmolenski, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin

Organizations: Fraunhofer HHI, Berlin, Germany · UMI Lab, ATB Potsdam, Germany · TU Berlin, Germany · BIFOLD, Berlin, Germany

Abstract

Training data attribution (TDA) methods estimate the influence of individual training samples on a model's predictions, offering a principled lens for interpreting neural networks. Despite rapid methodological progress, TDA evaluation remains scattered across papers and rarely reproducible, making fair comparison between methods challenging. We introduce quanda, a Python toolkit that standardizes TDA evaluation. quanda features a comprehensive collection of evaluation metrics and ready-to-use benchmarks spanning image classification, text classification, and language modeling, alongside a uniform interface for integrating diverse TDA implementations. We showcase quanda through a comparative study of existing TDA methods and find that no approach excels uniformly across metrics, with clear trade-offs between ground-truth faithfulness and downstream task performance. By consolidating the tooling around TDA, quanda equips the community to evaluate attribution methods rigorously and reproducibly. The toolkit is thoroughly tested, documented, and available as an open-source library on PyPI and at https://github.com/dilyabareeva/quanda.

Figures & tables

Appendix figures & tables17 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. dattri-LLM: A Unified and Efficient Library for Training Data Attribution at LLM Scale

    Sep 30, 2026Shixuan Liu, Tongli Zhou, Junwei Deng +2Gradient-Based AttributionTraining Data Attribution

  2. Efficient and Accurate Causal Validation of Training Data Attribution

    Nov 14, 2026Simon Vary, Alireza Mousavi-Hosseini, Roger GrosseTraining Data Attribution

  3. A Bayesian Information-Theoretic Approach to Data Attribution

    Apr 4, 2026Dharmesh Tailor, Nicolò Felicioni, Kamil CiosekTraining Data Attribution