Automated Data Slicing for Model Validation: A Big data - AI Integration Approach

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 28
  • Download : 0
As machine learning systems become democratized, it becomes increasingly important to help users easily debug their models. However, current data tools are still primitive when it comes to helping users trace model performance problems all the way to the data. We focus on the particular problem of slicing data to identify subsets of the validation data where the model performs poorly. This is an important problem in model validation because the overall model performance can fail to reflect that of the smaller subsets, and slicing allows users to analyze the model performance on a more granular-level. Unlike general techniques (e.g., clustering) that can find arbitrary slices, our goal is to find interpretable slices (which are easier to take action compared to arbitrary subsets) that are problematic and large. We propose mathsf{Slice Finder}SliceFinder, which is an interactive framework for identifying such slices using statistical techniques. Applications include diagnosing model fairness and fraud detection, where identifying slices that are interpretable to humans is crucial. This research is part of a larger trend of Big data and Artificial Intelligence (AI) integration and opens many opportunities for new research.
Publisher
IEEE COMPUTER SOC
Issue Date
2020-12
Language
English
Article Type
Article
Citation

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, v.32, no.12, pp.2284 - 2296

ISSN
1041-4347
DOI
10.1109/TKDE.2019.2916074
URI
http://hdl.handle.net/10203/277618
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0