Paper 4 BiaScope: Visual Unfairness Diagnosis for Graph Embeddings



Agapi Rissaki, Bruno Scarone, David Liu, Aditeya pandey, Brennan Klein, Tina Eliassi-Rad, Michelle Borkin

 View presentation:2022-10-16T15:14:00ZGMT-0600Change your timezone on the schedule page
2022-10-16T15:14:00Z

Exemplar figure, described by caption below — BiaScope is an interactive tool for visual unfairness diagnosis for graph embeddings. The tool consists of three views: - (A) The Statistical Summary View summarizes key properties of the selected network. - (B) The Unfairness Comparison View is a side-by-side view that facilitates the fairness comparison of two embeddings of the same network. - (C) The Diagnose View shows the embedding subspace affecting the unfairness score of a selected node, together with its ego network. Interactive linking allows the user to investigate how bias appears in an embedding and how it relates to the relevant graph structure.

The live footage of the talk, including the Q&A, can be viewed on the session page, VDS: Opening / Keynote 1 + Paper Session 1.

Abstract