mlsanityData to 7 Oct 2026

Picasso: Model-free Feature Visualization

arXiv 2111.12795 ↗First posted 24 Nov 2021cs.HC cs.AI cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Today, Machine Learning (ML) applications can have access to tens of thousands of features. With such feature sets, efficiently browsing and curating subsets of most relevant features is a challenge. In this paper, we present a novel approach to visualize up to several thousands of features in a single image. The image not only shows information on individual features, but also expresses feature interactions via the relative positioning of features.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 3 of its 13 references that are in the map. First posted on arXiv 24 Nov 2021.

Builds on

3 of 13 references.

References · 3

  1. 2020Captum: A unified and generic model interpretability library for PyTorchcited by 542
  2. 2019Understanding Neural Networks via Feature Visualization: A surveycited by 65
  3. 2019Maximum Relevance and Minimum Redundancy Feature Selection Methods for a Marketing Machine Learning Platformcited by 16

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Efficient Multi-stage Inference on Tabular Datacited by 0