SWATI AT EWAF 2024 IN MAINZ, GERMANY

19 July 2024

Our Postdoctoral researcher, Swati Swati, attended EWAF’24 and delivered an oral presentation of our paper titled "Exploring Fusion Techniques in Multimodal AI-Based Recruitment: Insights from FairCVdb", co-authored by Swati Swati, Arjun Roy, and Eirini Ntoutsi. Her presentation was part of the “Lightning Round” at the conference, where she also showcased a poster for an in-depth discussion after the presentation.

In her presentation, she discussed the fairness and bias implications of multimodal fusion techniques in multimodal AI-based recruitment systems using the FairCVdb dataset. She explained the results, which show that multimodal fusion improves learning compared to single modalities. However, late-fusion exacerbates biases by independently learning biased models for each modality, cumulatively impacting decision fairness. In contrast, early-fusion offers greater flexibility and generally yields fairer outcomes with lower prediction error.

Please follow the link for further details about the research, including access to the paper, code, presentation slides, and poster.