Obstructing Classification via Projection Article Swipe

MAKE IMPACT

Pantea Haghighatkhah , Wouter Meulemans , Bettina Speckman , Jérôme Urhausen , Kevin Verbeek · YOU? · · 2021 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2105.09047

Machine learning and data mining techniques are effective tools to classify large amounts of data. But they tend to preserve any inherent bias in the data, for example, with regards to gender or race. Removing such bias from data or the learned representations is quite challenging. In this paper we study a geometric problem which models a possible approach for bias removal. Our input is a set of points P in Euclidean space R^d and each point is labeled with k binary-valued properties. A priori we assume that it is "easy" to classify the data according to each property. Our goal is to obstruct the classification according to one property by a suitable projection to a lower-dimensional Euclidean space R^m (m < d), while classification according to all other properties remains easy. What it means for classification to be easy depends on the classification model used. We first consider classification by linear separability as employed by support vector machines. We use Kirchberger's Theorem to show that, under certain conditions, a simple projection to R^(d-1) suffices to eliminate the linear separability of one of the properties whilst maintaining the linear separability of the other properties. We also study the problem of maximizing the linear "inseparability" of the chosen property. Second, we consider more complex forms of separability and prove a connection between the number of projections required to obstruct classification and the Helly-type properties of such separabilities.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2105.09047

PDF

https://arxiv.org/pdf/2105.09047

OA Status

green

Cited By

1

References

26

Related Works

10

OpenAlex ID

https://openalex.org/W3160467181

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W3160467181

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2105.09047

Digital Object Identifier

Title

Obstructing Classification via Projection

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2021

Year of publication

Publication date

2021-05-19

Full publication date if available

Authors

Pantea Haghighatkhah, Wouter Meulemans, Bettina Speckman, Jérôme Urhausen, Kevin Verbeek

List of authors in order

Landing page

https://arxiv.org/abs/2105.09047

Publisher landing page

PDF URL

https://arxiv.org/pdf/2105.09047

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2105.09047

Direct OA link when available

Concepts

Projection (relational algebra), Computer science, Artificial intelligence, Algorithm

Top concepts (fields/topics) attached by OpenAlex

Cited by

1

Total citation count in OpenAlex

Citations by year (recent)

2023: 1

Per-year citation counts (last 5 years)

References (count)

26

Number of works referenced by this work

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload